From 6a801372ac54cbe405bef4692007bb0347f84680 Mon Sep 17 00:00:00 2001 From: mateo Date: Tue, 20 Oct 2026 17:45:30 +0000 Subject: [PATCH 01/66] fix(bedrock): add Claude Mantle model helper Minimal prerequisite from #43646 for stable/1.104.x. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/llms/bedrock_mantle/common_utils.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/litellm/llms/bedrock_mantle/common_utils.py b/litellm/llms/bedrock_mantle/common_utils.py index 9892ef6224e..7e929f607dd 100644 --- a/litellm/llms/bedrock_mantle/common_utils.py +++ b/litellm/llms/bedrock_mantle/common_utils.py @@ -45,6 +45,10 @@ def split_mantle_region_prefix(model: str) -> tuple[str | None, str]: return None, model +def is_mantle_claude_model(model: str) -> bool: + return "claude" in model.lower() + + def resolve_mantle_region(params: Mapping[str, object]) -> str: region: Final = params.get("aws_region_name") if isinstance(region, str) and region: From f9a1d5ea7a073cd8088f6d945258914c25f7abb1 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 20 Oct 2026 17:45:51 +0000 Subject: [PATCH 02/66] fix(bedrock): count tokens on bedrock-mantle when bedrock-runtime cannot count a Claude model (#45317) Backport of #45317 to stable/1.104.x. Cherry-picked from 577d74c1ceb73c31c05f4677c6df3a68d53b924c (main). Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../count_tokens/bedrock_token_counter.py | 180 +-- litellm/llms/bedrock/count_tokens/handler.py | 2 +- .../bedrock/count_tokens/mantle_handler.py | 106 ++ .../test_messages_count_tokens_bedrock_e2e.py | 70 ++ .../test_bedrock_mantle_count_tokens_wire.py | 1072 +++++++++++++++++ ...est_bedrock_mantle_count_tokens_handler.py | 109 ++ .../test_bedrock_token_counter.py | 140 +++ tests/unit/proxy/test_proxy_token_counter.py | 90 +- 8 files changed, 1652 insertions(+), 117 deletions(-) create mode 100644 litellm/llms/bedrock/count_tokens/mantle_handler.py create mode 100644 tests/e2e/llm_translation/test_messages_count_tokens_bedrock_e2e.py create mode 100644 tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py create mode 100644 tests/unit/llms/bedrock/count_tokens/test_bedrock_mantle_count_tokens_handler.py create mode 100644 tests/unit/llms/bedrock/count_tokens/test_bedrock_token_counter.py diff --git a/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py b/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py index 57bbb5b6cb6..65a6aee027c 100644 --- a/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py +++ b/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py @@ -3,29 +3,100 @@ Bedrock Token Counter implementation using the CountTokens API. """ from collections.abc import Mapping, Sequence +from dataclasses import dataclass from typing import Any, Final from pydantic import JsonValue +from typing_extensions import assert_never from litellm._logging import verbose_logger from litellm.llms.base_llm.base_utils import BaseTokenCounter from litellm.llms.bedrock.common_utils import BedrockError, get_bedrock_base_model from litellm.llms.bedrock.count_tokens.handler import BedrockCountTokensHandler -from litellm.types.utils import LlmProviders, TokenCountMessagesFormat, TokenCountResponse +from litellm.llms.bedrock.count_tokens.mantle_handler import BedrockMantleCountTokensHandler +from litellm.llms.bedrock_mantle.common_utils import is_mantle_claude_model +from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler +from litellm.types.utils import LiteLLMPydanticObjectBase, LlmProviders, TokenCountMessagesFormat, TokenCountResponse + +RUNTIME_TOKENIZER_TYPE: Final = "bedrock_api" +MANTLE_TOKENIZER_TYPE: Final = "bedrock_mantle_api" + + +class _CountTokensReply(LiteLLMPydanticObjectBase): + input_tokens: int + + +@dataclass(frozen=True, slots=True) +class CountedTokens: + input_tokens: int + original_response: Mapping[str, JsonValue] + tokenizer_type: str + + +@dataclass(frozen=True, slots=True) +class CountTokensFailure: + status_code: int + message: str + tokenizer_type: str + + +CountTokensOutcome = CountedTokens | CountTokensFailure + + +def _runtime_rejected_claude_model(outcome: CountTokensOutcome, resolved_model: str) -> bool: + return ( + isinstance(outcome, CountTokensFailure) + and outcome.status_code == 400 + and is_mantle_claude_model(resolved_model) + ) class BedrockTokenCounter(BaseTokenCounter): - """Token counter implementation for AWS Bedrock provider using the CountTokens API.""" + """Token counter for AWS Bedrock: bedrock-runtime CountTokens first, and Anthropic's count_tokens + on bedrock-mantle for the Claude models bedrock-runtime answers 400 for""" + + def __init__( + self, + runtime_handler: BedrockCountTokensHandler | None = None, + mantle_handler: BedrockMantleCountTokensHandler | None = None, + client: AsyncHTTPHandler | None = None, + ) -> None: + self._runtime_handler: Final = runtime_handler or BedrockCountTokensHandler() + self._mantle_handler: Final = mantle_handler or BedrockMantleCountTokensHandler() + self._client: Final = client def should_use_token_counting_api( self, custom_llm_provider: str | None = None, ) -> bool: - """ - Returns True if we should use the Bedrock CountTokens API for token counting. - """ return custom_llm_provider == LlmProviders.BEDROCK.value + async def _count_with( + self, + handler: BedrockCountTokensHandler | BedrockMantleCountTokensHandler, + tokenizer_type: str, + request_data: dict[str, object], + litellm_params: dict[str, object], + resolved_model: str, + ) -> CountTokensOutcome: + try: + result: Final = await handler.handle_count_tokens_request( + request_data=request_data, + litellm_params=litellm_params, + resolved_model=resolved_model, + client=self._client, + ) + reply: Final = _CountTokensReply.model_validate(result) + except BedrockError as e: + verbose_logger.debug( + "%s CountTokens API error: status=%s, message=%s", tokenizer_type, e.status_code, e.message + ) + return CountTokensFailure(status_code=e.status_code, message=e.message, tokenizer_type=tokenizer_type) + except Exception as e: + verbose_logger.debug("Error calling %s CountTokens API: %s", tokenizer_type, e) + return CountTokensFailure(status_code=500, message=str(e), tokenizer_type=tokenizer_type) + return CountedTokens(input_tokens=reply.input_tokens, original_response=result, tokenizer_type=tokenizer_type) + async def count_tokens( self, model_to_use: str, @@ -38,81 +109,52 @@ class BedrockTokenCounter(BaseTokenCounter): messages_format: TokenCountMessagesFormat = "anthropic", output_format: JsonValue = None, ) -> TokenCountResponse | None: - """ - Count tokens using AWS Bedrock's CountTokens API. - - This method calls the existing BedrockCountTokensHandler to make an API call - to Bedrock's token counting endpoint, bypassing the local tiktoken-based counting. - - Args: - model_to_use: The model identifier - messages: The messages to count tokens for - contents: Alternative content format (not used for Bedrock) - deployment: Deployment configuration containing litellm_params - request_model: The original request model name - - Returns: - TokenCountResponse with token count, or None if counting fails - """ if not messages: return None - deployment = deployment or {} - litellm_params: Final = deployment.get("litellm_params", {}) - - # Build request data in the format expected by BedrockCountTokensHandler + litellm_params: Final = (deployment or {}).get("litellm_params", {}) request_data: Final[dict[str, object]] = { "model": model_to_use, "messages": messages, + **({"tools": tools} if tools else {}), + **({"system": system} if system else {}), } - - if tools: - request_data["tools"] = tools - - if system: - request_data["system"] = system - - # Get the resolved model (strip prefixes like bedrock/, converse/, etc.) resolved_model: Final = get_bedrock_base_model(model_to_use) - try: - handler: Final = BedrockCountTokensHandler() - result: Final = await handler.handle_count_tokens_request( - request_data=request_data, - litellm_params=litellm_params, - resolved_model=resolved_model, + runtime: Final = await self._count_with( + self._runtime_handler, RUNTIME_TOKENIZER_TYPE, request_data, litellm_params, resolved_model + ) + outcome: Final = ( + await self._count_with( + self._mantle_handler, MANTLE_TOKENIZER_TYPE, request_data, litellm_params, resolved_model ) - - # Transform response to TokenCountResponse - if result is not None: + if _runtime_rejected_claude_model(runtime, resolved_model) + else runtime + ) + match outcome: + case CountedTokens(): return TokenCountResponse( - total_tokens=result.get("input_tokens", 0), + total_tokens=outcome.input_tokens, request_model=request_model, model_used=model_to_use, - tokenizer_type="bedrock_api", - original_response=result, + tokenizer_type=outcome.tokenizer_type, + original_response=dict(outcome.original_response), ) - except BedrockError as e: - verbose_logger.warning("Bedrock CountTokens API error: status=%s, message=%s", e.status_code, e.message) - return TokenCountResponse( - total_tokens=0, - request_model=request_model, - model_used=model_to_use, - tokenizer_type="bedrock_api", - error=True, - error_message=e.message, - status_code=e.status_code, - ) - except Exception as e: - verbose_logger.warning("Error calling Bedrock CountTokens API: %s", e) - return TokenCountResponse( - total_tokens=0, - request_model=request_model, - model_used=model_to_use, - tokenizer_type="bedrock_api", - error=True, - error_message=str(e), - status_code=500, - ) - - return None + case CountTokensFailure(): + verbose_logger.warning( + "%s CountTokens API error: status=%s, message=%s", + outcome.tokenizer_type, + outcome.status_code, + outcome.message, + ) + return TokenCountResponse( + total_tokens=0, + request_model=request_model, + model_used=model_to_use, + tokenizer_type=outcome.tokenizer_type, + error=True, + error_message=outcome.message, + status_code=outcome.status_code, + ) + case _: + assert_never(outcome) diff --git a/litellm/llms/bedrock/count_tokens/handler.py b/litellm/llms/bedrock/count_tokens/handler.py index d7fb510f057..be8243e48ef 100644 --- a/litellm/llms/bedrock/count_tokens/handler.py +++ b/litellm/llms/bedrock/count_tokens/handler.py @@ -125,7 +125,7 @@ class BedrockCountTokensHandler(BedrockCountTokensConfig): raise except httpx.HTTPStatusError as e: # HTTP errors - preserve the actual status code - verbose_logger.error("HTTP error in CountTokens handler: %s", e) + verbose_logger.debug("HTTP error in CountTokens handler: %s", e) raise BedrockError( status_code=e.response.status_code, message=e.response.text, diff --git a/litellm/llms/bedrock/count_tokens/mantle_handler.py b/litellm/llms/bedrock/count_tokens/mantle_handler.py new file mode 100644 index 00000000000..9cc13ac0bf4 --- /dev/null +++ b/litellm/llms/bedrock/count_tokens/mantle_handler.py @@ -0,0 +1,106 @@ +from typing import Final + +import httpx +from pydantic import JsonValue, TypeAdapter +from typing_extensions import NotRequired, ReadOnly, TypedDict + +import litellm +from litellm._logging import verbose_logger +from litellm.llms.anthropic.count_tokens.transformation import ( + COUNT_TOKEN_OPTION_NAMES, + AnthropicCountTokensConfig, +) +from litellm.llms.bedrock.base_aws_llm import BaseAWSLLM, run_aws_signing +from litellm.llms.bedrock.common_utils import BedrockError, build_mantle_messages_url +from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, get_async_httpx_client + +MANTLE_COUNT_TOKENS_SUFFIX: Final = "/count_tokens" +MANTLE_ANTHROPIC_VERSION: Final = "2023-06-01" + + +class MantleCountTokensRequest(TypedDict): + messages: ReadOnly[list[dict[str, JsonValue]]] + system: ReadOnly[NotRequired[JsonValue]] + tools: ReadOnly[NotRequired[list[dict[str, JsonValue]]]] + + +_COUNT_REQUEST: Final = TypeAdapter(MantleCountTokensRequest) +_COUNT_RESPONSE: Final = TypeAdapter(dict[str, JsonValue]) +_COUNT_OPTIONS: Final[TypeAdapter[Mapping[str, JsonValue]]] = TypeAdapter(Mapping[str, JsonValue]) + + +class BedrockMantleCountTokensHandler(BaseAWSLLM): + """Counts tokens through Anthropic's count_tokens on the bedrock-mantle endpoint. + + Claude models that Bedrock offers only through cross-region inference answer 400 on + bedrock-runtime's CountTokens; AWS documents Mantle's /anthropic/v1/messages/count_tokens + as the way to count them, with the base model id and the deployment's AWS credentials + """ + + def __init__(self, anthropic_config: AnthropicCountTokensConfig | None = None) -> None: + super().__init__() + self._anthropic_config: Final = anthropic_config or AnthropicCountTokensConfig() + + def get_mantle_count_tokens_endpoint(self, aws_region_name: str) -> str: + messages_url: Final = build_mantle_messages_url( + api_base=None, aws_bedrock_runtime_endpoint=None, region=aws_region_name + ) + return f"{messages_url}{MANTLE_COUNT_TOKENS_SUFFIX}" + + async def handle_count_tokens_request( + self, + request_data: dict[str, object], + litellm_params: dict[str, object], + resolved_model: str, + client: AsyncHTTPHandler | None = None, + ) -> dict[str, JsonValue]: + try: + request: Final = _COUNT_REQUEST.validate_python(request_data) + aws_region_name: Final = self._get_aws_region_name( + optional_params=litellm_params, model=resolved_model, model_id=None + ) + endpoint_url: Final = self.get_mantle_count_tokens_endpoint(aws_region_name) + body: Final = self._anthropic_config.transform_request_to_count_tokens( + model=resolved_model, + messages=request["messages"], + tools=request.get("tools"), + system=request.get("system"), + optional_params=_COUNT_OPTIONS.validate_python( + {name: value for name, value in request_data.items() if name in COUNT_TOKEN_OPTION_NAMES} + ), + ) + verbose_logger.debug("Making bedrock-mantle count_tokens request to: %s", endpoint_url) + api_key: Final = litellm_params.get("api_key") + signed_headers, signed_body = await run_aws_signing( + self._sign_request, + service_name="bedrock", + headers={"Content-Type": "application/json", "anthropic-version": MANTLE_ANTHROPIC_VERSION}, + optional_params=litellm_params, + request_data=body, + api_base=endpoint_url, + model=resolved_model, + api_key=api_key if isinstance(api_key, str) else None, + ) + async_client: Final = client or get_async_httpx_client(llm_provider=litellm.LlmProviders.BEDROCK) + response: Final = await async_client.post( + endpoint_url, headers=signed_headers, data=signed_body, timeout=30.0 + ) + if response.status_code != 200: + raise BedrockError( + status_code=response.status_code, + message=response.text, + headers=response.headers, + response=response, + ) + return _COUNT_RESPONSE.validate_json(response.content) + except BedrockError: + raise + except httpx.HTTPStatusError as e: + raise BedrockError( + status_code=e.response.status_code, + message=e.response.text, + headers=e.response.headers, + response=e.response, + ) + except Exception as e: + raise BedrockError(status_code=500, message=f"bedrock-mantle count_tokens processing error: {e}") diff --git a/tests/e2e/llm_translation/test_messages_count_tokens_bedrock_e2e.py b/tests/e2e/llm_translation/test_messages_count_tokens_bedrock_e2e.py new file mode 100644 index 00000000000..ee5cd54e4e0 --- /dev/null +++ b/tests/e2e/llm_translation/test_messages_count_tokens_bedrock_e2e.py @@ -0,0 +1,70 @@ +"""Live e2e: `/v1/messages/count_tokens` on a Bedrock Claude model that bedrock-runtime +cannot count. + +Claude Opus 4.8 is offered only through cross-region inference, and bedrock-runtime's +CountTokens answers 400 for it. The proxy then has to count through bedrock-mantle's +Anthropic count_tokens, and the answer must sit within a few percent of what `/v1/messages` +bills as `usage.input_tokens`. The local tokenizer fallback undercounts these models by +about 40%, so this is the line that proves the real count is served. Both calls go through +the real Anthropic SDK, the client customers count with +""" + +from __future__ import annotations + +from typing import Final + +import pytest +from anthropic.types import MessageParam +from e2e_config import unique_marker +from e2e_metadata import Domain, Provider, Route, Subject, meta +from lifecycle import ResourceManager +from models import LiteLLMParamsBody +from proxy_client import ProxyClient +from sdk_clients import NO_PROXY_CACHE, SdkClients + +pytestmark = pytest.mark.e2e + +CROSS_REGION_ONLY_CLAUDE_BACKEND: Final = "bedrock/global.anthropic.claude-opus-4-8" +COUNT_TOLERANCE: Final = 0.05 + + +def _register(proxy: ProxyClient, resources: ResourceManager, backend: str) -> tuple[str, str]: + model: Final = f"e2e-count-tokens-bedrock-{unique_marker()}" + model_id: Final = proxy.create_model( + model, + LiteLLMParamsBody( + model=backend, + aws_access_key_id="os.environ/AWS_ACCESS_KEY_ID", + aws_secret_access_key="os.environ/AWS_SECRET_ACCESS_KEY", + aws_region_name="os.environ/AWS_REGION", + ), + ) + resources.defer(lambda: proxy.delete_model(model_id)) + return model, resources.key() + + +class TestBedrockMessagesCountTokens: + @meta( + Subject( + domain=Domain.LLM_TRANSLATION, + route=Route.COUNT_TOKENS, + providers=(Provider.BEDROCK,), + models=(CROSS_REGION_ONLY_CLAUDE_BACKEND,), + ) + ) + def test_count_matches_billed_input_tokens_for_a_model_bedrock_runtime_cannot_count( + self, proxy: ProxyClient, resources: ResourceManager, sdk: SdkClients + ) -> None: + model, key = _register(proxy, resources, CROSS_REGION_ONLY_CLAUDE_BACKEND) + client: Final = sdk.anthropic(key) + prompt: Final = f"{unique_marker()} " + "The quick brown fox jumps over the lazy dog. " * 40 + message: Final[MessageParam] = {"role": "user", "content": prompt} + + counted: Final = client.messages.count_tokens(model=model, messages=[message]) + answered: Final = client.messages.create( + model=model, max_tokens=1, messages=[message], extra_body=NO_PROXY_CACHE + ) + + billed: Final = answered.usage.input_tokens + assert billed, answered.usage + assert abs(counted.input_tokens - billed) <= billed * COUNT_TOLERANCE, (counted, answered.usage) diff --git a/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py b/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py new file mode 100644 index 00000000000..f9d4f7f91bb --- /dev/null +++ b/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py @@ -0,0 +1,1072 @@ +import asyncio +import json +import re +import signal +import socket +import threading +import uuid +from collections.abc import Callable, Iterator, Mapping, Sequence +from concurrent.futures import Future, ThreadPoolExecutor +from contextlib import ExitStack +from pathlib import Path +from queue import SimpleQueue +from types import MappingProxyType +from typing import Final + +import anthropic +import httpx +import psutil +import pytest +import yaml +from anthropic.types import MessageCountTokensToolParam, MessageParam +from integration._support.bedrock_runtime_peer import answer, marker_of, target_of +from integration._support.bedrock_runtime_peer import respond as runtime_generation +from integration._support.client import Gateway, Scenario, eventually, gateway_from_environment, object_value +from integration._support.process import OwnedProxy, graceful_stop_seconds, owned_proxy_process +from integration._support.wire import Reply, Request, Wire, wire_server +from pydantic import JsonValue, TypeAdapter + +pytestmark = pytest.mark.timeout(2 * graceful_stop_seconds() + 120) + +_OPUS: Final = "global.anthropic.claude-opus-4-8" +_OPUS_BASE: Final = "anthropic.claude-opus-4-8" +_SONNET: Final = "anthropic.claude-sonnet-4-6" +_NOVA: Final = "amazon.nova-lite-v1:0" +_REGION: Final = "us-east-1" +_OWNED_OPUS: Final = "mantle-opus" +_OWNED_SONNET: Final = "mantle-sonnet" +_OWNED_NOVA: Final = "mantle-nova" +_OWNED_MODELS: Final = MappingProxyType({_OWNED_OPUS: _OPUS, _OWNED_SONNET: _SONNET, _OWNED_NOVA: _NOVA}) +_ACCESS_KEY: Final = "AKIAINTEGRATIONMANTLE" +_SECRET_KEY: Final = "integration-mantle-secret" +_SIGV4_SCOPE: Final = f"/{_REGION}/bedrock/aws4_request" +_MANTLE_TARGET: Final = "/anthropic/v1/messages/count_tokens" +_MANTLE_VERSION: Final = "2023-06-01" +_MANTLE_COUNT: Final = 4242 +_RUNTIME_COUNT: Final = 1345 +_UNSUPPORTED: Final = "The provided model doesn't support counting tokens." +_REJECTION: Final = "scripted mantle rejection" +_COUNT_TARGET: Final = re.compile(r"^/model/(.+)/count-tokens$") +_INVOKE_TARGET: Final = re.compile(r"^/model/(.+)/invoke$") +_SCRIPTED_STATUS: Final = re.compile(r"status=(\d{3})") +_STARTED_WORKER: Final = re.compile(r"Started server process \[(\d+)\]") +_JSON_OBJECT: Final = TypeAdapter(dict[str, JsonValue]) +_JSON_LIST: Final = TypeAdapter(list[JsonValue]) + +_SDK_MESSAGES: Final[list[MessageParam]] = [{"role": "user", "content": "Count this message"}] +_MESSAGES: Final = _JSON_LIST.validate_json(json.dumps(_SDK_MESSAGES)) +_SYSTEM: Final = "You are a terse assistant that answers in one sentence" +_SYSTEM_BLOCKS: Final[list[JsonValue]] = [ + {"type": "text", "text": "You are a terse assistant"}, + {"type": "text", "text": "Answer in one sentence"}, +] +_SDK_TOOLS: Final[list[MessageCountTokensToolParam]] = [ + { + "name": "get_weather", + "description": "Look up the current weather for a city", + "input_schema": { + "type": "object", + "properties": {"city": {"type": "string", "description": "City to look up"}}, + "required": ["city"], + }, + } +] +_TOOLS: Final = _JSON_LIST.validate_json(json.dumps(_SDK_TOOLS)) +_GEMINI_BODY: Final[dict[str, JsonValue]] = {"contents": [{"role": "user", "parts": [{"text": "Count this"}]}]} +_GEMINI_MESSAGES: Final[list[JsonValue]] = [{"role": "user", "content": "Count this"}] + + +def _mantle_body(**fields: JsonValue) -> dict[str, JsonValue]: + return {"model": _OPUS_BASE, "messages": _MESSAGES, **fields} + + +_MANTLE_BARE: Final = _mantle_body() +_MANTLE_FULL: Final = _mantle_body(system=_SYSTEM, tools=_TOOLS) + + +def _json_reply(status: int, payload: Mapping[str, JsonValue]) -> Reply: + return Reply(status=status, body=json.dumps(payload).encode()) + + +def _runtime_count(request: Request, model: str) -> Reply: + scripted: Final = _SCRIPTED_STATUS.search(request.body.decode(errors="replace")) + if scripted is not None: + return _json_reply(int(scripted.group(1)), {"message": f"scripted {scripted.group(1)}"}) + if "sonnet" in model: + return _json_reply(200, {"inputTokens": _RUNTIME_COUNT}) + return _json_reply(400, {"message": _UNSUPPORTED}) + + +def _invoke_reply(marker: str) -> Reply: + return _json_reply( + 200, + { + "id": f"msg_{marker}", + "type": "message", + "role": "assistant", + "model": _OPUS_BASE, + "content": [{"type": "text", "text": answer(marker)}], + "stop_reason": "end_turn", + "stop_sequence": None, + "usage": {"input_tokens": 5, "output_tokens": 3}, + }, + ) + + +def _runtime(request: Request) -> Reply: + target: Final = target_of(request) + counted: Final = _COUNT_TARGET.match(target) + if counted is not None: + return _runtime_count(request, counted.group(1)) + if _INVOKE_TARGET.match(target): + return _invoke_reply(marker_of(request)) + return runtime_generation(request) + + +def _mantle_counted(_request: Request) -> Reply: + return _json_reply(200, {"input_tokens": _MANTLE_COUNT}) + + +def _rejected(status: int) -> Reply: + return _json_reply(status, {"type": "error", "error": {"type": "invalid_request_error", "message": _REJECTION}}) + + +def _rejecting(status: int) -> Callable[[Request], Reply]: + def count(_request: Request) -> Reply: + return _rejected(status) + + return count + + +def _anthropic_message(message: JsonValue) -> bool: + return isinstance(message, dict) and message.get("role") in ("user", "assistant") + + +def _anthropic_tool(tool: JsonValue) -> bool: + return isinstance(tool, dict) and isinstance(tool.get("name"), str) and isinstance(tool.get("input_schema"), dict) + + +def _strict(request: Request) -> Reply: + body: Final = _JSON_OBJECT.validate_json(request.body) + messages: Final = body.get("messages") + tools: Final = body.get("tools", []) + accepted: Final = ( + isinstance(messages, list) + and all(map(_anthropic_message, messages)) + and isinstance(body.get("system", ""), (str, list)) + and isinstance(tools, list) + and all(map(_anthropic_tool, tools)) + ) + return _mantle_counted(request) if accepted else _rejected(400) + + +def _mantle(count: Callable[[Request], Reply] = _mantle_counted) -> Callable[[Request], Reply]: + def respond(request: Request) -> Reply: + if request.target == _MANTLE_TARGET: + return count(request) + return _json_reply(404, {"error": f"unscripted mantle target {request.target}"}) + + return respond + + +def _mantle_environment(port: int) -> Mapping[str, str]: + return {"BEDROCK_MANTLE_API_BASE": f"http://127.0.0.1:{port}"} + + +_INHERITED_BEARER: Final = ("AWS_BEARER_TOKEN_BEDROCK",) + + +def _reserved_port() -> int: + with socket.socket() as reserve: + reserve.bind(("127.0.0.1", 0)) + return reserve.getsockname()[1] + + +def _closed_port_url() -> str: + return f"http://127.0.0.1:{_reserved_port()}" + + +@pytest.fixture(scope="module") +def mantle_port() -> int: + return _reserved_port() + + +@pytest.fixture(scope="module") +def counting_proxy(tmp_path_factory: pytest.TempPathFactory, mantle_port: int) -> Iterator[OwnedProxy]: + with ( + gateway_from_environment() as gateway, + owned_proxy_process( + gateway, + tmp_path_factory.mktemp("mantle-count"), + _mantle_environment(mantle_port), + workers=1, + remove_environment=_INHERITED_BEARER, + ) as owned, + ): + yield owned + + +def _litellm_params(model: str, api_base: str) -> dict[str, JsonValue]: + return { + "model": f"bedrock/{model}", + "api_base": api_base, + "aws_access_key_id": _ACCESS_KEY, + "aws_secret_access_key": _SECRET_KEY, + "aws_region_name": _REGION, + } + + +def _owned_config(path: Path, runtime_url: str, settings: Mapping[str, JsonValue]) -> Path: + config: Final = object_value(yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text())) + litellm_settings: Final = object_value(config["litellm_settings"]) + path.write_text( + yaml.safe_dump( + { + **config, + "model_list": [ + {"model_name": name, "litellm_params": _litellm_params(model, runtime_url)} + for name, model in _OWNED_MODELS.items() + ], + "litellm_settings": {**litellm_settings, **settings}, + } + ) + ) + return path + + +def _deployment(scenario: Scenario, api_base: str, model: str = _OPUS) -> str: + return scenario.model(model_info=None, api_key=None, **_litellm_params(model, api_base)) + + +def _bare(model: str) -> dict[str, JsonValue]: + return {"model": model, "messages": _MESSAGES} + + +def _full(model: str) -> dict[str, JsonValue]: + return {**_bare(model), "system": _SYSTEM, "tools": _TOOLS} + + +def _count(gateway: Gateway, body: Mapping[str, JsonValue]) -> httpx.Response: + return gateway.request("POST", "/v1/messages/count_tokens", body) + + +def _payload(response: httpx.Response) -> dict[str, JsonValue]: + assert response.status_code == 200, response.text + return _JSON_OBJECT.validate_json(response.content) + + +def _local_count(gateway: Gateway, body: Mapping[str, JsonValue]) -> int: + response: Final = gateway.request("POST", "/utils/token_counter", body, params={"call_endpoint": "false"}) + payload: Final = _payload(response) + total: Final = payload["total_tokens"] + assert payload["tokenizer_type"] not in ("bedrock_api", "bedrock_mantle_api"), response.text + assert isinstance(total, int) and total > 0 and total not in (_MANTLE_COUNT, _RUNTIME_COUNT), response.text + return total + + +def _assert_sigv4(request: Request) -> None: + authorization: Final = request.headers.get("authorization", "") + assert authorization.startswith(f"AWS4-HMAC-SHA256 Credential={_ACCESS_KEY}/"), request.headers + assert _SIGV4_SCOPE in authorization, authorization + + +def _mantle_requests(requests: Sequence[Request]) -> tuple[dict[str, JsonValue], ...]: + for request in requests: + assert (request.method, request.target) == ("POST", _MANTLE_TARGET), request.target + assert request.headers["anthropic-version"] == _MANTLE_VERSION, request.headers + assert request.headers["content-type"] == "application/json", request.headers + _assert_sigv4(request) + return tuple(_JSON_OBJECT.validate_json(request.body) for request in requests) + + +def _mantle_bodies(wire: Wire) -> tuple[dict[str, JsonValue], ...]: + return _mantle_requests(wire.drain()) + + +def _runtime_count_targets(wire: Wire) -> tuple[str, ...]: + counts: Final = tuple(request for request in wire.drain() if _COUNT_TARGET.match(target_of(request))) + for request in counts: + assert request.method == "POST", request.method + _assert_sigv4(request) + return tuple(target_of(request) for request in counts) + + +def _clients(stack: ExitStack, base_url: str, count: int, timeout: float = 30) -> tuple[httpx.Client, ...]: + return tuple( + stack.enter_context(httpx.Client(base_url=base_url, timeout=timeout, trust_env=False)) for _ in range(count) + ) + + +def _counted_on(client: httpx.Client, key: str, body: Mapping[str, JsonValue]) -> tuple[int, JsonValue]: + response: Final = client.post( + "/v1/messages/count_tokens", json=dict(body), headers={"Authorization": f"Bearer {key}"} + ) + return response.status_code, _JSON_OBJECT.validate_json(response.content).get("input_tokens") + + +def _generated_then_counted( + client: httpx.Client, key: str, model: str, body: Mapping[str, JsonValue] +) -> tuple[int, int, JsonValue]: + generated: Final = client.post( + "/v1/messages", + json={ + "model": model, + "max_tokens": 16, + "messages": [{"role": "user", "content": f"Generate before counting marker-{uuid.uuid4().hex}"}], + }, + headers={"Authorization": f"Bearer {key}"}, + ) + return generated.status_code, *_counted_on(client, key, body) + + +def _counted_or_dropped(client: httpx.Client, key: str, body: Mapping[str, JsonValue]) -> tuple[int, JsonValue] | None: + try: + return _counted_on(client, key, body) + except httpx.TransportError: + return None + + +def _probed_then_counted_or_dropped( + client: httpx.Client, key: str, body: Mapping[str, JsonValue], probed: SimpleQueue[int] +) -> tuple[int, tuple[int, JsonValue] | None]: + port: Final = _local_port(client) + probed.put(port) + return port, _counted_or_dropped(client, key, body) + + +def _local_port(client: httpx.Client) -> int: + with client.stream("GET", "/health/liveliness") as response: + port: Final = int(response.extensions["network_stream"].get_extra_info("client_addr")[1]) + response.read() + assert response.status_code == 200, response.text + return port + + +def _accepted_client_ports(pid: int, proxy_port: int) -> frozenset[int]: + return frozenset( + connection.raddr.port + for connection in psutil.Process(pid).net_connections(kind="tcp") + if connection.raddr and connection.laddr.port == proxy_port + ) + + +def _holding(held: SimpleQueue[str], release: threading.Event, seconds: float) -> Callable[[Request], Reply]: + def hold(request: Request) -> Reply: + held.put(request.target) + assert release.wait(timeout=seconds), "Held count was never released" + return _mantle_counted(request) + + return hold + + +def _anthropic_client(gateway: Gateway) -> anthropic.Anthropic: + return anthropic.Anthropic(base_url=str(gateway.client.base_url), api_key=gateway.key, max_retries=0) + + +def _async_anthropic_client(gateway: Gateway) -> anthropic.AsyncAnthropic: + return anthropic.AsyncAnthropic(base_url=str(gateway.client.base_url), api_key=gateway.key, max_retries=0) + + +@pytest.mark.parametrize("system", [_SYSTEM, _SYSTEM_BLOCKS], ids=["string", "blocks"]) +def test_messages_count_tokens_counts_through_mantle_when_the_runtime_cannot( + counting_proxy: OwnedProxy, mantle_port: int, system: JsonValue +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = _count(gateway, {**_bare(model), "system": system, "tools": _TOOLS}) + assert _payload(response) == {"input_tokens": _MANTLE_COUNT}, response.text + assert _runtime_count_targets(runtime) == (f"/model/{_OPUS_BASE}/count-tokens",) + assert _mantle_bodies(mantle) == (_mantle_body(system=system, tools=_TOOLS),) + + +def test_messages_count_tokens_without_system_or_tools_sends_a_bare_body_to_mantle( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = _count(gateway, _bare(model)) + assert _payload(response) == {"input_tokens": _MANTLE_COUNT}, response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert _mantle_bodies(mantle) == (_MANTLE_BARE,) + + +def test_utils_token_counter_call_endpoint_reports_the_mantle_tokenizer( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = gateway.request( + "POST", "/utils/token_counter", _full(model), params={"call_endpoint": "true"} + ) + payload: Final = _payload(response) + assert (payload["total_tokens"], payload["tokenizer_type"]) == (_MANTLE_COUNT, "bedrock_mantle_api") + assert payload["original_response"] == {"input_tokens": _MANTLE_COUNT}, response.text + assert (payload["request_model"], payload["model_used"]) == (model, _OPUS), response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert _mantle_bodies(mantle) == (_MANTLE_FULL,) + + +def test_gemini_count_tokens_route_reports_the_mantle_total(counting_proxy: OwnedProxy, mantle_port: int) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = gateway.request("POST", f"/v1beta/models/{model}:countTokens", _GEMINI_BODY) + assert _payload(response) == {"totalTokens": _MANTLE_COUNT, "promptTokensDetails": []}, response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert _mantle_bodies(mantle) == ({"model": _OPUS_BASE, "messages": _GEMINI_MESSAGES},) + + +def test_gemini_count_tokens_route_reports_the_runtime_total_for_a_model_bedrock_counts( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url, _SONNET) + response: Final = gateway.request("POST", f"/v1beta/models/{model}:countTokens", _GEMINI_BODY) + assert _payload(response) == {"totalTokens": _RUNTIME_COUNT, "promptTokensDetails": []}, response.text + assert _runtime_count_targets(runtime) == (f"/model/{_SONNET}/count-tokens",) + assert mantle.drain() == () + + +def test_responses_input_tokens_counts_through_mantle(counting_proxy: OwnedProxy, mantle_port: int) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = gateway.request( + "POST", "/v1/responses/input_tokens", {"model": model, "input": "Count this message"} + ) + assert _payload(response) == {"object": "response.input_tokens", "input_tokens": _MANTLE_COUNT}, response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert _mantle_bodies(mantle) == (_MANTLE_BARE,) + + +def test_anthropic_sdk_count_tokens_counts_through_mantle(counting_proxy: OwnedProxy, mantle_port: int) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + counted: Final = _anthropic_client(gateway).messages.count_tokens( + model=model, messages=_SDK_MESSAGES, system=_SYSTEM, tools=_SDK_TOOLS + ) + assert counted.input_tokens == _MANTLE_COUNT, counted + assert len(_runtime_count_targets(runtime)) == 1 + assert _mantle_bodies(mantle) == (_MANTLE_FULL,) + + +def test_async_anthropic_sdk_count_tokens_counts_through_mantle(counting_proxy: OwnedProxy, mantle_port: int) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + counted: Final = asyncio.run( + _async_anthropic_client(gateway).messages.count_tokens(model=model, messages=_SDK_MESSAGES, system=_SYSTEM) + ) + assert counted.input_tokens == _MANTLE_COUNT, counted + assert len(_runtime_count_targets(runtime)) == 1 + assert _mantle_bodies(mantle) == (_mantle_body(system=_SYSTEM),) + + +def test_model_the_runtime_counts_never_reaches_mantle(counting_proxy: OwnedProxy, mantle_port: int) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url, _SONNET) + assert _payload(_count(gateway, _full(model))) == {"input_tokens": _RUNTIME_COUNT} + detailed: Final = gateway.request( + "POST", "/utils/token_counter", _full(model), params={"call_endpoint": "true"} + ) + payload: Final = _payload(detailed) + assert (payload["total_tokens"], payload["tokenizer_type"]) == (_RUNTIME_COUNT, "bedrock_api"), detailed.text + assert _runtime_count_targets(runtime) == (f"/model/{_SONNET}/count-tokens",) * 2 + assert mantle.drain() == () + + +def test_non_claude_model_the_runtime_cannot_count_falls_back_locally_without_mantle( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url, _NOVA) + response: Final = _count(gateway, _bare(model)) + assert _payload(response) == {"input_tokens": _local_count(gateway, _bare(model))}, response.text + assert _runtime_count_targets(runtime) == (f"/model/{_NOVA}/count-tokens",) + assert mantle.drain() == () + + +def test_runtime_403_on_a_claude_model_never_reaches_mantle(counting_proxy: OwnedProxy, mantle_port: int) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + body: Final[dict[str, JsonValue]] = { + "model": model, + "messages": [{"role": "user", "content": "status=403 Count this message"}], + } + response: Final = _count(gateway, body) + assert _payload(response) == {"input_tokens": _local_count(gateway, body)}, response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert mantle.drain() == () + + +def test_unreachable_runtime_falls_back_locally_without_mantle(counting_proxy: OwnedProxy, mantle_port: int) -> None: + gateway: Final = counting_proxy.gateway + with wire_server(_mantle(), port=mantle_port) as mantle, gateway.scenario() as scenario: + model: Final = _deployment(scenario, _closed_port_url()) + response: Final = _count(gateway, _full(model)) + assert _payload(response) == {"input_tokens": _local_count(gateway, _full(model))}, response.text + assert mantle.drain() == () + + +def test_bedrock_passthrough_count_tokens_still_answers_the_runtime_rejection( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = gateway.request("POST", "/bedrock/v1/messages/count_tokens", _full(model)) + assert response.status_code == 400, response.text + assert _UNSUPPORTED in response.text and "input_tokens" not in response.text, response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert mantle.drain() == () + + +def test_responses_input_tokens_with_instructions_still_counts_locally( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(_strict), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = gateway.request( + "POST", + "/v1/responses/input_tokens", + {"model": model, "input": "Count this message", "instructions": "Be terse"}, + ) + payload: Final = _payload(response) + assert len(_runtime_count_targets(runtime)) == 1 + (sent,) = _mantle_bodies(mantle) + messages: Final = sent["messages"] + assert isinstance(messages, list) and messages[0] == {"role": "system", "content": "Be terse"}, sent + assert "system" not in sent, sent + local: Final = _local_count(gateway, {"model": model, "messages": messages}) + assert payload == {"object": "response.input_tokens", "input_tokens": local}, response.text + + +@pytest.mark.parametrize("status", [400, 403, 404, 500, 503]) +def test_messages_count_tokens_falls_back_locally_when_mantle_errors( + counting_proxy: OwnedProxy, mantle_port: int, status: int +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(_rejecting(status)), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = _count(gateway, _full(model)) + assert _payload(response) == {"input_tokens": _local_count(gateway, _full(model))}, response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert _mantle_bodies(mantle) == (_MANTLE_FULL,) + + +@pytest.mark.parametrize( + "body", + [b'{"inputTokens": 7}', b"not json at all", b"{}"], + ids=["runtime_key", "not_json", "empty_object"], +) +def test_messages_count_tokens_falls_back_locally_when_mantle_answers_without_input_tokens( + counting_proxy: OwnedProxy, mantle_port: int, body: bytes +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(lambda _request: Reply(body=body)), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = _count(gateway, _bare(model)) + assert _payload(response) == {"input_tokens": _local_count(gateway, _bare(model))}, response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert _mantle_bodies(mantle) == (_MANTLE_BARE,) + + +def test_messages_count_tokens_falls_back_locally_when_mantle_is_unreachable(counting_proxy: OwnedProxy) -> None: + gateway: Final = counting_proxy.gateway + with wire_server(_runtime) as runtime, gateway.scenario() as scenario: + model: Final = _deployment(scenario, runtime.url) + response: Final = _count(gateway, _full(model)) + assert _payload(response) == {"input_tokens": _local_count(gateway, _full(model))}, response.text + assert len(_runtime_count_targets(runtime)) == 1 + + +def test_messages_count_tokens_falls_back_locally_when_mantle_never_answers( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + held: Final[SimpleQueue[str]] = SimpleQueue() + release: Final = threading.Event() + + def hold(request: Request) -> Reply: + held.put(request.target) + release.wait(timeout=120) + return Reply(drop_connection=True) + + with ExitStack() as stack: + (client,) = _clients(stack, str(gateway.client.base_url), 1, timeout=120) + pool: Final = stack.enter_context(ThreadPoolExecutor(max_workers=1)) + runtime: Final = stack.enter_context(wire_server(_runtime)) + mantle: Final = stack.enter_context(wire_server(_mantle(hold), port=mantle_port)) + stack.callback(release.set) + scenario: Final = stack.enter_context(gateway.scenario()) + model: Final = _deployment(scenario, runtime.url) + body: Final = _full(model) + local: Final = _local_count(gateway, body) + future: Final = pool.submit(_counted_on, client, gateway.key, body) + eventually(held.qsize, lambda size: size == 1, seconds=30) + assert gateway.request("GET", "/health/liveliness").status_code == 200 + assert _local_count(gateway, body) == local + assert not future.done() + assert future.result(timeout=120) == (200, local) + assert len(_runtime_count_targets(runtime)) == 1 + assert len(mantle.drain()) == 1 + + +def test_messages_count_tokens_falls_back_locally_when_mantle_rejects_a_non_text_system( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(_strict), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = _count(gateway, {**_bare(model), "system": 5}) + assert _payload(response) == {"input_tokens": _local_count(gateway, _bare(model))}, response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert _mantle_bodies(mantle) == (_mantle_body(system=5),) + + +@pytest.mark.parametrize( + "tools", + [5, "", "x" * 5120, ["get_weather"]], + ids=["int", "empty_string", "5kb_string", "list_of_strings"], +) +def test_messages_count_tokens_rejects_malformed_tools_without_calling_either_peer( + counting_proxy: OwnedProxy, mantle_port: int, tools: JsonValue +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + refused: Final = _count(gateway, {**_bare(model), "tools": tools}) + assert 400 <= refused.status_code < 600, refused.text + assert "input_tokens" not in refused.text, refused.text + assert runtime.drain() == () and mantle.drain() == () + assert _generated_then_counted(gateway.client, gateway.key, model, _bare(model)) == (200, 200, _MANTLE_COUNT) + assert _mantle_bodies(mantle) == (_MANTLE_BARE,) + + +@pytest.mark.parametrize("fields", [{}, {"messages": []}], ids=["missing", "empty"]) +def test_messages_count_tokens_without_messages_is_rejected( + counting_proxy: OwnedProxy, mantle_port: int, fields: dict[str, JsonValue] +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = _count(gateway, {"model": model, "system": _SYSTEM, "tools": _TOOLS, **fields}) + assert response.status_code == 400, response.text + assert "messages parameter is required" in response.text, response.text + assert runtime.drain() == () and mantle.drain() == () + + +def test_messages_count_tokens_unauthenticated_request_never_reaches_either_peer( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = gateway.request( + "POST", "/v1/messages/count_tokens", _full(model), key="sk-not-a-key-this-proxy-issued" + ) + assert response.status_code == 401, response.text + assert "input_tokens" not in response.text, response.text + assert runtime.drain() == () and mantle.drain() == () + + +def test_messages_count_tokens_forwards_a_5kb_system_verbatim_to_mantle( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + system: Final = "Answer in one sentence. " * 214 + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = _count(gateway, {**_bare(model), "system": system}) + assert _payload(response) == {"input_tokens": _MANTLE_COUNT}, response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert _mantle_bodies(mantle) == (_mantle_body(system=system),) + + +def test_messages_count_tokens_duplicate_system_and_tools_keys_forward_one_value_each_to_mantle( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + fields: Final = f'"system": {json.dumps(_SYSTEM)}, "tools": {json.dumps(_TOOLS)}' + response: Final = gateway.client.post( + "/v1/messages/count_tokens", + content=f'{{"model": "{model}", "messages": {json.dumps(_MESSAGES)}, {fields}, {fields}}}', + headers={"Authorization": f"Bearer {gateway.key}", "Content-Type": "application/json"}, + ) + assert _payload(response) == {"input_tokens": _MANTLE_COUNT}, response.text + assert len(_runtime_count_targets(runtime)) == 1 + (sent,) = mantle.drain() + assert _mantle_requests((sent,)) == (_MANTLE_FULL,) + assert (sent.body.count(b'"system"'), sent.body.count(b'"tools"')) == (1, 1), sent.body + + +def test_messages_count_tokens_leaves_empty_tools_and_system_out_of_the_mantle_body( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = _count(gateway, {**_bare(model), "tools": [], "system": ""}) + assert _payload(response) == {"input_tokens": _MANTLE_COUNT}, response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert _mantle_bodies(mantle) == (_MANTLE_BARE,) + + +def test_messages_count_tokens_repeated_request_reaches_both_peers_each_time( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + answers: Final = tuple(_payload(_count(gateway, _bare(model))) for _ in range(2)) + assert answers == ({"input_tokens": _MANTLE_COUNT},) * 2 + assert _runtime_count_targets(runtime) == (f"/model/{_OPUS_BASE}/count-tokens",) * 2 + assert _mantle_bodies(mantle) == (_MANTLE_BARE,) * 2 + + +def test_disabled_token_counter_surfaces_the_mantle_error_instead_of_counting_locally( + gateway: Gateway, mantle_port: int, tmp_path: Path +) -> None: + with ExitStack() as stack: + runtime: Final = stack.enter_context(wire_server(_runtime)) + config: Final = _owned_config( + tmp_path / "disabled-token-counter.yaml", runtime.url, {"disable_token_counter": True} + ) + owned: Final = stack.enter_context( + owned_proxy_process( + gateway, + tmp_path, + _mantle_environment(mantle_port), + config=config, + workers=2, + remove_environment=_INHERITED_BEARER, + ) + ) + with wire_server(_mantle(_rejecting(403)), port=mantle_port) as refusing: + refused: Final = _count(owned.gateway, _full(_OWNED_OPUS)) + assert refused.status_code == 403, refused.text + assert _REJECTION in refused.text and "input_tokens" not in refused.text, refused.text + assert _mantle_bodies(refusing) == (_MANTLE_FULL,) + with wire_server(_mantle(), port=mantle_port) as counting: + assert _payload(_count(owned.gateway, _full(_OWNED_OPUS))) == {"input_tokens": _MANTLE_COUNT} + assert _mantle_bodies(counting) == (_MANTLE_FULL,) + assert _payload(_count(owned.gateway, _full(_OWNED_SONNET))) == {"input_tokens": _RUNTIME_COUNT} + rejected: Final = _count(owned.gateway, _full(_OWNED_NOVA)) + assert rejected.status_code == 400, rejected.text + assert _UNSUPPORTED in rejected.text and "input_tokens" not in rejected.text, rejected.text + assert counting.drain() == () + assert len(_runtime_count_targets(runtime)) == 4 + + +def test_mantle_outage_between_concurrent_waves_falls_back_then_recovers( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + with ExitStack() as stack: + clients: Final = _clients(stack, str(gateway.client.base_url), 8) + pool: Final = stack.enter_context(ThreadPoolExecutor(max_workers=len(clients))) + runtime: Final = stack.enter_context(wire_server(_runtime)) + scenario: Final = stack.enter_context(gateway.scenario()) + model: Final = _deployment(scenario, runtime.url) + body: Final = _full(model) + local: Final = _local_count(gateway, body) + + def generate_then_count(client: httpx.Client) -> tuple[int, int, JsonValue]: + return _generated_then_counted(client, gateway.key, model, body) + + def count_only(client: httpx.Client) -> tuple[int, JsonValue]: + return _counted_on(client, gateway.key, body) + + with wire_server(_mantle(), port=mantle_port) as mantle: + assert tuple(pool.map(generate_then_count, clients)) == ((200, 200, _MANTLE_COUNT),) * len(clients) + assert _mantle_bodies(mantle) == (_MANTLE_FULL,) * len(clients) + outage: Final = tuple(pool.map(count_only, clients)) + assert outage == ((200, local),) * len(clients) + with wire_server(_mantle(), port=mantle_port) as revived: + assert tuple(pool.map(generate_then_count, clients)) == ((200, 200, _MANTLE_COUNT),) * len(clients) + assert _mantle_bodies(revived) == (_MANTLE_FULL,) * len(clients) + assert len(_runtime_count_targets(runtime)) == 3 * len(clients) + + +def test_slow_mantle_holds_concurrent_counts_without_stalling_the_proxy( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + held: Final[SimpleQueue[str]] = SimpleQueue() + release: Final = threading.Event() + with ExitStack() as stack: + clients: Final = _clients(stack, str(gateway.client.base_url), 6) + runtime: Final = stack.enter_context(wire_server(_runtime)) + mantle: Final = stack.enter_context(wire_server(_mantle(_holding(held, release, 20)), port=mantle_port)) + scenario: Final = stack.enter_context(gateway.scenario()) + pool: Final = stack.enter_context(ThreadPoolExecutor(max_workers=len(clients))) + stack.callback(release.set) + model: Final = _deployment(scenario, runtime.url) + futures: Final = tuple( + pool.submit(_generated_then_counted, client, gateway.key, model, _full(model)) for client in clients + ) + eventually(held.qsize, lambda size: size == len(clients), seconds=30) + assert gateway.request("GET", "/health/liveliness").status_code == 200 + assert _local_count(gateway, _full(model)) > 0 + assert not any(future.done() for future in futures) + release.set() + assert tuple(future.result(timeout=30) for future in futures) == ((200, 200, _MANTLE_COUNT),) * len(clients) + assert _mantle_bodies(mantle) == (_MANTLE_FULL,) * len(clients) + assert len(_runtime_count_targets(runtime)) == len(clients) + + +def test_worker_sigkill_mid_burst_leaves_the_sibling_counting( + gateway: Gateway, mantle_port: int, tmp_path: Path +) -> None: + held: Final[SimpleQueue[str]] = SimpleQueue() + release: Final = threading.Event() + with ExitStack() as stack: + runtime: Final = stack.enter_context(wire_server(_runtime)) + mantle: Final = stack.enter_context(wire_server(_mantle(_holding(held, release, 60)), port=mantle_port)) + config: Final = _owned_config(tmp_path / "worker-kill.yaml", runtime.url, {}) + owned: Final = stack.enter_context( + owned_proxy_process( + gateway, + tmp_path, + _mantle_environment(mantle_port), + config=config, + workers=2, + remove_environment=_INHERITED_BEARER, + ) + ) + body: Final = _full(_OWNED_OPUS) + proxy_url: Final = owned.gateway.client.base_url + workers: Final = eventually( + lambda: tuple(int(pid) for pid in _STARTED_WORKER.findall(owned.log.read_text())), + lambda pids: len(pids) == 2, + seconds=30, + ) + clients: Final = _clients(stack, str(proxy_url), 12) + pool: Final = stack.enter_context(ThreadPoolExecutor(max_workers=len(clients))) + stack.callback(release.set) + probed: Final[SimpleQueue[int]] = SimpleQueue() + futures: Final[tuple[Future[tuple[int, tuple[int, JsonValue] | None]], ...]] = tuple( + pool.submit(_probed_then_counted_or_dropped, client, owned.gateway.key, body, probed) for client in clients + ) + eventually(held.qsize, lambda size: size == len(clients), seconds=30) + ports: Final = frozenset(probed.get_nowait() for _ in clients) + shares: Final = {pid: _accepted_client_ports(pid, proxy_url.port or 0) & ports for pid in workers} + assert sum(map(len, shares.values())) == len(clients), shares + victim: Final = min((pid for pid in workers if shares[pid]), key=lambda pid: len(shares[pid])) + psutil.Process(victim).send_signal(signal.SIGKILL) + release.set() + for port, result in (future.result(timeout=60) for future in futures): + assert result == (None if port in shares[victim] else (200, _MANTLE_COUNT)), (port, result, shares) + second_wave: Final = _clients(stack, str(proxy_url), 6) + assert tuple(_counted_on(client, owned.gateway.key, body) for client in second_wave) == ( + (200, _MANTLE_COUNT), + ) * len(second_wave) + assert len(_mantle_bodies(mantle)) == len(clients) + len(second_wave) + eventually(lambda: len(_STARTED_WORKER.findall(owned.log.read_text())), lambda started: started >= 3, 120) + assert owned.process.poll() is None + + +def _streamed_text(text: str) -> str: + events: Final = tuple( + _JSON_OBJECT.validate_json(line.removeprefix("data: ")) + for line in text.splitlines() + if line.startswith("data: {") + ) + return "".join(_delta_content(event) for event in events) + + +def _delta_content(event: dict[str, JsonValue]) -> str: + choices: Final = event.get("choices") + if not isinstance(choices, list) or not choices: + return "" + delta: Final = object_value(choices[0]).get("delta") + if not isinstance(delta, dict): + return "" + content: Final = delta.get("content") + return content if isinstance(content, str) else "" + + +@pytest.mark.parametrize("stream", [False, True], ids=["non_stream", "stream"]) +def test_chat_completions_on_the_same_deployment_still_generate( + counting_proxy: OwnedProxy, mantle_port: int, stream: bool +) -> None: + gateway: Final = counting_proxy.gateway + marker: Final = uuid.uuid4().hex + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = gateway.request( + "POST", + "/v1/chat/completions", + { + "model": model, + "messages": [{"role": "user", "content": f"chat control marker-{marker}"}], + "stream": stream, + "cache": {"no-cache": True}, + }, + ) + assert response.status_code == 200, response.text + generated: Final = _streamed_text(response.text) if stream else response.text + assert answer(marker) in generated, response.text + assert not stream or response.text.rstrip().endswith("data: [DONE]"), response.text + (sent,) = runtime.drain() + assert target_of(sent) == f"/model/{_OPUS}/{'converse-stream' if stream else 'converse'}", sent.target + assert mantle.drain() == () + + +def test_messages_endpoint_on_the_same_deployment_still_generates(counting_proxy: OwnedProxy, mantle_port: int) -> None: + gateway: Final = counting_proxy.gateway + marker: Final = uuid.uuid4().hex + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = gateway.request( + "POST", + "/v1/messages", + {"model": model, "max_tokens": 16, "messages": [{"role": "user", "content": f"marker-{marker}"}]}, + ) + assert response.status_code == 200, response.text + assert answer(marker) in response.text, response.text + (sent,) = runtime.drain() + assert target_of(sent) == f"/model/{_OPUS}/invoke", sent.target + assert mantle.drain() == () + + +def test_responses_endpoint_on_the_same_deployment_still_generates( + counting_proxy: OwnedProxy, mantle_port: int +) -> None: + gateway: Final = counting_proxy.gateway + marker: Final = uuid.uuid4().hex + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = gateway.request("POST", "/v1/responses", {"model": model, "input": f"marker-{marker}"}) + assert response.status_code == 200, response.text + assert answer(marker) in response.text, response.text + (sent,) = runtime.drain() + assert target_of(sent) == f"/model/{_OPUS}/converse", sent.target + assert mantle.drain() == () + + +def test_utils_token_counter_local_mode_never_calls_either_peer(counting_proxy: OwnedProxy, mantle_port: int) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + assert _local_count(gateway, _full(model)) > 0 + assert runtime.drain() == () and mantle.drain() == () diff --git a/tests/unit/llms/bedrock/count_tokens/test_bedrock_mantle_count_tokens_handler.py b/tests/unit/llms/bedrock/count_tokens/test_bedrock_mantle_count_tokens_handler.py new file mode 100644 index 00000000000..71b451f834c --- /dev/null +++ b/tests/unit/llms/bedrock/count_tokens/test_bedrock_mantle_count_tokens_handler.py @@ -0,0 +1,109 @@ +import json +from collections.abc import Mapping +from typing import Final + +import httpx +import pytest + +from litellm.llms.bedrock.common_utils import BedrockError +from litellm.llms.bedrock.count_tokens.mantle_handler import BedrockMantleCountTokensHandler +from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler + +MANTLE_COUNT_URL: Final = "https://bedrock-mantle.us-east-1.api.aws/anthropic/v1/messages/count_tokens" +LITELLM_PARAMS: Final = { + "aws_access_key_id": "AKIATESTACCESSKEY", + "aws_secret_access_key": "test-secret", + "aws_region_name": "us-east-1", +} +REQUEST: Final[dict[str, object]] = { + "model": "global.anthropic.claude-opus-4-8", + "messages": [{"role": "user", "content": "The quick brown fox"}], + "system": "You are a terse assistant.", + "tools": [{"name": "get_weather", "input_schema": {"type": "object", "properties": {}}}], +} + + +class _MantleEndpoint: + def __init__(self, status_code: int, body: Mapping[str, object]) -> None: + self.status_code: Final = status_code + self.body: Final = body + self.requests: tuple[httpx.Request, ...] = () + + def __call__(self, request: httpx.Request) -> httpx.Response: + self.requests = (*self.requests, request) + return httpx.Response(self.status_code, json=dict(self.body), request=request) + + def only_request(self) -> httpx.Request: + assert len(self.requests) == 1, self.requests + return self.requests[0] + + +def _client(endpoint: _MantleEndpoint) -> AsyncHTTPHandler: + return AsyncHTTPHandler(transport=httpx.MockTransport(endpoint)) + + +@pytest.fixture(autouse=True) +def _sigv4_only(monkeypatch: pytest.MonkeyPatch) -> None: + monkeypatch.delenv("AWS_BEARER_TOKEN_BEDROCK", raising=False) + monkeypatch.delenv("BEDROCK_MANTLE_API_BASE", raising=False) + + +@pytest.mark.asyncio +async def test_counts_on_mantle_with_the_base_model_and_the_deployment_credentials() -> None: + mantle: Final = _MantleEndpoint(200, {"input_tokens": 2177}) + + result: Final = await BedrockMantleCountTokensHandler().handle_count_tokens_request( + request_data=dict(REQUEST), + litellm_params=dict(LITELLM_PARAMS), + resolved_model="anthropic.claude-opus-4-8", + client=_client(mantle), + ) + + assert result == {"input_tokens": 2177} + posted: Final = mantle.only_request() + assert str(posted.url) == MANTLE_COUNT_URL + assert posted.headers["Authorization"].startswith("AWS4-HMAC-SHA256") + assert "us-east-1/bedrock/aws4_request" in posted.headers["Authorization"] + assert posted.headers["anthropic-version"] == "2023-06-01" + assert json.loads(posted.content) == { + "model": "anthropic.claude-opus-4-8", + "messages": REQUEST["messages"], + "system": REQUEST["system"], + "tools": REQUEST["tools"], + } + + +@pytest.mark.asyncio +async def test_bedrock_mantle_api_base_env_names_the_host(monkeypatch: pytest.MonkeyPatch) -> None: + monkeypatch.setenv("BEDROCK_MANTLE_API_BASE", "https://vpce-abc.bedrock-mantle.us-east-1.vpce.api.aws") + mantle: Final = _MantleEndpoint(200, {"input_tokens": 3}) + + await BedrockMantleCountTokensHandler().handle_count_tokens_request( + request_data=dict(REQUEST), + litellm_params=dict(LITELLM_PARAMS), + resolved_model="anthropic.claude-opus-4-8", + client=_client(mantle), + ) + + assert ( + str(mantle.only_request().url) + == "https://vpce-abc.bedrock-mantle.us-east-1.vpce.api.aws/anthropic/v1/messages/count_tokens" + ) + + +@pytest.mark.asyncio +async def test_non_200_answers_raise_bedrock_error_with_mantle_status() -> None: + mantle: Final = _MantleEndpoint( + 404, {"type": "error", "error": {"type": "not_found_error", "message": "does not exist"}} + ) + + with pytest.raises(BedrockError) as raised: + await BedrockMantleCountTokensHandler().handle_count_tokens_request( + request_data=dict(REQUEST), + litellm_params=dict(LITELLM_PARAMS), + resolved_model="anthropic.claude-sonnet-5-5", + client=_client(mantle), + ) + + assert raised.value.status_code == 404 + assert "does not exist" in raised.value.message diff --git a/tests/unit/llms/bedrock/count_tokens/test_bedrock_token_counter.py b/tests/unit/llms/bedrock/count_tokens/test_bedrock_token_counter.py new file mode 100644 index 00000000000..a3dd8021f73 --- /dev/null +++ b/tests/unit/llms/bedrock/count_tokens/test_bedrock_token_counter.py @@ -0,0 +1,140 @@ +from collections.abc import Mapping +from typing import Final + +import httpx +import pytest +from pydantic import JsonValue, TypeAdapter + +from litellm.llms.bedrock.count_tokens.bedrock_token_counter import BedrockTokenCounter +from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler + +RUNTIME_HOST: Final = "bedrock-runtime.us-east-1.amazonaws.com" +MANTLE_HOST: Final = "bedrock-mantle.us-east-1.api.aws" +UNSUPPORTED: Final = {"message": "The provided model doesn't support counting tokens."} +DEPLOYMENT: Final = { + "litellm_params": { + "aws_access_key_id": "AKIATESTACCESSKEY", + "aws_secret_access_key": "test-secret", + "aws_region_name": "us-east-1", + } +} +MESSAGES: Final = [{"role": "user", "content": "The quick brown fox jumps over the lazy dog."}] +_JSON_BODY: Final = TypeAdapter(dict[str, JsonValue]) + + +class _Bedrock: + def __init__(self, runtime: tuple[int, Mapping[str, object]], mantle: tuple[int, Mapping[str, object]]) -> None: + self.runtime: Final = runtime + self.mantle: Final = mantle + self.requests: tuple[httpx.Request, ...] = () + + def __call__(self, request: httpx.Request) -> httpx.Response: + self.requests = (*self.requests, request) + status_code, body = self.runtime if request.url.host == RUNTIME_HOST else self.mantle + return httpx.Response(status_code, json=dict(body), request=request) + + def posted_hosts(self) -> tuple[str, ...]: + return tuple(request.url.host for request in self.requests) + + +def _counter(bedrock: _Bedrock) -> BedrockTokenCounter: + return BedrockTokenCounter(client=AsyncHTTPHandler(transport=httpx.MockTransport(bedrock))) + + +@pytest.fixture(autouse=True) +def _sigv4_only(monkeypatch: pytest.MonkeyPatch) -> None: + monkeypatch.delenv("AWS_BEARER_TOKEN_BEDROCK", raising=False) + monkeypatch.delenv("BEDROCK_MANTLE_API_BASE", raising=False) + + +@pytest.mark.asyncio +async def test_claude_model_bedrock_runtime_cannot_count_is_counted_on_mantle() -> None: + bedrock: Final = _Bedrock(runtime=(400, UNSUPPORTED), mantle=(200, {"input_tokens": 2177})) + + result: Final = await _counter(bedrock).count_tokens( + model_to_use="global.anthropic.claude-opus-4-8", + messages=MESSAGES, + contents=None, + deployment=DEPLOYMENT, + request_model="claude-opus-4-8", + system="You are a terse assistant.", + ) + + assert result is not None + assert result.error is False + assert result.total_tokens == 2177 + assert result.tokenizer_type == "bedrock_mantle_api" + assert result.original_response == {"input_tokens": 2177} + assert bedrock.posted_hosts() == (RUNTIME_HOST, MANTLE_HOST) + mantle_body: Final = _JSON_BODY.validate_json(bedrock.requests[1].content) + assert mantle_body["model"] == "anthropic.claude-opus-4-8" + assert mantle_body["system"] == "You are a terse assistant." + + +@pytest.mark.asyncio +async def test_bedrock_runtime_count_is_kept_when_it_answers() -> None: + bedrock: Final = _Bedrock(runtime=(200, {"inputTokens": 1353}), mantle=(200, {"input_tokens": 1336})) + + result: Final = await _counter(bedrock).count_tokens( + model_to_use="global.anthropic.claude-sonnet-4-6", + messages=MESSAGES, + contents=None, + deployment=DEPLOYMENT, + request_model="claude-sonnet-4-6", + ) + + assert result is not None + assert result.total_tokens == 1353 + assert result.tokenizer_type == "bedrock_api" + assert bedrock.posted_hosts() == (RUNTIME_HOST,) + + +@pytest.mark.asyncio +@pytest.mark.parametrize( + ("model_to_use", "runtime"), + ( + ("global.anthropic.claude-opus-4-8", (403, {"Message": "not authorized to perform: bedrock:CountTokens"})), + ("amazon.nova-pro-v1:0", (400, UNSUPPORTED)), + ), +) +async def test_other_bedrock_runtime_failures_are_not_retried_on_mantle( + model_to_use: str, runtime: tuple[int, Mapping[str, object]] +) -> None: + bedrock: Final = _Bedrock(runtime=runtime, mantle=(200, {"input_tokens": 2177})) + + result: Final = await _counter(bedrock).count_tokens( + model_to_use=model_to_use, + messages=MESSAGES, + contents=None, + deployment=DEPLOYMENT, + request_model=model_to_use, + ) + + assert result is not None + assert result.error is True + assert result.status_code == runtime[0] + assert result.tokenizer_type == "bedrock_api" + assert bedrock.posted_hosts() == (RUNTIME_HOST,) + + +@pytest.mark.asyncio +async def test_mantle_failure_is_reported_with_its_status() -> None: + bedrock: Final = _Bedrock( + runtime=(400, UNSUPPORTED), + mantle=(404, {"type": "error", "error": {"type": "not_found_error", "message": "does not exist"}}), + ) + + result: Final = await _counter(bedrock).count_tokens( + model_to_use="global.anthropic.claude-sonnet-5-5", + messages=MESSAGES, + contents=None, + deployment=DEPLOYMENT, + request_model="claude-sonnet-5-5", + ) + + assert result is not None + assert result.error is True + assert result.status_code == 404 + assert result.tokenizer_type == "bedrock_mantle_api" + assert "does not exist" in (result.error_message or "") + assert bedrock.posted_hosts() == (RUNTIME_HOST, MANTLE_HOST) diff --git a/tests/unit/proxy/test_proxy_token_counter.py b/tests/unit/proxy/test_proxy_token_counter.py index 9703e8ad1dc..24026c5bc75 100644 --- a/tests/unit/proxy/test_proxy_token_counter.py +++ b/tests/unit/proxy/test_proxy_token_counter.py @@ -815,41 +815,45 @@ def test_vertex_ai_partner_models_token_counting_endpoint(vertex_location): assert endpoint.startswith(f"https://{vertex_location}-aiplatform.googleapis.com") +class _FailingRuntimeHandler(BedrockCountTokensHandler): + def __init__(self, error: Exception) -> None: + super().__init__() + self._error = error + + async def handle_count_tokens_request( + self, + request_data: dict[str, object], + litellm_params: dict[str, object], + resolved_model: str, + client: AsyncHTTPHandler | None = None, + ) -> dict[str, JsonValue]: + raise self._error + + @pytest.mark.asyncio async def test_bedrock_token_counter_error_propagation_bedrock_error(): """ Test that BedrockTokenCounter properly returns error response when BedrockError is raised. Verifies that the status code and error message are preserved. """ - counter = BedrockTokenCounter() + counter = BedrockTokenCounter( + runtime_handler=_FailingRuntimeHandler(BedrockError(status_code=429, message="Rate limit exceeded")) + ) - # Mock the handler to raise BedrockError with specific status code - with patch.object( - counter, "count_tokens", wraps=counter.count_tokens - ) as mock_count: - # We need to patch at the handler level - with patch( - "litellm.llms.bedrock.count_tokens.bedrock_token_counter.BedrockCountTokensHandler" - ) as MockHandler: - mock_handler_instance = MockHandler.return_value - mock_handler_instance.handle_count_tokens_request = AsyncMock( - side_effect=BedrockError(status_code=429, message="Rate limit exceeded") - ) + result = await counter.count_tokens( + model_to_use="anthropic.claude-3-sonnet", + messages=[{"role": "user", "content": "hello"}], + contents=None, + deployment={"litellm_params": {}}, + request_model="bedrock/anthropic.claude-3-sonnet", + ) - result = await counter.count_tokens( - model_to_use="anthropic.claude-3-sonnet", - messages=[{"role": "user", "content": "hello"}], - contents=None, - deployment={"litellm_params": {}}, - request_model="bedrock/anthropic.claude-3-sonnet", - ) - - assert result is not None - assert result.error is True - assert result.status_code == 429 - assert "Rate limit exceeded" in result.error_message - assert result.tokenizer_type == "bedrock_api" - assert result.total_tokens == 0 + assert result is not None + assert result.error is True + assert result.status_code == 429 + assert "Rate limit exceeded" in result.error_message + assert result.tokenizer_type == "bedrock_api" + assert result.total_tokens == 0 @pytest.mark.asyncio @@ -857,28 +861,20 @@ async def test_bedrock_token_counter_error_propagation_generic_exception(): """ Test that BedrockTokenCounter returns error response with 500 status for generic exceptions. """ - counter = BedrockTokenCounter() + counter = BedrockTokenCounter(runtime_handler=_FailingRuntimeHandler(Exception("Unexpected error"))) - with patch( - "litellm.llms.bedrock.count_tokens.bedrock_token_counter.BedrockCountTokensHandler" - ) as MockHandler: - mock_handler_instance = MockHandler.return_value - mock_handler_instance.handle_count_tokens_request = AsyncMock( - side_effect=Exception("Unexpected error") - ) + result = await counter.count_tokens( + model_to_use="anthropic.claude-3-sonnet", + messages=[{"role": "user", "content": "hello"}], + contents=None, + deployment={"litellm_params": {}}, + request_model="bedrock/anthropic.claude-3-sonnet", + ) - result = await counter.count_tokens( - model_to_use="anthropic.claude-3-sonnet", - messages=[{"role": "user", "content": "hello"}], - contents=None, - deployment={"litellm_params": {}}, - request_model="bedrock/anthropic.claude-3-sonnet", - ) - - assert result is not None - assert result.error is True - assert result.status_code == 500 - assert "Unexpected error" in result.error_message + assert result is not None + assert result.error is True + assert result.status_code == 500 + assert "Unexpected error" in result.error_message @pytest.mark.asyncio From ef3c50f2d99ae840dc10f12135b7e1191d2ddba3 Mon Sep 17 00:00:00 2001 From: mrinal-berri Date: Tue, 20 Oct 2026 17:46:21 +0000 Subject: [PATCH 03/66] fix(count_tokens): fall back to Mantle on Bedrock 404 (Bedrock part of #46430) Backport of #46430 to stable/1.104.x. Cherry-picked from 08a24d391af6ba0fbd4e99313857fbb05754ddf2 (main), Bedrock changes only. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../count_tokens/bedrock_token_counter.py | 5 +- .../test_bedrock_mantle_count_tokens_wire.py | 46 +++++++++++++++++++ .../test_bedrock_token_counter.py | 38 ++++++++++++++- 3 files changed, 86 insertions(+), 3 deletions(-) diff --git a/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py b/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py index 65a6aee027c..66fcd53b948 100644 --- a/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py +++ b/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py @@ -20,6 +20,7 @@ from litellm.types.utils import LiteLLMPydanticObjectBase, LlmProviders, TokenCo RUNTIME_TOKENIZER_TYPE: Final = "bedrock_api" MANTLE_TOKENIZER_TYPE: Final = "bedrock_mantle_api" +_RUNTIME_FALLBACK_STATUSES: Final = frozenset({400, 404}) class _CountTokensReply(LiteLLMPydanticObjectBase): @@ -46,14 +47,14 @@ CountTokensOutcome = CountedTokens | CountTokensFailure def _runtime_rejected_claude_model(outcome: CountTokensOutcome, resolved_model: str) -> bool: return ( isinstance(outcome, CountTokensFailure) - and outcome.status_code == 400 + and outcome.status_code in _RUNTIME_FALLBACK_STATUSES and is_mantle_claude_model(resolved_model) ) class BedrockTokenCounter(BaseTokenCounter): """Token counter for AWS Bedrock: bedrock-runtime CountTokens first, and Anthropic's count_tokens - on bedrock-mantle for the Claude models bedrock-runtime answers 400 for""" + on bedrock-mantle for the Claude models bedrock-runtime answers 400 or 404 for""" def __init__( self, diff --git a/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py b/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py index f9d4f7f91bb..8d8750a1da9 100644 --- a/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py +++ b/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py @@ -451,6 +451,52 @@ def test_gemini_count_tokens_route_reports_the_runtime_total_for_a_model_bedrock assert mantle.drain() == () +def test_runtime_404_on_claude_falls_back_to_mantle(counting_proxy: OwnedProxy, mantle_port: int) -> None: + gateway: Final = counting_proxy.gateway + system: Final = f"{_SYSTEM} status=404" + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = _count(gateway, {**_bare(model), "system": system, "tools": _TOOLS}) + assert _payload(response) == {"input_tokens": _MANTLE_COUNT}, response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert _mantle_bodies(mantle) == (_mantle_body(system=system, tools=_TOOLS),) + + +def test_runtime_404_and_mantle_404_surface_provider_error(counting_proxy: OwnedProxy, mantle_port: int) -> None: + gateway: Final = counting_proxy.gateway + system: Final = f"{_SYSTEM} status=404" + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(_rejecting(404)), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url) + response: Final = _count(gateway, {**_bare(model), "system": system, "tools": _TOOLS}) + assert response.status_code == 404, response.text + assert _REJECTION in response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert _mantle_bodies(mantle) == (_mantle_body(system=system, tools=_TOOLS),) + + +def test_runtime_404_on_nova_does_not_call_mantle(counting_proxy: OwnedProxy, mantle_port: int) -> None: + gateway: Final = counting_proxy.gateway + with ( + wire_server(_runtime) as runtime, + wire_server(_mantle(), port=mantle_port) as mantle, + gateway.scenario() as scenario, + ): + model: Final = _deployment(scenario, runtime.url, _NOVA) + body: Final = {**_bare(model), "messages": [{"role": "user", "content": "status=404"}]} + response: Final = _count(gateway, body) + assert response.status_code == 404, response.text + assert len(_runtime_count_targets(runtime)) == 1 + assert mantle.drain() == () + + def test_responses_input_tokens_counts_through_mantle(counting_proxy: OwnedProxy, mantle_port: int) -> None: gateway: Final = counting_proxy.gateway with ( diff --git a/tests/unit/llms/bedrock/count_tokens/test_bedrock_token_counter.py b/tests/unit/llms/bedrock/count_tokens/test_bedrock_token_counter.py index a3dd8021f73..8a21027872a 100644 --- a/tests/unit/llms/bedrock/count_tokens/test_bedrock_token_counter.py +++ b/tests/unit/llms/bedrock/count_tokens/test_bedrock_token_counter.py @@ -93,8 +93,10 @@ async def test_bedrock_runtime_count_is_kept_when_it_answers() -> None: @pytest.mark.parametrize( ("model_to_use", "runtime"), ( + ("global.anthropic.claude-opus-4-8", (401, {"Message": "not authorized to perform: bedrock:CountTokens"})), ("global.anthropic.claude-opus-4-8", (403, {"Message": "not authorized to perform: bedrock:CountTokens"})), ("amazon.nova-pro-v1:0", (400, UNSUPPORTED)), + ("amazon.nova-pro-v1:0", (404, UNSUPPORTED)), ), ) async def test_other_bedrock_runtime_failures_are_not_retried_on_mantle( @@ -120,7 +122,7 @@ async def test_other_bedrock_runtime_failures_are_not_retried_on_mantle( @pytest.mark.asyncio async def test_mantle_failure_is_reported_with_its_status() -> None: bedrock: Final = _Bedrock( - runtime=(400, UNSUPPORTED), + runtime=(404, UNSUPPORTED), mantle=(404, {"type": "error", "error": {"type": "not_found_error", "message": "does not exist"}}), ) @@ -138,3 +140,37 @@ async def test_mantle_failure_is_reported_with_its_status() -> None: assert result.tokenizer_type == "bedrock_mantle_api" assert "does not exist" in (result.error_message or "") assert bedrock.posted_hosts() == (RUNTIME_HOST, MANTLE_HOST) + + +@pytest.mark.asyncio +async def test_claude_runtime_404_retries_with_system_and_tools_on_mantle() -> None: + bedrock: Final = _Bedrock(runtime=(404, UNSUPPORTED), mantle=(200, {"input_tokens": 2177})) + tools: Final = [ + { + "name": "lookup", + "description": "Find a record", + "input_schema": {"type": "object", "properties": {"query": {"type": "string"}}}, + } + ] + + result: Final = await _counter(bedrock).count_tokens( + model_to_use="global.anthropic.claude-opus-4-8", + messages=MESSAGES, + contents=None, + deployment=DEPLOYMENT, + request_model="claude-opus-4-8", + system="You are a terse assistant.", + tools=tools, + ) + + assert result is not None + assert result.error is False + assert result.total_tokens == 2177 + assert bedrock.posted_hosts() == (RUNTIME_HOST, MANTLE_HOST) + mantle_body: Final = _JSON_BODY.validate_json(bedrock.requests[1].content) + assert mantle_body == { + "model": "anthropic.claude-opus-4-8", + "messages": MESSAGES, + "system": "You are a terse assistant.", + "tools": tools, + } From 8fbc0471f378e33a99345cb45f1f8afd21076fde Mon Sep 17 00:00:00 2001 From: mateo Date: Tue, 20 Oct 2026 18:00:07 +0000 Subject: [PATCH 04/66] fix(bedrock): adapt stable count token wire test Replace the main-only Bedrock runtime peer helper with stable-compatible test-local handlers and add the missing Mapping import. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../bedrock/count_tokens/mantle_handler.py | 1 + .../test_bedrock_mantle_count_tokens_wire.py | 57 ++++++++++++++++++- 2 files changed, 55 insertions(+), 3 deletions(-) diff --git a/litellm/llms/bedrock/count_tokens/mantle_handler.py b/litellm/llms/bedrock/count_tokens/mantle_handler.py index 9cc13ac0bf4..801bf03bd3f 100644 --- a/litellm/llms/bedrock/count_tokens/mantle_handler.py +++ b/litellm/llms/bedrock/count_tokens/mantle_handler.py @@ -1,3 +1,4 @@ +from collections.abc import Mapping from typing import Final import httpx diff --git a/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py b/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py index 8d8750a1da9..e6801269fad 100644 --- a/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py +++ b/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py @@ -12,6 +12,7 @@ from pathlib import Path from queue import SimpleQueue from types import MappingProxyType from typing import Final +from urllib.parse import unquote import anthropic import httpx @@ -19,10 +20,9 @@ import psutil import pytest import yaml from anthropic.types import MessageCountTokensToolParam, MessageParam -from integration._support.bedrock_runtime_peer import answer, marker_of, target_of -from integration._support.bedrock_runtime_peer import respond as runtime_generation from integration._support.client import Gateway, Scenario, eventually, gateway_from_environment, object_value from integration._support.process import OwnedProxy, graceful_stop_seconds, owned_proxy_process +from integration._support.upstream import _aws_event_frame from integration._support.wire import Reply, Request, Wire, wire_server from pydantic import JsonValue, TypeAdapter @@ -52,6 +52,11 @@ _SCRIPTED_STATUS: Final = re.compile(r"status=(\d{3})") _STARTED_WORKER: Final = re.compile(r"Started server process \[(\d+)\]") _JSON_OBJECT: Final = TypeAdapter(dict[str, JsonValue]) _JSON_LIST: Final = TypeAdapter(list[JsonValue]) +_MARKER: Final = re.compile(r"marker-([0-9a-f]{32})") +_NO_MARKER: Final = "0" * 32 +_CONVERSE: Final = re.compile(r"^/model/.+/converse$") +_CONVERSE_STREAM: Final = re.compile(r"^/model/.+/converse-stream$") +_EVENT_STREAM: Final = "application/vnd.amazon.eventstream" _SDK_MESSAGES: Final[list[MessageParam]] = [{"role": "user", "content": "Count this message"}] _MESSAGES: Final = _JSON_LIST.validate_json(json.dumps(_SDK_MESSAGES)) @@ -76,6 +81,52 @@ _GEMINI_BODY: Final[dict[str, JsonValue]] = {"contents": [{"role": "user", "part _GEMINI_MESSAGES: Final[list[JsonValue]] = [{"role": "user", "content": "Count this"}] +def marker_of(request: Request) -> str: + found: Final = _MARKER.search(request.body.decode(errors="replace")) + return _NO_MARKER if found is None else found.group(1) + + +def target_of(request: Request) -> str: + return unquote(request.target) + + +def answer(marker: str) -> str: + return f"answer marker-{marker}" + + +def _runtime_generation(request: Request) -> Reply: + target: Final = target_of(request) + marker: Final = marker_of(request) + if _CONVERSE.match(target): + return Reply( + body=json.dumps( + { + "output": {"message": {"role": "assistant", "content": [{"text": answer(marker)}]}}, + "stopReason": "end_turn", + "usage": {"inputTokens": 9, "outputTokens": 5, "totalTokens": 14}, + "metrics": {"latencyMs": 1}, + } + ).encode() + ) + if _CONVERSE_STREAM.match(target): + events: Final[tuple[tuple[str, Mapping[str, JsonValue]], ...]] = ( + ("messageStart", {"role": "assistant"}), + ("contentBlockDelta", {"delta": {"text": "answer "}, "contentBlockIndex": 0}), + ("contentBlockDelta", {"delta": {"text": f"marker-{marker}"}, "contentBlockIndex": 0}), + ("contentBlockStop", {"contentBlockIndex": 0}), + ("messageStop", {"stopReason": "end_turn"}), + ( + "metadata", + {"usage": {"inputTokens": 9, "outputTokens": 5, "totalTokens": 14}, "metrics": {"latencyMs": 1}}, + ), + ) + return Reply( + content_type=_EVENT_STREAM, + chunks=tuple(_aws_event_frame(kind, payload, "sc", marker) for kind, payload in events), + ) + return Reply(status=404, body=json.dumps({"message": f"unknown bedrock route {request.method} {target}"}).encode()) + + def _mantle_body(**fields: JsonValue) -> dict[str, JsonValue]: return {"model": _OPUS_BASE, "messages": _MESSAGES, **fields} @@ -120,7 +171,7 @@ def _runtime(request: Request) -> Reply: return _runtime_count(request, counted.group(1)) if _INVOKE_TARGET.match(target): return _invoke_reply(marker_of(request)) - return runtime_generation(request) + return _runtime_generation(request) def _mantle_counted(_request: Request) -> Reply: From 28e2612a9159a04aaf522dfad2290f6f23145090 Mon Sep 17 00:00:00 2001 From: mateo Date: Tue, 20 Oct 2026 18:17:32 +0000 Subject: [PATCH 05/66] fix(deps): update aiohttp on stable/1.104.x Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- uv.lock | 477 +++++++++++++++++++++++++++----------------------------- 1 file changed, 227 insertions(+), 250 deletions(-) diff --git a/uv.lock b/uv.lock index fb9d8bbd9ac..23d9f9304cb 100644 --- a/uv.lock +++ b/uv.lock @@ -10,7 +10,7 @@ resolution-markers = [ ] [options] -exclude-newer = "2026-10-03T01:54:46.765163Z" +exclude-newer = "2026-10-17T18:08:05.560666223Z" exclude-newer-span = "P3D" [manifest] @@ -85,7 +85,7 @@ wheels = [ [[package]] name = "aiohttp" -version = "3.14.3" +version = "3.14.4" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "aiohappyeyeballs" }, @@ -98,126 +98,127 @@ dependencies = [ { name = "typing-extensions", marker = "python_full_version < '3.13'" }, { name = "yarl" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/58/d9/22ce5786ac0c1653ae8b6c23bded02c1686d11f0dbb45b31ce128e0df985/aiohttp-3.14.3.tar.gz", hash = "sha256:9491196535a88924a60afd5b5f434b5b203b6cc616250878dbdb223a8f7844bc", size = 7971213, upload-time = "2026-07-23T01:57:27.037Z" } +sdist = { url = "https://files.pythonhosted.org/packages/93/2f/6a91adaa2dc26877d6ed2f54c0370c8910f019db7d77c5c6a194611e93ea/aiohttp-3.14.4.tar.gz", hash = "sha256:831fc5bd39ec2517851e348f613ddb5447a47cf4b71cb09845af7ad7ed45d8f9", size = 8077839, upload-time = "2026-10-05T17:43:48.309Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/2d/4d/4a99fb425c5e0cad715eea7bd190aff46f38b959a0a2dadb993705d34b26/aiohttp-3.14.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:eb0495d778817619273c108784292be161a924b9f5ae5cbbc70a2caa6838250b", size = 765848, upload-time = "2026-07-23T01:52:08.217Z" }, - { url = "https://files.pythonhosted.org/packages/74/e8/43b85dc55b8e950dc644babe762add781319ea881b57b33d2cce12017d12/aiohttp-3.14.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c3c200cf9757edd785051dc699c7ecbec22110dbfcb3fefc7a9f9695eda8ea7a", size = 517476, upload-time = "2026-07-23T01:52:10.846Z" }, - { url = "https://files.pythonhosted.org/packages/7f/9e/73b582c4dbbc3c12ef4473822475effaabf1f934b56f14f5b03fe5d3a2af/aiohttp-3.14.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:fd51ebf9d3a00c074df4ede271023f4d2dba289bcc740b88191872716014e3c5", size = 515334, upload-time = "2026-07-23T01:52:12.636Z" }, - { url = "https://files.pythonhosted.org/packages/79/03/e98c3c9e05a5bdf97defe5ff9169baba4f0ec9a901f2d60e0f060c2f051e/aiohttp-3.14.3-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:134ac5ddcf61c6fad984b9a5727d83492ada43d63471db20fb73042c13fca62f", size = 1708830, upload-time = "2026-07-23T01:52:14.538Z" }, - { url = "https://files.pythonhosted.org/packages/d7/2c/26e60b694844dfd2176c57f913a22d0cd6a16f9ff202cbda7580d0328b98/aiohttp-3.14.3-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:70c987b27534f9ae1a723f47ae921571d616da21d3208282bf4c52af5164ac43", size = 1674012, upload-time = "2026-07-23T01:52:16.486Z" }, - { url = "https://files.pythonhosted.org/packages/38/65/672df92e3172cd876aacfa97a952ac560877eb169384b2991ac5b273de4c/aiohttp-3.14.3-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:1b59533861b70a2185c8f4f350f791f39d64358ef6944ce71c5240c9ec0982c9", size = 1767015, upload-time = "2026-07-23T01:52:18.28Z" }, - { url = "https://files.pythonhosted.org/packages/9e/c5/228dec7bfec1c373cc2217cdeb47d6456dcd7a13a4c55144930a75ae3851/aiohttp-3.14.3-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:1c5281acc88b92396f88c7e1e2748f8466689df22b80170e4f51efa712fb47a8", size = 1858700, upload-time = "2026-07-23T01:52:20.08Z" }, - { url = "https://files.pythonhosted.org/packages/bd/ff/cb36724e8c8d17f90ada567a9ff3efe1d6e9b549fba697a242aece180f21/aiohttp-3.14.3-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:48d67b87db6279c044760787eb01f6413032c2e6f3ba1cafaa492b1c8e578479", size = 1714075, upload-time = "2026-07-23T01:52:22.071Z" }, - { url = "https://files.pythonhosted.org/packages/9f/3a/296a4135c6366376263aeef54b15caca1f07676c2ae0c525d7832f2f808a/aiohttp-3.14.3-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f53bcd52f585e1ac3e590d61434eb61f9a88c38df041b4ea126d97144344a77b", size = 1588234, upload-time = "2026-07-23T01:52:23.757Z" }, - { url = "https://files.pythonhosted.org/packages/7d/81/9d5d853ef892dc066d1eb6db0e87a47348b920c1c879aa554612fdbd9d79/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:0fdea2281997af69da84c77ffa6f5938a0285f21fb3887c249d67419ca865b3d", size = 1677300, upload-time = "2026-07-23T01:52:25.861Z" }, - { url = "https://files.pythonhosted.org/packages/68/96/021d386ae32d9b26d4b88df2e794546232ff56bb6be952bf6be227c0bbc7/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:cda5fd5c95ad7a125a2e8464acc78b98b94c475a3780d6aa0aa157c93f470f4d", size = 1691501, upload-time = "2026-07-23T01:52:28Z" }, - { url = "https://files.pythonhosted.org/packages/29/9f/af66adce26a14af135c003cbd0f44ccaa68cebd30ff8ac99ca47fb4958f7/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:6debfa7312ff9d4c124dc71d72e9a0a4b9e0879e48ba6fcb42bef5c3300289e2", size = 1735113, upload-time = "2026-07-23T01:52:29.995Z" }, - { url = "https://files.pythonhosted.org/packages/2f/90/28c390d4c9851effe52ac25b5a2e1d92246acd00728b4fc7975dafb67484/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:f4e05329faa0ea1a404b37de4f034fd2c2defcca06a68dc6745e4e56c88e8a48", size = 1577486, upload-time = "2026-07-23T01:52:31.937Z" }, - { url = "https://files.pythonhosted.org/packages/db/c2/00e23a1bf2abb70dd353f6987db7e7f2491d0261f7363997738c71c98f95/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:a3a8296e7ab5c295f53f1041487cb088e1480775aafbf7fe545d93b770a0f96f", size = 1751353, upload-time = "2026-07-23T01:52:33.688Z" }, - { url = "https://files.pythonhosted.org/packages/6e/7d/d51a706a8cbfa57f0611127daf61ab3ae02ab8420b0407412079227d1c65/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:5373dc80ad1aa2fb9ad95c83f24eef418bbda3a61375f128e5b0192e4f3f9b32", size = 1698681, upload-time = "2026-07-23T01:52:38.167Z" }, - { url = "https://files.pythonhosted.org/packages/ec/b0/90bd5cd9fdd9787cb4211d284d1fb8401339a933cb0227a15b71e789232f/aiohttp-3.14.3-cp310-cp310-win32.whl", hash = "sha256:a3e22975f905b89a55a488c2a08f2fdb2186175349e917d48985cc468a3d4c6e", size = 456733, upload-time = "2026-07-23T01:52:41.823Z" }, - { url = "https://files.pythonhosted.org/packages/d8/15/fe5b8f6a71ae112bc677163d0b0701bda5dc15005249582258ede0eb88c7/aiohttp-3.14.3-cp310-cp310-win_amd64.whl", hash = "sha256:bdd0e2834dce1a26c1bbe26464861e16bbe217042cbff619247c11594472518c", size = 480460, upload-time = "2026-07-23T01:52:43.905Z" }, - { url = "https://files.pythonhosted.org/packages/54/00/45e98b6645cd7f00a4b78b749ebd309094b0eaeb2d2e96157eadbc0d0050/aiohttp-3.14.3-cp310-cp310-win_arm64.whl", hash = "sha256:eac645b09bcfdf73df7536331f0678c1086ea250981118ddb5199e17ccef72bb", size = 453479, upload-time = "2026-07-23T01:52:46.075Z" }, - { url = "https://files.pythonhosted.org/packages/f8/5c/b3e4ff8ad43a8afef9602c5e90285936da1beaea8b029016b793891f03c3/aiohttp-3.14.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:e568e14940c09955aa51f4e645b6daa18a581c5dcfcd73744dcc86a856e3ced3", size = 764250, upload-time = "2026-07-23T01:52:48.525Z" }, - { url = "https://files.pythonhosted.org/packages/0e/da/f1b384465e51449d844056b75070461da03a9a23e6c1747003695bf4172a/aiohttp-3.14.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:54cfcdee2770dac994417cbb0ee1f3eb0e7cb6b30c79bf44f2c02ff79ec5124a", size = 516281, upload-time = "2026-07-23T01:52:51.047Z" }, - { url = "https://files.pythonhosted.org/packages/b9/3f/01264f820ee2e3712a827892b1cd6ff80f3300c1fcbffbb45714a915d47a/aiohttp-3.14.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:21c016079415ed3fd676963e9793700a566d85dbbd6bfc564b9b2d209147dcc8", size = 514742, upload-time = "2026-07-23T01:52:53.779Z" }, - { url = "https://files.pythonhosted.org/packages/9e/8d/a71c6f2db52ac1ed142b133f7feddaa6b70539c3f4de24d7e226c95b794c/aiohttp-3.14.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d6088ec9894113802bddb3c09e974929aed2c7b3a8c456219b8aab4481f1a239", size = 1780613, upload-time = "2026-07-23T01:52:56.948Z" }, - { url = "https://files.pythonhosted.org/packages/a5/11/3dd9b3fb3a170f6ec9011b5291d876a6fab4086714c9e158600edf01b4fd/aiohttp-3.14.3-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:16ea7e24c309fb7c0bbd505d149abe4fe4dccfb8db911db7dbec0921bc889a6f", size = 1737688, upload-time = "2026-07-23T01:52:59.294Z" }, - { url = "https://files.pythonhosted.org/packages/6d/3e/834c26918be7d88068822b40e0db30fca50b5f4fe79104aa16a93f1d74e6/aiohttp-3.14.3-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:56f355e79f71aef2a85c80305cc915f894b170dba76de5fe84f6351939b83c06", size = 1845742, upload-time = "2026-07-23T01:53:01.641Z" }, - { url = "https://files.pythonhosted.org/packages/cc/c9/49ab8572df7d66bc13d11e31f781292badb04180dd87ba98733066c6aed7/aiohttp-3.14.3-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:18c441d0a8fca6de8d1f546849b9f0ab20d435993e2c5b59562b2fae6be2f929", size = 1928412, upload-time = "2026-07-23T01:53:04.018Z" }, - { url = "https://files.pythonhosted.org/packages/a5/b9/2b8f0c0ce09c87a1daf80fd483431b56b1435d3f62789bc86f572e1245de/aiohttp-3.14.3-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:53e7b4ce82b54a8bcc71b3b67a5cbd177ca1d7f592cbc92cd38b7349f73482db", size = 1786220, upload-time = "2026-07-23T01:53:06.481Z" }, - { url = "https://files.pythonhosted.org/packages/85/00/9c45f81de11710460edfa1dc81317b6e882703b160926c879a9d20da9fcc/aiohttp-3.14.3-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f55119f7bf25f49ed210f6096090715da24f2943c62102448915fde3c62877ce", size = 1637231, upload-time = "2026-07-23T01:53:10.258Z" }, - { url = "https://files.pythonhosted.org/packages/19/ce/967d628e910756f3539c6107cb7844a1b69440dcb3029a5ee7871b09ab63/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:9aa6e61fdf20105c4144e755bd586008ff450791d67b1c8146fdc15959c4d51c", size = 1753161, upload-time = "2026-07-23T01:53:13.817Z" }, - { url = "https://files.pythonhosted.org/packages/11/b2/0c3d4114f0aee4f580f5b3b4eb71b24d7a23b834ea506a4dfebe76513f35/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:ccd4893707b3e2a13e39c90d43cf80edf2e4d0457935bcc103bf2346214c3f15", size = 1756356, upload-time = "2026-07-23T01:53:16.211Z" }, - { url = "https://files.pythonhosted.org/packages/63/5d/99e7d91c82f1399d1ae2a854e080bd1493fbc31e5e959dbc4ec33dac3bec/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:b2466434105a4e03113c36ec775cc2ebe6676b62eae326fa670bb607ef788c1c", size = 1819846, upload-time = "2026-07-23T01:53:18.289Z" }, - { url = "https://files.pythonhosted.org/packages/ad/05/d5e1cb6480eeffd3f901d40a2c5e2d1e7effdc797837da3b490272699f13/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:ba59d59aba08ac02fc03b0c8983ccd5ee39a199d0552ce9e6d2b4845b34d59ae", size = 1628531, upload-time = "2026-07-23T01:53:23.86Z" }, - { url = "https://files.pythonhosted.org/packages/c9/90/b934682bcaefae18a9e04f3dff5b68522ba810906358ae5029b68110ea3b/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:ed099d105449c4f9e84f24af203cd131349d4761d8813fa7e02c32e7128cd910", size = 1832712, upload-time = "2026-07-23T01:53:27.551Z" }, - { url = "https://files.pythonhosted.org/packages/21/df/6061679faaf81fac746e7307c7adb71e858071a5d34c27583afefc64f543/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:152516815ef926786a0b6ae2b8f1fd2e0c71582dee0b435636865316fd4891b7", size = 1775014, upload-time = "2026-07-23T01:53:30.223Z" }, - { url = "https://files.pythonhosted.org/packages/8a/1d/f854878bbc69b88faefe924b619a34a6f59ec05fd387c77690667eaa75eb/aiohttp-3.14.3-cp311-cp311-win32.whl", hash = "sha256:a4af35c443e0b1a1bd6a8af3f3485d7fda15c142751a00f3ff8090f0b93346fa", size = 456006, upload-time = "2026-07-23T01:53:34.97Z" }, - { url = "https://files.pythonhosted.org/packages/73/0c/2af9d1674baccd1dbd47282a93d660a22e57ef6167c856deb24b4214fbab/aiohttp-3.14.3-cp311-cp311-win_amd64.whl", hash = "sha256:e1e74298bab6ee0d6e749ed4fd1901c7e604bdda32c03d787a2cc71c46d0433d", size = 481069, upload-time = "2026-07-23T01:53:39.673Z" }, - { url = "https://files.pythonhosted.org/packages/8e/76/88401ff3fc95e85c5fc38d588f36f55e61ecb64343b2bc8d69326f453cc0/aiohttp-3.14.3-cp311-cp311-win_arm64.whl", hash = "sha256:03cd2bde3d7f085b64e549c985f4bb928cad7e8ecf5323bfca320db548d81b39", size = 453021, upload-time = "2026-07-23T01:53:43.749Z" }, - { url = "https://files.pythonhosted.org/packages/18/d4/eb96299230e20acf2efae207cb8d69051f1f68e357e5ea5e479bf6fb097a/aiohttp-3.14.3-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:39aded8c7f3b935b54aab1d8d73c70ec0ee2d3ec3b943e0e86611bc150ba47f5", size = 754690, upload-time = "2026-07-23T01:53:47.332Z" }, - { url = "https://files.pythonhosted.org/packages/88/11/e7a70a209eb9a067c0d3212b518a0134e3484f5178c7533878b6b514d469/aiohttp-3.14.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:5bcb6ff3fdab1258a192679ff1a05d44f59626430aa05cd1a9d2447423599228", size = 509484, upload-time = "2026-07-23T01:53:51.159Z" }, - { url = "https://files.pythonhosted.org/packages/30/07/4bbc222cc8dbe31d4c3e8a5baad2286e4d42026ac0c570027b89afce6344/aiohttp-3.14.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:617105e2c3018ee38d0c8ce5ee3c84f621a6d8b9f723202aacaff28449ca91ee", size = 511949, upload-time = "2026-07-23T01:53:55.083Z" }, - { url = "https://files.pythonhosted.org/packages/54/b9/42e74c46b7b7c794b995bbc1f573fb48950c38b19d8600c62a6804ee2d67/aiohttp-3.14.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f631fe87a6f30df5fbe6d79640b25e4cffb38c31c7fb6f10871517b84b0f8c1a", size = 1765282, upload-time = "2026-07-23T01:53:59.662Z" }, - { url = "https://files.pythonhosted.org/packages/6b/ed/62bc4d74363ad346d518e0720363a949f63e2e23439a79eb5813d4d29bb3/aiohttp-3.14.3-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:a94dbaae5ae27bd849c93570669bff91e0510f33a80805738e3de72a7be0447b", size = 1741511, upload-time = "2026-07-23T01:54:04.063Z" }, - { url = "https://files.pythonhosted.org/packages/d0/9f/181e8a8bc79e47d13c7fc4540bd7a3b729d9505609c61f392a8dd2fbfe55/aiohttp-3.14.3-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:8f2f1c4c032c7cedd7d8da6f54c97b70266c6570c3108d3fdffee7188bb70529", size = 1810680, upload-time = "2026-07-23T01:54:09.882Z" }, - { url = "https://files.pythonhosted.org/packages/5c/9a/dec94d6ad694552fe3424e3f1928d7a606a5d9d9433a04e7ecdd9d38ae7f/aiohttp-3.14.3-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:ea05e1f97ceea523942d9b2a7d7c0359d781d683d6b043f5943a602b14da4787", size = 1905646, upload-time = "2026-07-23T01:54:13.475Z" }, - { url = "https://files.pythonhosted.org/packages/52/b7/7cd31f29d6055bd711ae6e669367fba6f5ae9de463910a793e30556a8db7/aiohttp-3.14.3-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:543906c127fb1d929b95076db19b83fa2d46751006ff1e23b093aa5ac4d8db42", size = 1792122, upload-time = "2026-07-23T01:54:15.752Z" }, - { url = "https://files.pythonhosted.org/packages/66/73/10b1ef93afa61f4963c746257b70ced619cf31a4798671de5fdb2608501d/aiohttp-3.14.3-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0a5ff2dfbb9ce645fa5b8ef3e02c6c0b9cc3f6030ff863d0c51fffc50cb5541b", size = 1591127, upload-time = "2026-07-23T01:54:19.489Z" }, - { url = "https://files.pythonhosted.org/packages/49/ed/3b203fa6de1b338c14acdc06bf6ca9b043b7944f005966958c2ced932cde/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:041badb8f84396357c4d3ad26de6afd7a32b112f43d3c63045c0c8278cfd2043", size = 1725210, upload-time = "2026-07-23T01:54:24.129Z" }, - { url = "https://files.pythonhosted.org/packages/28/b7/1c2aab8c706436dcc28598452488ac9cd7c409da815237c28c27d58993e6/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:530125ee1163c4219af35dc3aa1206e541e7b31b6efc1a3f93b70a136f65d427", size = 1764848, upload-time = "2026-07-23T01:54:27.973Z" }, - { url = "https://files.pythonhosted.org/packages/54/50/94c28f08b131c4bf10984ea2c7a536c9920608bb2d6e7f95642c30cc87b7/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:c8653fd547c93a61aadc612007790f5555cdd18946fa48cf45e26d8ea4ea473d", size = 1777102, upload-time = "2026-07-23T01:54:31.775Z" }, - { url = "https://files.pythonhosted.org/packages/13/d4/e7d09ba7d345fb2d74440fd2fa033c5e079fac05552927705986f41a364f/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:89176250f686cb9853c0fb7ead90e639e915b84a6f43eedc2a4e7ec21f1037f0", size = 1580205, upload-time = "2026-07-23T01:54:34.518Z" }, - { url = "https://files.pythonhosted.org/packages/a3/84/072a91d68e1e1eb587985b54baab94221277f877e8ef274fc213a0ceae28/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:3a26434dafe408229ff3403458ca58de24fb51936504decac49ce6755f77e59d", size = 1797219, upload-time = "2026-07-23T01:54:36.995Z" }, - { url = "https://files.pythonhosted.org/packages/e0/eb/aad34e897e668424d6e995da5dff8a4a09af93363d3392488772957a63aa/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:d1558173930a5a8d3069cee5c92fc91c87c4dbcb099debbb3622053717145a19", size = 1768629, upload-time = "2026-07-23T01:54:40.103Z" }, - { url = "https://files.pythonhosted.org/packages/b6/2b/6bb88ddba0fecd9122aa3ebcad25996cf6c083a4a7040dbb3a4f97972af6/aiohttp-3.14.3-cp312-cp312-win32.whl", hash = "sha256:16100ad3ab8d649fdfbee87602d9d2dcdca9df0b9eda8a1b5fdc0d41f96da559", size = 451481, upload-time = "2026-07-23T01:54:42.547Z" }, - { url = "https://files.pythonhosted.org/packages/76/9b/f2f8f108da17ecef2cc3efc424e8b7ad3782b1a8360f7b8eae8ced84f6ea/aiohttp-3.14.3-cp312-cp312-win_amd64.whl", hash = "sha256:33a2d7c28d33797a2e99923dffa63f83d908a19b6bf26cfe80fa790aa5e1a75a", size = 476845, upload-time = "2026-07-23T01:54:44.853Z" }, - { url = "https://files.pythonhosted.org/packages/3e/44/28dac80a8941b604f4da10ce21097614ca1bf905ce93dca28d8d7de9c1e7/aiohttp-3.14.3-cp312-cp312-win_arm64.whl", hash = "sha256:362a3fd481769cac1a824514bcd86fda51c65e8fe6e051099e008fddde6db17c", size = 448050, upload-time = "2026-07-23T01:54:47.087Z" }, - { url = "https://files.pythonhosted.org/packages/57/be/5afd201cc0ab139029aadb75392efe85a293403d9dd3a3226161c21ce00c/aiohttp-3.14.3-cp313-cp313-android_21_arm64_v8a.whl", hash = "sha256:2e9878ae68e4a5f1c0abe4dd497dbc3d51946f5837b56759e2a02e78fa90ef86", size = 506269, upload-time = "2026-07-23T01:54:49.075Z" }, - { url = "https://files.pythonhosted.org/packages/22/09/dec8189d62b45ade009f6792a2264b942a90cb88aeaf181239933cd72c3c/aiohttp-3.14.3-cp313-cp313-android_21_x86_64.whl", hash = "sha256:f3d2669fe7dec7fc359ecdb5984b29b50d85d5d00f8c1cb61de4f4a24ee42627", size = 515166, upload-time = "2026-07-23T01:54:51.894Z" }, - { url = "https://files.pythonhosted.org/packages/28/24/2854869d29ed8a8b19d74f9ec6629515f7e04d02dd329d9d179201e58e47/aiohttp-3.14.3-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:cc7cb243a68167172f48c1fd43cee91ec4b1d40cefd190edd43369d1a6bc9c82", size = 486263, upload-time = "2026-07-23T01:54:54.223Z" }, - { url = "https://files.pythonhosted.org/packages/d4/dd/57187c8be2a35aea65eaee3bd2c3dcbbcf0204f5106c89637e3610380cd1/aiohttp-3.14.3-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:78253b573e6ffab5028924fc98bc281aae05445969982a10864bc360dea2016c", size = 492299, upload-time = "2026-07-23T01:54:56.236Z" }, - { url = "https://files.pythonhosted.org/packages/b9/11/06ae6ed8f0d414edf4068861e233d8fe23ee699bfd4b3ceb8663db948a62/aiohttp-3.14.3-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:7041d52c3a7fa20c9e8c182b534704abb19502c8bdcbde7ab23bfda6f642394f", size = 502235, upload-time = "2026-07-23T01:54:58.377Z" }, - { url = "https://files.pythonhosted.org/packages/7e/a3/559639c34a345d2cf7c52dff6838119f2eaf29eb508227b5b83f573af813/aiohttp-3.14.3-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:ac74facc01463f138b0da5580329cfcc82818dea5656e83ddcd11268fc12ff80", size = 750883, upload-time = "2026-07-23T01:55:00.65Z" }, - { url = "https://files.pythonhosted.org/packages/91/cd/41e131f13afd1e7b0172a9d9eda085ef90eb8439f41f0d279db81ed3ae60/aiohttp-3.14.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:d6218d92e450824e9b4881f44e8c09f1853b490f9a64130801024a4793b1b3b0", size = 508473, upload-time = "2026-07-23T01:55:02.945Z" }, - { url = "https://files.pythonhosted.org/packages/bc/6b/e7f13410d391c6e55b4c007a8de024355389d7d459e3d64c42b2d33617e5/aiohttp-3.14.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:11fb37ef075669eee52ab1928fbf6e1741fada40409fa309ebde9607a962aebf", size = 509190, upload-time = "2026-07-23T01:55:05.173Z" }, - { url = "https://files.pythonhosted.org/packages/97/21/6464573e53d69672cc1eada3e5c5cb2d2efa82701e8305a0f2047a576967/aiohttp-3.14.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:55bdcc472aafe2de4a253045cc128007a64f1e0264fb675791e132ea5edaa3bd", size = 1761478, upload-time = "2026-07-23T01:55:07.383Z" }, - { url = "https://files.pythonhosted.org/packages/1a/81/d217043a4c17fbce360905e3b2bdd20139ebc9a2de836d035d179c4da006/aiohttp-3.14.3-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:c39846c3aad97a8530c89d7a3869a8f8e9e3762c6ac0504481e5c80948f7e807", size = 1735092, upload-time = "2026-07-23T01:55:09.803Z" }, - { url = "https://files.pythonhosted.org/packages/a1/66/e13a02d0eeb1a9a502402a977abb4e4abff9fe4051c26f80558c57a7c975/aiohttp-3.14.3-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:5895ef58c4620afe02fa16044f023dc4dafec08158f9d08874a46a7dbc0341b8", size = 1800546, upload-time = "2026-07-23T01:55:12.012Z" }, - { url = "https://files.pythonhosted.org/packages/26/5e/57d42fca1d18cb5acc1cad945d017fabc5d6ae71d8a08ad66be8dc3ee544/aiohttp-3.14.3-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:fa9467a8113aa69d3d7c55a70ef0b7c636010a40993f3df9d9d0d73b3eb7ef24", size = 1895250, upload-time = "2026-07-23T01:55:14.357Z" }, - { url = "https://files.pythonhosted.org/packages/ca/1c/7da8d08e74d56f00070822f9638ff3f1c563f8ad87d1efa996c87bfc8644/aiohttp-3.14.3-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d7d2deec16eeedf55f2c7cf75b521ea3856a5177e123844f8fd0f114ce252cb5", size = 1789289, upload-time = "2026-07-23T01:55:16.668Z" }, - { url = "https://files.pythonhosted.org/packages/cd/0f/cf16bcf56896981c1a0319f5d5db9337994b5165730c48a8fa07e9b34be6/aiohttp-3.14.3-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:dd54d0e8717de95939766febac482ac0474d8ac3b048115f9f2b1d23a16e7db4", size = 1586706, upload-time = "2026-07-23T01:55:18.913Z" }, - { url = "https://files.pythonhosted.org/packages/fe/6f/76eac12a7f2480e1e304f842efdb07db33256b0d9165b866b6ef0806c202/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:df82f3787c940c94986b34222d59c9e38843fba85139f36e85255a82ad5355a9", size = 1724652, upload-time = "2026-07-23T01:55:21.296Z" }, - { url = "https://files.pythonhosted.org/packages/39/b6/19c8c592baeeb94b75f966547d40c02ac7590902306ec5863d5c027cf506/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:42a67efc36300d052fb4508a53e8b6901b9284b599ae63945c377569c5fcc1e1", size = 1756239, upload-time = "2026-07-23T01:55:23.705Z" }, - { url = "https://files.pythonhosted.org/packages/dc/c9/4e9383150296f97f873b680c4de8fb2cd88608fb9f48c79edcb111611abc/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:7a75aa63cbf9b21cfaf60dc2657e19df2c2867d91707d653fee171ffeedd1371", size = 1769161, upload-time = "2026-07-23T01:55:26.082Z" }, - { url = "https://files.pythonhosted.org/packages/aa/1e/147bdc6cc5de5f3ab011be8bf5d6e786633249f22c20bae06f85e45f5387/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:e92eb8acc45eb6a9f4935071a77edf5b85cc6f8dfad5cd99e97653c26593cdde", size = 1578759, upload-time = "2026-07-23T01:55:28.846Z" }, - { url = "https://files.pythonhosted.org/packages/fd/31/78388a9d6040ece2e11df62ea229a822cf5e52d238374b220ae9975b2623/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:b014a6ed7cf912e787149fdc529166d3ceabac23f26efeea3158c9aba2354e7e", size = 1792025, upload-time = "2026-07-23T01:55:31.457Z" }, - { url = "https://files.pythonhosted.org/packages/03/51/a3d29fdf2c25d796746af8ad6fe56a45d6256c38b0a8a2ed752e1160b3a2/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:3d4f72af88ac2474bb5bca640030320e3d38a0163a1d7533500e87be458eef71", size = 1768477, upload-time = "2026-07-23T01:55:33.87Z" }, - { url = "https://files.pythonhosted.org/packages/29/a6/442e18b5afeade534d877a2dc3c3e392aff8d49787890b0cf84790410267/aiohttp-3.14.3-cp313-cp313-win32.whl", hash = "sha256:5f08ec777f35ee70720233b8b9811d3bb5d728137f30ac91b7457709c3261ac0", size = 451069, upload-time = "2026-07-23T01:55:36.121Z" }, - { url = "https://files.pythonhosted.org/packages/9d/69/3d876ac02659f271cf7f6769f14a8e3de5b6e888ed8b5a7e998086a4cec8/aiohttp-3.14.3-cp313-cp313-win_amd64.whl", hash = "sha256:dff9461ec275f22135650d5ba4b4931a11f3958df7dfbb8db630000d4dee0883", size = 476518, upload-time = "2026-07-23T01:55:38.303Z" }, - { url = "https://files.pythonhosted.org/packages/b2/0e/50d6e6471cd31edce8b282bdec59375a3a69124d8a989a0b1313355cae52/aiohttp-3.14.3-cp313-cp313-win_arm64.whl", hash = "sha256:ddcac3c6b382e81f1dd0499199d4136b877beb4cb5ef770bbbfba56c4b8f55d2", size = 447676, upload-time = "2026-07-23T01:55:40.451Z" }, - { url = "https://files.pythonhosted.org/packages/c8/20/887fdcf832326571b370ffc347b3e70abe101096f3720126aac161b1d872/aiohttp-3.14.3-cp314-cp314-android_24_arm64_v8a.whl", hash = "sha256:49f7325beb0f85ef4aef5f48f490269575f83e6e2acad00a1d80b807eb027062", size = 509067, upload-time = "2026-07-23T01:55:42.618Z" }, - { url = "https://files.pythonhosted.org/packages/ad/a3/92cec936f78cc4bf0fa5554ebe593b73459d94e3c62303e1902a4cccb6f7/aiohttp-3.14.3-cp314-cp314-android_24_x86_64.whl", hash = "sha256:e3be98a7c30b8c25d573dafba7171d66dfb05ee6a9070fc46535464ff97700a6", size = 514774, upload-time = "2026-07-23T01:55:44.937Z" }, - { url = "https://files.pythonhosted.org/packages/29/ba/2a0c38df3fc557620b6a5acd98364af050053b6285b4dc7ee74100c63c18/aiohttp-3.14.3-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:614c61d478b83953e261d02bb2df750f17227cd33ef8002945bf5aebbde21919", size = 488134, upload-time = "2026-07-23T01:55:47.135Z" }, - { url = "https://files.pythonhosted.org/packages/48/d6/d51b7d4bf309af3693940d8ffd2b9ed0b682434ef85959b7c9c137f60cf8/aiohttp-3.14.3-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:1caa7b0d05f3e3a36f87788c59e970a7ee1cefcfcbb924a9f138c4a6551c9cb7", size = 494201, upload-time = "2026-07-23T01:55:49.451Z" }, - { url = "https://files.pythonhosted.org/packages/3f/5a/8f624384e5f1efabb5229b94157eb966b021e97bdb188c62860c2ae243c2/aiohttp-3.14.3-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:dfa68deb2a443bdaa3ea5297b0699c1464f08aef3812b486d1348eee61b07dc0", size = 502766, upload-time = "2026-07-23T01:55:51.656Z" }, - { url = "https://files.pythonhosted.org/packages/a6/26/4ff0164370deec18fb19254ee4ab10b7a73304ac0c860b13f5f84663759b/aiohttp-3.14.3-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:e72ee89e28d907a18f46959b4eb0bb06701cc7f8cf4366e00029e2ccfaaf5924", size = 756557, upload-time = "2026-07-23T01:55:53.964Z" }, - { url = "https://files.pythonhosted.org/packages/97/a3/7056b86dc0d9ec709ea9777eae3b0161428f943372f8b98c01c11593b682/aiohttp-3.14.3-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:ad4c8b7488d745d2ca4838ebd8ae5ba9b56341d30b1da43640e4ce87f9f49646", size = 510168, upload-time = "2026-07-23T01:55:56.22Z" }, - { url = "https://files.pythonhosted.org/packages/85/ed/0357a015892fd68058bf2d39d3fd1958e459b997a7db30aaa6aaa434ae96/aiohttp-3.14.3-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:db332af25642007330fca8be5c4d194caf2bea7a7fc84415aff3497af5dfee6b", size = 512957, upload-time = "2026-07-23T01:55:58.437Z" }, - { url = "https://files.pythonhosted.org/packages/47/d1/8aba53f15ccb2238405f5e9d30e2a8ca44f93878c26e7165ade00d374b1c/aiohttp-3.14.3-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:25bd2708db6bdf6a6630dd37bdcdfcb47c4434d22ac69c64665b802910140b30", size = 1750149, upload-time = "2026-07-23T01:56:00.856Z" }, - { url = "https://files.pythonhosted.org/packages/49/bd/40c3fee327529284375c6701cbb0fa4600cc2e8432af1378f897e2ef7d3a/aiohttp-3.14.3-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:cef89a58e628c4efcac3275c2d68083f82426dcdc89c1492a6f654f9f7ea6ab9", size = 1707685, upload-time = "2026-07-23T01:56:03.371Z" }, - { url = "https://files.pythonhosted.org/packages/2a/a3/ca0cc6724cca8114b05694abd916060758c79894c3aa5b012cdadc1bc28e/aiohttp-3.14.3-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:c23ec8ee9d5ab2f5421f9c7fffce208435607af27fd46d4a44e031954352838f", size = 1803911, upload-time = "2026-07-23T01:56:05.817Z" }, - { url = "https://files.pythonhosted.org/packages/95/b5/85b099c299c3ffd38ad9b3e43694c8a346934e4a30c88c4fd5a841234f77/aiohttp-3.14.3-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:e2667f0bbe7eb6c74eae5e9691441ad186e5845ca3cff63230fc09c4e7514f5d", size = 1876929, upload-time = "2026-07-23T01:56:08.413Z" }, - { url = "https://files.pythonhosted.org/packages/d5/b7/1da684a04175473fa4cddbf9a2f572e79514c3fd27a74597f43057d4f3da/aiohttp-3.14.3-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:18cb43369747b2ae007bd2655fb8e63a099c2ff1d207962943636dac989b3147", size = 1761112, upload-time = "2026-07-23T01:56:10.918Z" }, - { url = "https://files.pythonhosted.org/packages/d1/16/bc4b55e3e5cb175fd69c53c90d60d2f47797cb343da5106e23863dc4dba4/aiohttp-3.14.3-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:d77640cc618c1d99fc4f8589c0f24a730adfa54eb1e57ef7bf0c8dfb78da898c", size = 1583500, upload-time = "2026-07-23T01:56:13.613Z" }, - { url = "https://files.pythonhosted.org/packages/2a/e8/13a9d957a1ee40837f46aa30f0f4c657e673ad86a2e6362a9f9be20d26d9/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:53e5179d8abb5710f8e83ba207c41c8d1261fcffd4616500e15ca2b7a33be10a", size = 1713940, upload-time = "2026-07-23T01:56:15.969Z" }, - { url = "https://files.pythonhosted.org/packages/38/05/d33c680c1bcf1c7e130f9cbfc1fc02fe8bb0c4af2a94a53dd5fb56131e5c/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:cd817772b2fcf2b8c0905795318485f9ec16eae60b29feb7f4c77085311637f0", size = 1724413, upload-time = "2026-07-23T01:56:18.591Z" }, - { url = "https://files.pythonhosted.org/packages/85/1d/af798d306f7a74b6a632dbcabcf62a4c91391b7582d2a8c6d7712e2cc54e/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:4e3ac92d90e92773b2362d506068e9a948192bd553e743c5b2429e28527c8661", size = 1770748, upload-time = "2026-07-23T01:56:21.074Z" }, - { url = "https://files.pythonhosted.org/packages/a8/92/ad720d472556a995049206867765e9410969684f86ee09423ff9969044c1/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:3f42e9b78301f11c8f861746175d8b9c1ccef713fcad9eab396e2f6db8ed4a22", size = 1577564, upload-time = "2026-07-23T01:56:23.475Z" }, - { url = "https://files.pythonhosted.org/packages/60/ad/0ed7586cbef7a884e23a752fa2bb987a122e6a5dd50dab109258d0a95193/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:9d9edccfe496b476db5f398d97b865e9a6752bcf8aec4eef8390ce20fb64bb41", size = 1782080, upload-time = "2026-07-23T01:56:25.994Z" }, - { url = "https://files.pythonhosted.org/packages/97/ea/dbaed0d73e8a69aad653b045dab451c67c2454bb731a37b45a86593e9422/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:1c5ec8fb1bcc31a8466f74aaf26c345d5c386fa4bd08a3f0eb9c7a4a3fe8b5bf", size = 1745813, upload-time = "2026-07-23T01:56:28.604Z" }, - { url = "https://files.pythonhosted.org/packages/81/1b/6893d4bc57e434fc93a6c9217c637d967a0b651d989f6e3265179375754a/aiohttp-3.14.3-cp314-cp314-win32.whl", hash = "sha256:38901a84da3ce22249f6e860bf8f90d141bcab7da090cc398f8bb58c0e44b7da", size = 455872, upload-time = "2026-07-23T01:56:31.031Z" }, - { url = "https://files.pythonhosted.org/packages/f5/8b/c7baa1ba1eda4db6989baefe5de6d99834921b84ebd7918624febcb9f290/aiohttp-3.14.3-cp314-cp314-win_amd64.whl", hash = "sha256:8b3b60de05f3dcb6f6a00f818bb2ec781cee4de0645f59ccaf99b1d1823b6100", size = 481030, upload-time = "2026-07-23T01:56:33.365Z" }, - { url = "https://files.pythonhosted.org/packages/22/8c/c29d067df825a2df88ca432db848aa2fe8199598359cc06c12b09320cac9/aiohttp-3.14.3-cp314-cp314-win_arm64.whl", hash = "sha256:1576145bdceeb92382d899751e12743a3a5b8e460a841e3e50543859e54864dc", size = 453669, upload-time = "2026-07-23T01:56:35.731Z" }, - { url = "https://files.pythonhosted.org/packages/6a/a4/9c033beb355d39b6147980597ec9645e4729243f686ee4dc73945de72030/aiohttp-3.14.3-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:8800c996b01c2772a783e3e46f3e1abd5823029adca0df54231960de9bfefa5b", size = 791403, upload-time = "2026-07-23T01:56:37.972Z" }, - { url = "https://files.pythonhosted.org/packages/80/ca/87c32a0a7704583cfc49660bd817889bae5b830bf53b5dcb4e92145ac2da/aiohttp-3.14.3-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:ebe8e504f058fe91223351cecd2d9d6946c9d241bb0250d898ffbdf584cc72b0", size = 526413, upload-time = "2026-07-23T01:56:40.523Z" }, - { url = "https://files.pythonhosted.org/packages/9e/d8/8ec0e471248c500acdce2be3f46db8fb62b5eb60efef072529cc85ee1d26/aiohttp-3.14.3-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:30402d03a7c0ff52bce290b57e564e9079fd9d0cb545c8aba73f86a103162d2e", size = 532135, upload-time = "2026-07-23T01:56:42.876Z" }, - { url = "https://files.pythonhosted.org/packages/fe/45/f8919fd936e8b79fcd9bda7b6d8e62613462a713f4f17987fd7c34399142/aiohttp-3.14.3-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9fc7b5bfec6573f3ae844f457fdde5adeb713f8b8e4a81ad64fc207b49383716", size = 1922742, upload-time = "2026-07-23T01:56:45.528Z" }, - { url = "https://files.pythonhosted.org/packages/f6/ec/9ca76b28a27525b0cc53e20842e0228b022f301ce1f436b7d814b4aaf2df/aiohttp-3.14.3-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:8a5fd34f7f7410d1730d5c2ba873cacb2eed3fede366feb268a70ba22581ed8f", size = 1787371, upload-time = "2026-07-23T01:56:48.045Z" }, - { url = "https://files.pythonhosted.org/packages/b1/04/6acdbf17315f7b55f1937e3387acb89a3cddeb4995689553d064af8e92ab/aiohttp-3.14.3-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:270d3dace9ca2f10f0da5d8ebe519b7a310fc6112ed916e32df5866df0888553", size = 1912623, upload-time = "2026-07-23T01:56:50.605Z" }, - { url = "https://files.pythonhosted.org/packages/86/e6/438b0c79ca6f45eb9fd9817dd4c01a91919a38c0de5ee9e05e2b4dc0ece7/aiohttp-3.14.3-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:3ae5b3a59436d089b5395d910121a390feed4d00578eb95a0fd1a329fe963100", size = 2005515, upload-time = "2026-07-23T01:56:53.153Z" }, - { url = "https://files.pythonhosted.org/packages/bb/6b/62cbd6577758699525f5c712d1ddef57d9875fbab0ae8d5f5a202fd598f8/aiohttp-3.14.3-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2498f0fe69ead802f9675beca44a7c21c62fdaa4ec5145ea1c3ad6edbee29f85", size = 1879906, upload-time = "2026-07-23T01:56:55.818Z" }, - { url = "https://files.pythonhosted.org/packages/00/95/18bcbf830a21dc3aae24d8f6b6feaf3db1d2090242d00a7868db2ffb0b67/aiohttp-3.14.3-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:a0dc483c00da8b673abbb367eb6f8d8f4bcec30eb58529ea13cb42e7fd2dfa33", size = 1675849, upload-time = "2026-07-23T01:56:58.861Z" }, - { url = "https://files.pythonhosted.org/packages/a9/19/47f4968659c5e23606c3790c80fc624e691c153d036148449ee84d31b287/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:c7d3a97c678d34fc5b59da671ee9cd630096ddc643e7b5a30d54a2a6f3574d3f", size = 1843496, upload-time = "2026-07-23T01:57:01.591Z" }, - { url = "https://files.pythonhosted.org/packages/64/af/38c33c4dd82fddcb4e56c4653b6f1072a8edbc6b7fa15809f14932c41e2d/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:f8fb78a83c9e5f741ca3a68cfb455c1f5bb83b4e7249a3848b3cd78d0a8563b0", size = 1827746, upload-time = "2026-07-23T01:57:05.131Z" }, - { url = "https://files.pythonhosted.org/packages/a1/9d/0537cda4885ac8f5b7053d164dd06312f4c483a4edcb8ee5b8aaf2a989bf/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:74ab5b6a9fb13e873e5a90946588baecaf488745e1db1a4a5c433f971f035098", size = 1853810, upload-time = "2026-07-23T01:57:08.043Z" }, - { url = "https://files.pythonhosted.org/packages/19/fe/26f9c5e6458385aa86497836b0dea6fb2f027827d63f37c7856cce9286ee/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:bd52f811e65f6fb634b1047159657c98f52b407f8efec907bcfc09da9a4c0a25", size = 1668895, upload-time = "2026-07-23T01:57:10.837Z" }, - { url = "https://files.pythonhosted.org/packages/ec/4c/618b1db9b9ba079b8875d2cdf78e7c4a3bf72903bd5850fee7dd9544600a/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:f0f177d1b195b9e06376cfd7d308d8a1b920909a609d03ac82a8c73bbb16d3b9", size = 1883833, upload-time = "2026-07-23T01:57:13.672Z" }, - { url = "https://files.pythonhosted.org/packages/94/c6/bd959bd1e4771f9fd944e9e436224c48c77b018b73b519b5aad346335bcc/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:498c6c623134f8e09a3c4e60bcd607a0b4590dd7dbf08dd40851b27cbb520ccb", size = 1844251, upload-time = "2026-07-23T01:57:16.593Z" }, - { url = "https://files.pythonhosted.org/packages/5e/19/08d41839658bdd44a0ed2480f3891705ecb487ce28c0dde62c9040c997e0/aiohttp-3.14.3-cp314-cp314t-win32.whl", hash = "sha256:b304db572b4368edd8dda8a2274f73156fe15558fca4a917cb8a09fc47af5963", size = 474180, upload-time = "2026-07-23T01:57:19.306Z" }, - { url = "https://files.pythonhosted.org/packages/99/5d/3cd6ef0a2b2851f7ab913b5b079334781bd50ff56a323e4454063377a080/aiohttp-3.14.3-cp314-cp314t-win_amd64.whl", hash = "sha256:b20032766aedf6261c7a566585a40867d092ac03a0d81592d5370ef9b054f99b", size = 500528, upload-time = "2026-07-23T01:57:21.762Z" }, - { url = "https://files.pythonhosted.org/packages/a4/37/cfd1ed540a4d318da025590d96b728e63713c09e9377950fc655dadeb856/aiohttp-3.14.3-cp314-cp314t-win_arm64.whl", hash = "sha256:2e1161602f45a54de2ce0905243a95f58cb42dcd378402f3697f5e0b21e9d2e7", size = 469280, upload-time = "2026-07-23T01:57:24.241Z" }, + { url = "https://files.pythonhosted.org/packages/b3/08/290e4be6e3ed239751c446505c324406a4ae8a82a15009a12a3c550f18d9/aiohttp-3.14.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:dea3b3653c1d0d6babd8ce09cb9e5a7776864315d9cfb1c569f926389874a261", size = 834853, upload-time = "2026-10-05T17:37:45.079Z" }, + { url = "https://files.pythonhosted.org/packages/81/81/ed5e04508ba1fcf9a34e0449c78009956e8256f62ebef708e2948594cf94/aiohttp-3.14.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:3099a389e5b5900fc79c6f613015ff3f8fa06a519744e6001cc68a31ba418cac", size = 560957, upload-time = "2026-10-05T17:37:47.497Z" }, + { url = "https://files.pythonhosted.org/packages/90/28/1a91411c53704db0481cc64b0f0c9465aa9d738856abdcaa3a5bbbe18180/aiohttp-3.14.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:70247156fc76e92919f9aacb820556cb30289a54784299a31714d030bb604d84", size = 553475, upload-time = "2026-10-05T17:37:49.099Z" }, + { url = "https://files.pythonhosted.org/packages/cf/2e/1038f3fa8832f9f4bed0f9f751f70dbc52bc4a09c66788f97bbfb0ce3d88/aiohttp-3.14.4-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:fdf2d2a6ad402797422949f4a200a60d43e3a021695c8a7804aa1d5bbef22652", size = 1845211, upload-time = "2026-10-05T17:37:50.728Z" }, + { url = "https://files.pythonhosted.org/packages/ea/54/e2253f17604c5c1c69a05e3c12400b51cd6a5fb32d7175592114d8c7a470/aiohttp-3.14.4-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:ba835fad8d4b5eaea0d34f9461cf499737a720a5f8bc6768d2f6d98a1d3ba8b5", size = 1814629, upload-time = "2026-10-05T17:37:52.481Z" }, + { url = "https://files.pythonhosted.org/packages/f1/ef/7bd1e45db925376720555d7268c2d642b113105263d37a522e41e1ba3a6c/aiohttp-3.14.4-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:0d4415ca5c9c8b24bc2f5733f870d4eab4929e680203559ba60131dd1a27852a", size = 1898528, upload-time = "2026-10-05T17:37:54.078Z" }, + { url = "https://files.pythonhosted.org/packages/5d/40/26d09668e7e0cadc16027566765aa4ce26e8a41276bad6764848c8b04d11/aiohttp-3.14.4-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:f6757e02c2c2b0d7985f57be87cf4a7c5b35708f849e1feaea3f77656ddb9dff", size = 2024385, upload-time = "2026-10-05T17:37:55.626Z" }, + { url = "https://files.pythonhosted.org/packages/73/38/0f1c4aab1cc9518e1bf874e2481e59e541b3e32330b9542e52bb2712f86f/aiohttp-3.14.4-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2a950bd8418ef54eccf5f9f517f08e37c1adab4bc50a470a0422ee1cc1032e29", size = 1859130, upload-time = "2026-10-05T17:37:57.342Z" }, + { url = "https://files.pythonhosted.org/packages/5f/98/09d5998ba4b5fe9f0cb97d794fab9d1b3d8245c5ec6a5fb84e41a8cec142/aiohttp-3.14.4-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:34cf6f2fe4fc1d7183e8cc0d8c48bbdda828a740bc372d8278126149714d343c", size = 1714768, upload-time = "2026-10-05T17:37:58.831Z" }, + { url = "https://files.pythonhosted.org/packages/c2/63/39d01a74d525d6443084d47ad4aa8c719f44a030149d03566f3761527465/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:bc0fbe4f79c3b156d754dd062718ffe404c3b31ca878d9d2b88ecdbc72ef8369", size = 1813228, upload-time = "2026-10-05T17:38:00.611Z" }, + { url = "https://files.pythonhosted.org/packages/39/6b/183d7b969bdb7892e86af74147b4afedbb4e03b8cad5006e41aa2034c288/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:d3d50a5a07a2b31a4369b86dd4a3acf3c2577c45091dbd5e884b198dec56480b", size = 1831844, upload-time = "2026-10-05T17:38:02.272Z" }, + { url = "https://files.pythonhosted.org/packages/2c/be/4c6df02b62083efd3f008974cf9016a4afd2023f5a9d2c3fd55499fcbac6/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:de15c46a63f46da881d219e44a04778c40114c756e5575b5ea38143b20eb3713", size = 1868738, upload-time = "2026-10-05T17:38:03.831Z" }, + { url = "https://files.pythonhosted.org/packages/86/21/406be8b0cf1105a35a6a6da16a95796be39b354e29bfca0d1626d822835f/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:caa4c0fc9b25e8c679baac68337e9c00deb6baf6601fe6f07e8511469cc1ceba", size = 1700006, upload-time = "2026-10-05T17:38:05.631Z" }, + { url = "https://files.pythonhosted.org/packages/4e/e6/beac98020ea0885ea1ee3b2ef59ec952405590fe2ccef2fa4ef7614c3c2b/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:3647f8c090632c70abb1e80826e4ee24faea3f895f0283b60e91a0b17aea5e34", size = 1889997, upload-time = "2026-10-05T17:38:07.578Z" }, + { url = "https://files.pythonhosted.org/packages/c4/89/d608dd9571988a529c7fead5bc79ad36b56fd52bad7941f40774acbc87e9/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:3f3e8030169843fb652a60a3d32c206e03f260198aa398985a48b41cd7e42f0a", size = 1844619, upload-time = "2026-10-05T17:38:10.003Z" }, + { url = "https://files.pythonhosted.org/packages/7e/7d/7f51e6338d2c74b75173ee66fcb50d778d5407c32f34e76ef1c4b25d0d75/aiohttp-3.14.4-cp310-cp310-win32.whl", hash = "sha256:a1205cbdddfca1428129bb6d23e0b292b09e681df951fa828145d83a63ffc0ca", size = 489598, upload-time = "2026-10-05T17:38:11.795Z" }, + { url = "https://files.pythonhosted.org/packages/33/2a/3434e450a4395fc07f3070d6ac24553f0b170b173e949216b1723395028c/aiohttp-3.14.4-cp310-cp310-win_amd64.whl", hash = "sha256:e90980e0454a043f81b435309a089ac5deab883779557eb58d004f33990f61e4", size = 512204, upload-time = "2026-10-05T17:38:13.309Z" }, + { url = "https://files.pythonhosted.org/packages/53/c0/1d89303cf1bea5418268c1cb82b872661bad027e5fd785c2d30d0a31ee6f/aiohttp-3.14.4-cp310-cp310-win_arm64.whl", hash = "sha256:e63eecf9a4b670a24055d5c0486128af16f83b02d9817abd685d3238940f8752", size = 492725, upload-time = "2026-10-05T17:38:14.825Z" }, + { url = "https://files.pythonhosted.org/packages/81/e3/998dc75634ecd2a24f33bab480b57313059d55bcadff8825a46b7c80a8af/aiohttp-3.14.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:eb0093ca0817019d539f0d27bdf98e823944e05bb7efd9d2337a45b92e4d1b06", size = 832892, upload-time = "2026-10-05T17:38:16.373Z" }, + { url = "https://files.pythonhosted.org/packages/58/c9/9bacc26397854440d169f70ae00ea51721f504611d3a64cf043643792c32/aiohttp-3.14.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f482dc9c8309801b4259dd218609d3dae0a7bcdedeac56d90500eabaa0c23465", size = 559893, upload-time = "2026-10-05T17:38:18.74Z" }, + { url = "https://files.pythonhosted.org/packages/fa/f3/90c5856014328a8b1e9a753de794edea282182b776ff65f0602ad4ffa520/aiohttp-3.14.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:aa800bb7c1d00e166493931f2ddacb982db913292503dc2f4884db1f2bc5f105", size = 552850, upload-time = "2026-10-05T17:38:20.385Z" }, + { url = "https://files.pythonhosted.org/packages/9b/88/e71c29ce6daa78fcee0feb1992f0fdc408f09f42c3311b1f1c68c36f16ea/aiohttp-3.14.4-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d90e4dae71b26597f6d1fd12af7d092ae67551edf0e524b73e0687214b79ee33", size = 1928941, upload-time = "2026-10-05T17:38:22.218Z" }, + { url = "https://files.pythonhosted.org/packages/3a/4f/f0f3bebfa521a2ce5fd4302c937701cbc50cd6d908beaa597388639b0b98/aiohttp-3.14.4-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:5b681054b8c3b86aa6a0384b6ad7f5cb78dccbabab1f4a3a6793f98ad1378959", size = 1882092, upload-time = "2026-10-05T17:38:24.016Z" }, + { url = "https://files.pythonhosted.org/packages/b5/0d/5df041fd25dceb4f4cafbbee49bb2c1e2d54a91aedecaf03b77cbb404c44/aiohttp-3.14.4-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6dfe80b41bcf8d80d2125fb99a171adeb86db2fcb35c1a68e0226acba0ba7f03", size = 1986051, upload-time = "2026-10-05T17:38:26.022Z" }, + { url = "https://files.pythonhosted.org/packages/1a/07/e95eddafffef7c3a74446f67ac4e477a49cec2c78f2ab6c86d1acfd90d2d/aiohttp-3.14.4-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:71e4a59c6a8c5a6ae8b0b696c32635913e8f526cc01448762eaf5a3c59df8a4f", size = 2107840, upload-time = "2026-10-05T17:38:28.112Z" }, + { url = "https://files.pythonhosted.org/packages/da/6c/1f83990fea249dcb10f48086726953546efc9199c96b6be7114532ac361f/aiohttp-3.14.4-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f887c3b7fb3058fc1ccd917f52078540c18d938d12018cb9edd64b6811d20c57", size = 1930721, upload-time = "2026-10-05T17:38:30.046Z" }, + { url = "https://files.pythonhosted.org/packages/6f/d1/48184a186ea26df4f81dd466144dcab7f9cdd1e131bfee0f0e41278c6f0d/aiohttp-3.14.4-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0da4525e9ba145a11617d2cd7e44fe1acaf471f9c72a0cad28e72879c1020fbb", size = 1774508, upload-time = "2026-10-05T17:38:31.8Z" }, + { url = "https://files.pythonhosted.org/packages/0f/ef/a9ec758c6d3850453838c31b56d1e4499eb47c80883753a12dcb203f9afa/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:f7e8d3c5caa44fdbee3eba1aa1417aa58c74c95d4089fe3c451911117fcbb2f3", size = 1902311, upload-time = "2026-10-05T17:38:33.791Z" }, + { url = "https://files.pythonhosted.org/packages/d6/49/9a2be54900f2dea6e63bbf9628fced604686a2e301130ccde0b1aa2e7e53/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:09092cf906c18c824b6b16881da5a89cc9cfa9b15344e496bcf880e9045bee33", size = 1912107, upload-time = "2026-10-05T17:38:35.614Z" }, + { url = "https://files.pythonhosted.org/packages/a2/2b/151254abfc0fe5cbb8e6c41ad04d52122db0af176fb31dbf3bc44e081bda/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:dfd144837e92264878bba6d3a7ffa8206668b21e87748740afd45d193e48c87e", size = 1960207, upload-time = "2026-10-05T17:38:37.322Z" }, + { url = "https://files.pythonhosted.org/packages/23/99/92c8dce336ac5784755a3144623528516f2e3b6b4871d02cad5a0642ae66/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:9413cffe4e0d654b9b524f9c99dde8cbdb37e0ed9a2c4edd2e63adbac6b374e8", size = 1760168, upload-time = "2026-10-05T17:38:39.214Z" }, + { url = "https://files.pythonhosted.org/packages/66/3e/f05fd8d1a9595730db8d522882eea76429b9be2ed5337609f7c6e3d9d49c/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:f50d719f97ba488dfb8e306cf8c8cc172ff0683ec0af53917b288229aa555ba5", size = 1979946, upload-time = "2026-10-05T17:38:40.927Z" }, + { url = "https://files.pythonhosted.org/packages/b9/14/8941aa73ffceabc2a0eb26878b4f1b2958fb7b5358f97cc49b1c00ed9258/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:68ed4824d96b7afec1f3a8d7fba190fe282718041c5772e20298003e1e3e5d66", size = 1923375, upload-time = "2026-10-05T17:38:43.184Z" }, + { url = "https://files.pythonhosted.org/packages/18/b5/ef275b63c8bfe0a21e7e8d3ef0e67c4745ed403f1894fe5205057cedd3b9/aiohttp-3.14.4-cp311-cp311-win32.whl", hash = "sha256:d7a41d1427136828e6b11d3f3fd194d4357d5205a5b610be7ae07b1ba52ab974", size = 488414, upload-time = "2026-10-05T17:38:44.978Z" }, + { url = "https://files.pythonhosted.org/packages/e7/0b/21bdd70a1e072222d9dbd96bed4fbed26f7c46c5a20af11b78d32fd049d6/aiohttp-3.14.4-cp311-cp311-win_amd64.whl", hash = "sha256:2efbdb87e79d596325c4eefaef0f4495d701145e882351310ebc538e854dc7a3", size = 512755, upload-time = "2026-10-05T17:38:47.036Z" }, + { url = "https://files.pythonhosted.org/packages/b7/4c/bb324a7d20a9598187bb028ca8d6bcf66c63589c8632420919dd576964ed/aiohttp-3.14.4-cp311-cp311-win_arm64.whl", hash = "sha256:ac6e6f90d9360e460c873f945f11dc8698db0a71fec6612823f1aaaab2c11faa", size = 492960, upload-time = "2026-10-05T17:38:49.006Z" }, + { url = "https://files.pythonhosted.org/packages/22/02/db5935d45347fa8ede56b777930740fb0e72bbb4473ddb6ff8541f6f2afa/aiohttp-3.14.4-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:55b0b335982b0db7117dff7f6a8e3aad43c4105f9e392ca04f9fc8d958a95cce", size = 817689, upload-time = "2026-10-05T17:38:50.69Z" }, + { url = "https://files.pythonhosted.org/packages/e6/56/f00aa46127e6342f019d567853eeeb932e04fb9b9424b5fb981ad68f4178/aiohttp-3.14.4-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:2d0d8e435582b0d53009dac99e26a3d2be932ed7c9dbfcfc70f3fce1cf943bd5", size = 549599, upload-time = "2026-10-05T17:38:52.525Z" }, + { url = "https://files.pythonhosted.org/packages/3f/bc/825c09b09962253a2103e4a88c04374ee939c0c8ea31c270daa0308efb07/aiohttp-3.14.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:bf734016932d68e1324cfb638cac7a0866a83933a33badf15e836a7e24efb8c0", size = 548132, upload-time = "2026-10-05T17:38:54.629Z" }, + { url = "https://files.pythonhosted.org/packages/40/80/8a1bc8036540fe7cb38219cc5c0aa67d32e9068165725e8199ea8200b08b/aiohttp-3.14.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:322e3d741b3133bcbb981a41d4f9b8ac3545c18de49c662c2b1f4e1c770b98ad", size = 1898485, upload-time = "2026-10-05T17:38:56.439Z" }, + { url = "https://files.pythonhosted.org/packages/3c/fe/65b464d8520ace0d65b4ca69bc9abe175f842c8ce8d1522d363d9669903f/aiohttp-3.14.4-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:15a3bb5f90a4e515071f3617a45dfe26560beb834a6b6e108cdf4bc9e9719ec3", size = 1875334, upload-time = "2026-10-05T17:38:58.536Z" }, + { url = "https://files.pythonhosted.org/packages/be/51/9c583be502720e927560a8414f4dfb7c7de41945e1a30ccf7003b93c6f85/aiohttp-3.14.4-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6c044e52df1a466af82cad3518c92ea80cc4ddcfea86966ff083bb34bab29bf4", size = 1937772, upload-time = "2026-10-05T17:39:00.376Z" }, + { url = "https://files.pythonhosted.org/packages/a2/3d/b56512df7ea9cbb5f59099a6b375088dd578356a5a3fb27198ab82e19832/aiohttp-3.14.4-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d613d7d51bf06fe9a5e3aab86ce06d835bb0ceb1a31ea9e8766df4a403ae62a6", size = 2066220, upload-time = "2026-10-05T17:39:02.54Z" }, + { url = "https://files.pythonhosted.org/packages/11/6c/a7a42701d9ea319140a3d44a24ec72a00b0b46d1b899b26d8a705e65bdd8/aiohttp-3.14.4-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c5e93ab6e6330dce40f5b43996f1fc5f2543296d263a5e4b59ff09e73870b7d8", size = 1922895, upload-time = "2026-10-05T17:39:04.638Z" }, + { url = "https://files.pythonhosted.org/packages/77/04/f8337bd824ca3fe3968d34dc5037ace1c4872551c4621f8266239311d301/aiohttp-3.14.4-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:20134dc8e68c67e7478124d516449428684c0545b2d3faa575691c8bcbd56678", size = 1712589, upload-time = "2026-10-05T17:39:06.671Z" }, + { url = "https://files.pythonhosted.org/packages/fe/a6/d20e2c940b592d7c4a21690889dbff64fe0ca3facd9190696368694e1488/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:f0daef5ef012369dddc391c61f604111424aa9a96313a69fb899018b09d1b01e", size = 1862251, upload-time = "2026-10-05T17:39:08.523Z" }, + { url = "https://files.pythonhosted.org/packages/f5/e4/d50edd5ae5d024b380a8e892e333840bb22967a9eb9c8492108a403f678a/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:19290a108de0718b73bc69b86e788975c6a59855c671ebe2a98a07a6f968328f", size = 1895155, upload-time = "2026-10-05T17:39:10.305Z" }, + { url = "https://files.pythonhosted.org/packages/c3/d3/f36f2931f807ccf8437ec15e8f8bfaa4748d4792639401cc767a866abaa0/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:1494877625baeffab669f4a25a09ec4eea721b49e35363081a2a8e4231fe141f", size = 1906623, upload-time = "2026-10-05T17:39:12.411Z" }, + { url = "https://files.pythonhosted.org/packages/5d/0a/94821b711493142bf5e11c27b0d7502776778f7792c77ecc6647357d20c1/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:a779ce4bf099ce4ad2cdfed62f1ca536d435f53237c54ff40172fddada24d1b5", size = 1698932, upload-time = "2026-10-05T17:39:14.446Z" }, + { url = "https://files.pythonhosted.org/packages/d9/76/3d5a0d28362f0053c1c457024749911932481e8fd105fddf8305b1f93c81/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:0b4cec9fca876e2d4f4c6cb32b177390132d04618867689f43fefabf3f5c3980", size = 1934528, upload-time = "2026-10-05T17:39:16.354Z" }, + { url = "https://files.pythonhosted.org/packages/a7/51/9784a21dc05d2e0f6acaf864f16db53dab0fbd7b0753cef168601eacb012/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:217707313e23aedde9bea67cf8365c7b138b549ae179121ef3f476cf67e3173a", size = 1901984, upload-time = "2026-10-05T17:39:18.299Z" }, + { url = "https://files.pythonhosted.org/packages/44/4f/f98c88703e6d620243aa08473a946ca4e3756b6288690e38f0d9f9c1d007/aiohttp-3.14.4-cp312-cp312-win32.whl", hash = "sha256:18a9fb9a3f6e6e63f4d27f9adeef313a2d3c69a84d31170a844623824e722534", size = 480278, upload-time = "2026-10-05T17:39:20.206Z" }, + { url = "https://files.pythonhosted.org/packages/b7/bc/8555013f84b53e4fdde423131b641af50e822c6d7d9118b24c52b31f6900/aiohttp-3.14.4-cp312-cp312-win_amd64.whl", hash = "sha256:69dcb02d33dfe415d5ee342cc63b7d320efcaf4b761701c7bd7bfb91c715481a", size = 506317, upload-time = "2026-10-05T17:39:22.706Z" }, + { url = "https://files.pythonhosted.org/packages/21/3f/ca5bad7bfdaa7ddca053a044a1c7c0d4f3ad9d1f12f96dcab10bfb9c50e7/aiohttp-3.14.4-cp312-cp312-win_arm64.whl", hash = "sha256:d36b0263e7c2fbf1750b9f35d4e7e48b0442d8c45e4a89e3e74168821fb014bb", size = 487683, upload-time = "2026-10-05T17:39:24.482Z" }, + { url = "https://files.pythonhosted.org/packages/23/ec/7fee140da700ec3f5aa5e0fd2319f67be5e86de197e2384d27e5e6209e0e/aiohttp-3.14.4-cp313-cp313-android_24_arm64_v8a.whl", hash = "sha256:264b5a7568306590c44ae4a0237ad1715e35d447ea44ebf324e4c8fd9f78f67a", size = 539114, upload-time = "2026-10-05T17:39:26.322Z" }, + { url = "https://files.pythonhosted.org/packages/4e/04/930c01ce9e186e787046433d7dc5b45b188885f8406c14b58435b4431974/aiohttp-3.14.4-cp313-cp313-android_24_x86_64.whl", hash = "sha256:17e5d7c7775d8dd8e894c7ef6ebfa26509de36868a9a6c7c4fcfaf6a1bf43d60", size = 553514, upload-time = "2026-10-05T17:39:28.104Z" }, + { url = "https://files.pythonhosted.org/packages/2c/d7/983e3cea81c07e95f35d34da4d1e182b5c05489c49b7560b198a83f0da79/aiohttp-3.14.4-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:e91dc8fe9cbd052d16f7f1267e285cf8bbac4d2194bd5741f05ef201c77ed09e", size = 521381, upload-time = "2026-10-05T17:39:30.419Z" }, + { url = "https://files.pythonhosted.org/packages/0e/2d/80baed11659093883f51245755105557d3253e45bd0b693d70df0059d68b/aiohttp-3.14.4-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:8df6157d31703972aec9e3b93963f039ff06318301e30b007c3e941ff8a7ac42", size = 528347, upload-time = "2026-10-05T17:39:32.344Z" }, + { url = "https://files.pythonhosted.org/packages/c8/18/bfda255c311096c08dab26dc65f3d219f090df37dc5f5f6345f8c3aefc1f/aiohttp-3.14.4-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:220912b351549dc736c59d104dc443fa615753102bb778a4e98f86e4d94bff6a", size = 539914, upload-time = "2026-10-05T17:39:34.265Z" }, + { url = "https://files.pythonhosted.org/packages/51/fc/3b6ca6117c0c42481d719411fff7b5d3970ebd906543d3dc1ba40fe2462f/aiohttp-3.14.4-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:2efa42b39bb3f524d5eca3760639b584afdd1143a6b047fda29910ffb75e4993", size = 813997, upload-time = "2026-10-05T17:39:36.061Z" }, + { url = "https://files.pythonhosted.org/packages/b5/f6/86e3e02a9712aadc1ae0a1076bb2d1adf3d9addfe5542a28190c8f9b6d9b/aiohttp-3.14.4-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:7e7356059c8262d2c1fd95242e2b7b70fbc6eee3135bf470049cbec3e968b5b0", size = 548058, upload-time = "2026-10-05T17:39:38.109Z" }, + { url = "https://files.pythonhosted.org/packages/85/7e/6b9c2e271419d40ca76589613b3c7ab185fd3050a407bd2565b6aa46f695/aiohttp-3.14.4-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:fac247d0cc956d732df1211ac2d8a9999ec8dc1a92a90401de9d52e4ead546f7", size = 545933, upload-time = "2026-10-05T17:39:40.193Z" }, + { url = "https://files.pythonhosted.org/packages/14/fc/33d6e24a5f8ac32423230088c415e2a1c6efee23d902b62f20506631e40b/aiohttp-3.14.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6e2eb0f8b03b4f2bd154ed8cf7c1a119a1ad04808c258bf58f90138c83b8c6d5", size = 1888265, upload-time = "2026-10-05T17:39:42.182Z" }, + { url = "https://files.pythonhosted.org/packages/8d/e8/2eca1d468d83a514621d1280f9992d08649191db2028c9236b4edfa7c723/aiohttp-3.14.4-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7fbe827d27e0e369fd7bb88ceeaa5b46ea006e73e015b9dd77e3723a53162293", size = 1872300, upload-time = "2026-10-05T17:39:44.195Z" }, + { url = "https://files.pythonhosted.org/packages/d6/f6/5872983de71b0214acdfb86822f5cca295b39be4832ec589fa224aee0f6c/aiohttp-3.14.4-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a70387146d03af9f047c629b71aa27d9594b3b31ec4c9c91e1a73d0d8bf38e0e", size = 1926213, upload-time = "2026-10-05T17:39:46.199Z" }, + { url = "https://files.pythonhosted.org/packages/ee/65/ebfefa11a546c33c717af63c67868408ecf0b33b23a9d75669af95485407/aiohttp-3.14.4-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0d0934926fc65744e2fdd44ce68b2d79d5ee608a1e23f0596b35dd696519bb7c", size = 2056609, upload-time = "2026-10-05T17:39:48.221Z" }, + { url = "https://files.pythonhosted.org/packages/69/c0/70667e82ec041f4122a17afce711bbcf94a71bec5888b69a49aed8817be2/aiohttp-3.14.4-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ff4b366510c733974adb7a4102c094e4a6308e6f369315a4cf14d2d0a619cf82", size = 1914740, upload-time = "2026-10-05T17:39:50.304Z" }, + { url = "https://files.pythonhosted.org/packages/bf/86/559e9dfea676206b20737d7ccb5b3716bff5e58d2a8d53682e5301724cd1/aiohttp-3.14.4-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:85fac7c99e0ac3dcbd6ae1c33774e0603bfc732ddb967a6fce4a731103c1888e", size = 1703390, upload-time = "2026-10-05T17:39:52.385Z" }, + { url = "https://files.pythonhosted.org/packages/fc/91/c98897d4cf23e120b2f3980042835cb34c86bbe3c653f3eaacf4bf986349/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ef1e9c3b4a2300023a5dc865889ce532cfaf6798ba4ef78fbbefe738a9d23efa", size = 1852642, upload-time = "2026-10-05T17:39:54.391Z" }, + { url = "https://files.pythonhosted.org/packages/14/13/0258f352cb2c236f358a5b57d138e15fa2566e17accc0758d968dbf2ceb6/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:97e65916588be0f952b3307aaa8460c0771fa98dbea2dd27dabc9f5d84d53c3b", size = 1890616, upload-time = "2026-10-05T17:39:56.466Z" }, + { url = "https://files.pythonhosted.org/packages/64/3c/f43e294ce1a06d1234a97bd862c1aa31acfa1a0eea3786c22fd0dc1ea731/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:840775cb39a9424f9edf142133a1192263ac5bd79117ad2a16602cef6a0c1e9d", size = 1896638, upload-time = "2026-10-05T17:39:58.585Z" }, + { url = "https://files.pythonhosted.org/packages/9f/f7/ce1e3a85b73d05037d729d3d32da7d6959b9e433435e9abd46c2fb38410f/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:54f9256430ca040d58affbd551513de13a5cff7d065204fc52b9a1b0af09a049", size = 1693003, upload-time = "2026-10-05T17:40:00.698Z" }, + { url = "https://files.pythonhosted.org/packages/1d/72/45eb900d6a9ee046728f5589f3d07f5d78f049b5fb84f48881fa4174d5df/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:6112d5931bf12c776188cab81b82bbb17d86e2e1381f2ade6edc43e6b240f0cb", size = 1927730, upload-time = "2026-10-05T17:40:02.943Z" }, + { url = "https://files.pythonhosted.org/packages/b2/43/a83ff79dc8375953a1f00b808a21c82590f4e68304fecccdcc42a25fb7d8/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:facc6df39047c4732cbd885bb62e40df20885fcd709fc399e11f81b45ce0fff9", size = 1891177, upload-time = "2026-10-05T17:40:04.989Z" }, + { url = "https://files.pythonhosted.org/packages/5c/ba/fbdc41608d4e2fb6084d960a41b392fa82beb5b126c2466de549b5c67fc8/aiohttp-3.14.4-cp313-cp313-win32.whl", hash = "sha256:7968634fa3a967a2bc0b9aeba1d5a1955501dcd7d0de44b96f7ebfb662797735", size = 479943, upload-time = "2026-10-05T17:40:07.402Z" }, + { url = "https://files.pythonhosted.org/packages/35/51/d75629750e705832fd5cd52516a82943ed58b6e09c30e14830f5d87452fa/aiohttp-3.14.4-cp313-cp313-win_amd64.whl", hash = "sha256:c0a894b0265d139cd4c2c8bd4643822cc289a4a5331e21e810881bd000ffb2dc", size = 506209, upload-time = "2026-10-05T17:40:09.49Z" }, + { url = "https://files.pythonhosted.org/packages/02/64/66452d2ffcc13e5e5ee4ba4a968656fa4a98c29ed5ff0205d4fde02b2943/aiohttp-3.14.4-cp313-cp313-win_arm64.whl", hash = "sha256:da16c3037178e72589d91de59536d271dffc92c2be2b47c38a45538cba54fd29", size = 487163, upload-time = "2026-10-05T17:40:11.526Z" }, + { url = "https://files.pythonhosted.org/packages/d2/fd/b653b1f969e2e949fe4726af7a8043e8ef117f202bed7757ac8564e077a1/aiohttp-3.14.4-cp314-cp314-android_24_arm64_v8a.whl", hash = "sha256:749bfc43bb1df71bbe6ed215044d5412d786698fc5771d2037436ca49622f3c9", size = 540738, upload-time = "2026-10-05T17:40:14.109Z" }, + { url = "https://files.pythonhosted.org/packages/90/b5/eea49a0bb697deffac5165d707ec53a24748d6720b3af77a544107b49573/aiohttp-3.14.4-cp314-cp314-android_24_x86_64.whl", hash = "sha256:c113e4b489d711f606ca278cd8dc89179746244ea841aa0638b1b134600afad0", size = 554494, upload-time = "2026-10-05T17:40:16.231Z" }, + { url = "https://files.pythonhosted.org/packages/11/ea/cf8f4efbbfa8572d9965cd43b3c6c84c581aa006772e5ce3ab4020027e9b/aiohttp-3.14.4-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:50969522bc7022026a2c7968e67da5c789f6b716b988edac55dc630390efd5df", size = 522653, upload-time = "2026-10-05T17:40:18.879Z" }, + { url = "https://files.pythonhosted.org/packages/a3/24/9f6721f0b52323789cb1041ffc3afa729462d9925607e733a065b6fc5e17/aiohttp-3.14.4-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:cbf92cd7a1c800cee244558dd5630abb45c1c1093ef7b0d546a99f526ff7a9eb", size = 529697, upload-time = "2026-10-05T17:40:21.296Z" }, + { url = "https://files.pythonhosted.org/packages/9c/a4/399debc3c2ca0ab88a08e3082b4c4f62d0f66978af60243c63f2345ef337/aiohttp-3.14.4-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:fc76be08ff407fba717a769aff04ca1b4bf9ecfdcb5caadef84a563fdbbd146d", size = 540526, upload-time = "2026-10-05T17:40:23.548Z" }, + { url = "https://files.pythonhosted.org/packages/a2/97/90379813b18b795bccdeb3a5a85e9b93ac2c69f9c2a5d0faba59da3ad6d1/aiohttp-3.14.4-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:9b416f995b68a921069e6ec61fa07f2ac3ff033d92e97a69f673af89f5bb954d", size = 818866, upload-time = "2026-10-05T17:40:25.842Z" }, + { url = "https://files.pythonhosted.org/packages/78/70/824fd0dac819652f1df895b3f621a75bf0a3050c30e38d8d2316e34ab821/aiohttp-3.14.4-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:2c9585101cfca10e74a07cc0ef2bdc6d90616e6750926b20456f429d0608f740", size = 549666, upload-time = "2026-10-05T17:40:28.523Z" }, + { url = "https://files.pythonhosted.org/packages/8c/45/eafb2dd200dd2b770ed25a2dc5731c4ba5d58ab3fa8e2e82494bb946808e/aiohttp-3.14.4-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:3c4dcf611b095e7983421f49d01ffbed7ed574891533d606ea115fc23e7c4e90", size = 548961, upload-time = "2026-10-05T17:40:30.613Z" }, + { url = "https://files.pythonhosted.org/packages/a7/bc/6c733a1c71300293471ac7ef1dffd12b5b4dc9a43c53461224b2b8a7f667/aiohttp-3.14.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f8f61a9b5fa56c58e3441f9dc64137f786232d40fb89127190d0e0f84e1e5865", size = 1883165, upload-time = "2026-10-05T17:40:33.062Z" }, + { url = "https://files.pythonhosted.org/packages/37/34/885ddbd351679a31141b25e0d1a5e4f67738806e564c858b399709b61239/aiohttp-3.14.4-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:d43e538dfc85b705fd832620d050970ef5613b3869a7169b44a554b9dab9eee9", size = 1844119, upload-time = "2026-10-05T17:40:35.266Z" }, + { url = "https://files.pythonhosted.org/packages/cc/ef/0a64dac53c11d569851efb3e7eddb43551df72b2c172ebb34cccc93bcd3f/aiohttp-3.14.4-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:4135c4bb4b7682a7633fadc7170ea969d843f83aa7224e70111a20675105c985", size = 1930222, upload-time = "2026-10-05T17:40:37.527Z" }, + { url = "https://files.pythonhosted.org/packages/69/5f/774792ed8f973e0d234fcb06b0f0bc9f29e9a0a0dd847f6418c2904be7d9/aiohttp-3.14.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:9055324f156a94fdf6dc9a825ae60f9a2947b88f591ea81ee80826633de62ae7", size = 2038842, upload-time = "2026-10-05T17:40:39.815Z" }, + { url = "https://files.pythonhosted.org/packages/cb/05/e00f35581c97656d9e864edaa03292382c620dd1d9c836a4f73a2279acc4/aiohttp-3.14.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fb22c8e4b60385a9b414c70c6e8b2d0f4b23ff7fc4bb572ceb58297b228169f1", size = 1887845, upload-time = "2026-10-05T17:40:42.359Z" }, + { url = "https://files.pythonhosted.org/packages/ca/2e/07e3eff5b4c1b082a2eaf0ffb508b409b21ea1ddc9fdc57f3eabb51469a1/aiohttp-3.14.4-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:3b6945559a260112742ed58cde2165488d2fc51aeea34afbaa99d9371b43e1b5", size = 1702533, upload-time = "2026-10-05T17:40:44.569Z" }, + { url = "https://files.pythonhosted.org/packages/75/44/816844b7f876e6f8fee4ecb088269fcd92241da712e4814a4d624eda13a9/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:8f4078a90b174f15efb2c8725e8720c40dbd3b2cf6350dbc085c964a938d9de7", size = 1849058, upload-time = "2026-10-05T17:40:47.818Z" }, + { url = "https://files.pythonhosted.org/packages/ae/bd/163242e12464a1f3e58a77e28beca949652ddce84abdd5500a91c70a1e0d/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:f433c5654e32f72de3ef074d715eb5c7604eb6d28a5c2f3c9e5056f20fe6b306", size = 1854600, upload-time = "2026-10-05T17:40:50.401Z" }, + { url = "https://files.pythonhosted.org/packages/f2/59/5c1ae708a89524eddfd9c727b87cae26b5c50c3c76683b910ac06151ead0/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:871035fe79c636b6bc126ed78df37d72b830dfc751612cb4b1040360edf2719f", size = 1896565, upload-time = "2026-10-05T17:40:52.625Z" }, + { url = "https://files.pythonhosted.org/packages/37/45/95300a7de69241fe47d3f838f3fb582c712782e172d447ff650a013ea673/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:2617132524f66338f6c1d218cd16081576aefc40df4f2bcba338a99fbf67fec1", size = 1693092, upload-time = "2026-10-05T17:40:54.862Z" }, + { url = "https://files.pythonhosted.org/packages/ff/33/01a8e61d48d0094121092c74125df14c0f8f10ee3149bfe68b6f869409a9/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:d8bc326133272deee8ef337581550450e4bb735c0520be893b950a1f5baaf41a", size = 1917073, upload-time = "2026-10-05T17:40:57.656Z" }, + { url = "https://files.pythonhosted.org/packages/9e/d6/1a4f24624cda6686d5b927e26d5d1ae3ebb692faf88e93017fab4b391fd0/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:3ec57223e261b7fa9979c12dbce009ca53439be76cac3af27f860d3e4b1d6f7a", size = 1872656, upload-time = "2026-10-05T17:41:00.123Z" }, + { url = "https://files.pythonhosted.org/packages/be/be/ed286fcfa2d22061ae021b568c790123505cd482df35e23023339ecaed96/aiohttp-3.14.4-cp314-cp314-win32.whl", hash = "sha256:7242043e71fc449a19a47d92f4e9fd1e0ae8d3f88488982381f422bf6d651218", size = 485461, upload-time = "2026-10-05T17:41:02.686Z" }, + { url = "https://files.pythonhosted.org/packages/c0/74/e040e6f65f4da305777f1adb3023d47401693489e4a337c983b52d2a0a6b/aiohttp-3.14.4-cp314-cp314-win_amd64.whl", hash = "sha256:019587c7b3a44917dd61bcb312fd5c034f341dc9851b83e7b41b65e08b68ca0f", size = 512147, upload-time = "2026-10-05T17:41:04.98Z" }, + { url = "https://files.pythonhosted.org/packages/2e/5e/bddb33ae15fdd5a68a10a986587aa9916c418a712fdd110d3b3ae9b51407/aiohttp-3.14.4-cp314-cp314-win_arm64.whl", hash = "sha256:60dc71d38db0988f37e78f6ad4a010a2f6355cfac3fff5f130cf5ef2231f3f0d", size = 494685, upload-time = "2026-10-05T17:41:07.366Z" }, + { url = "https://files.pythonhosted.org/packages/22/2e/7b884014b40573f919fc3a528e5028bc37b249e31a93928ba61bdd25c960/aiohttp-3.14.4-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:674f53ab9d2794e2dd767619a3384bf1006f8d075e43c19d449a645f8ff641c2", size = 855696, upload-time = "2026-10-05T17:41:09.514Z" }, + { url = "https://files.pythonhosted.org/packages/5f/e6/b6e2b4f580ab6ae39241bb9182aca60e6e1915cdad0148faaa04db3f366b/aiohttp-3.14.4-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:6d243221f73e5ac546c2ed9255100423e4bc092b08b944f23498e8cf3096c26c", size = 567931, upload-time = "2026-10-05T17:41:11.685Z" }, + { url = "https://files.pythonhosted.org/packages/63/99/ae8e3a1a18adcbf636839d18b3cccc51007836ccdae5209381c5cf82d1ae/aiohttp-3.14.4-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:0daa016eb74e7888ed5f9ceec6eea3158999c1c4a115ef5cbe88baa8d924f94c", size = 567421, upload-time = "2026-10-05T17:41:13.836Z" }, + { url = "https://files.pythonhosted.org/packages/63/38/c5d4bb58be72b967a4090d2deeb38571f8c992852936c51dbbbeae49db1c/aiohttp-3.14.4-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:70c031a622aa20add05ebd234b90adaf6bf51c1c88cc305ec760721af83308c3", size = 2054173, upload-time = "2026-10-05T17:41:16.098Z" }, + { url = "https://files.pythonhosted.org/packages/eb/87/3c8a9c7670f56d478a75c5bb84b336fb61a67b908e36c30a4a96ed8c8e86/aiohttp-3.14.4-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7df363fa7c38945a896e12c69af4a1a56cbd4152791d9e41fd0bac396b72de38", size = 1918296, upload-time = "2026-10-05T17:41:18.478Z" }, + { url = "https://files.pythonhosted.org/packages/49/97/bd00e499c0a1505b44f5e23b9739034ea9be792ad42537f2894211ba1c07/aiohttp-3.14.4-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:02a508ba5ad91c4d730523584c0adc65882274bba5e37c33bc2f475e37577256", size = 2027513, upload-time = "2026-10-05T17:41:20.874Z" }, + { url = "https://files.pythonhosted.org/packages/23/1d/a3666a7c224f86a881f18d673a8ffdc92fa4c35274fb4361822f8f0dc566/aiohttp-3.14.4-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0cb3edece6fe6a944eaf97d803b88f606da6bc1600b1894c2969e78ffdc1fc29", size = 2152686, upload-time = "2026-10-05T17:41:23.181Z" }, + { url = "https://files.pythonhosted.org/packages/46/7e/f4204b8c4959c46f6367c182afbbacef08a1b53874281912c52fbd80151c/aiohttp-3.14.4-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:21ce1223b461bcc5fb389a7204001578f1c0b85c2da60a84d915ebb021294245", size = 2006431, upload-time = "2026-10-05T17:41:25.776Z" }, + { url = "https://files.pythonhosted.org/packages/33/43/091e69d42967cbea833ceb355c5457f8f70748fe08b88c9d91491b3fafb8/aiohttp-3.14.4-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:35d5432f0dc1c8b71307e9112461b52f336da225e344283eec4779222c0a1dff", size = 1789101, upload-time = "2026-10-05T17:41:28.095Z" }, + { url = "https://files.pythonhosted.org/packages/47/7b/b57cbe533c01098c5d30471f057e7c3c19f281122f756acc9c716b636e2c/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:d6ec364493057c118d08292f7cd60865965c209167d8657b45643a26aef77495", size = 1974472, upload-time = "2026-10-05T17:41:30.499Z" }, + { url = "https://files.pythonhosted.org/packages/9f/44/79acce03611450e4ed8594f96f1cea40d70bc84fb4e918f94d7d9454a4af/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:70492983b7aed9e61bda82fe1ce80bcba9199610886443133783a288638923c0", size = 1956340, upload-time = "2026-10-05T17:41:33.009Z" }, + { url = "https://files.pythonhosted.org/packages/da/bb/36e6cbd6720e3377a02f8709aec6fe80de729ef41e78ba01f13d50363c73/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:a77776673331577147e9d25cd7833a72e8891b47556336cff06ba1569e488b99", size = 1965771, upload-time = "2026-10-05T17:41:35.506Z" }, + { url = "https://files.pythonhosted.org/packages/69/0f/879735ac70ce5e6852916eed51c706a517b205150a8d384f9fa60933a3fc/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:73799000dd6fd5247094fd8e6d3e1eb871e41aab5cc35dff9d9f654cd230bc24", size = 1780297, upload-time = "2026-10-05T17:41:38.284Z" }, + { url = "https://files.pythonhosted.org/packages/01/5d/7c030ca5b6baf3b02eccd11afc3d58f0b35e407031d5cc78cae9c24921c0/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:27b370fb532e707e8c96d04fa0c96301fb7dba2d50aaca57f6c456cdfffec5bd", size = 2001374, upload-time = "2026-10-05T17:41:40.888Z" }, + { url = "https://files.pythonhosted.org/packages/80/1e/ddacbb8141d727034c51dd192d17749521d5b30b03f84aa034325396089e/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:884e0d1c707b6217fee3080b9b4029eee7551af788ee761010df19be158414b7", size = 1968531, upload-time = "2026-10-05T17:41:43.62Z" }, + { url = "https://files.pythonhosted.org/packages/3a/08/2214f823701eebc3e57db141faeae76df7bfd415f254cc7c1692258f228d/aiohttp-3.14.4-cp314-cp314t-win32.whl", hash = "sha256:f2e3d34edb151d3e27f93a8338e2da33e2c7261cd4c879ce5f5fe280cc190ea5", size = 504126, upload-time = "2026-10-05T17:41:46.321Z" }, + { url = "https://files.pythonhosted.org/packages/91/a1/90e9b6fd23310b4e82d0c0a37b5ecc2944053350473c57533c1da9647235/aiohttp-3.14.4-cp314-cp314t-win_amd64.whl", hash = "sha256:88cf889e51092537fe44adfbff96c2a22d6479d6f92b97b3d413fbfd0a4decf4", size = 531494, upload-time = "2026-10-05T17:41:48.849Z" }, + { url = "https://files.pythonhosted.org/packages/97/ab/5b501472c92b9b1dc53742591d6210dccb262962f4721299300d3a9f664b/aiohttp-3.14.4-cp314-cp314t-win_arm64.whl", hash = "sha256:ca450c6d42fda7c0bfaf0e200f32f77c5f2c960a33be1e14d197c84588b7f5f6", size = 510544, upload-time = "2026-10-05T17:41:51.358Z" }, + { url = "https://files.pythonhosted.org/packages/2b/27/5e1f8446545be98e9416af59c396b1ed1f9f3294afb0a40ee3a709889273/aiohttp-3.14.4-py3-none-any.whl", hash = "sha256:5c6758ba62aea282c537179cfc8474a90f2b5f7b089cc5ff66d8920d86a9bfdd", size = 279487, upload-time = "2026-10-05T17:43:44.905Z" }, ] [[package]] @@ -10779,142 +10780,118 @@ wheels = [ [[package]] name = "yarl" -version = "1.23.0" +version = "1.25.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "idna" }, { name = "multidict" }, { name = "propcache" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/23/6e/beb1beec874a72f23815c1434518bfc4ed2175065173fb138c3705f658d4/yarl-1.23.0.tar.gz", hash = "sha256:53b1ea6ca88ebd4420379c330aea57e258408dd0df9af0992e5de2078dc9f5d5", size = 194676, upload-time = "2026-03-01T22:07:53.373Z" } +sdist = { url = "https://files.pythonhosted.org/packages/75/16/e8be8e2fb175bbf41a0680381a319f1199fae256588241a2ac8677eafb49/yarl-1.25.1.tar.gz", hash = "sha256:03dd38de09bc213e9a8b29761eec33ee1d5318dac0e49d8af36e4d27830e23a7", size = 246245, upload-time = "2026-09-15T19:35:02.264Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/8b/0d/9cc638702f6fc3c7a3685bcc8cf2a9ed7d6206e932a49f5242658047ef51/yarl-1.23.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:cff6d44cb13d39db2663a22b22305d10855efa0fa8015ddeacc40bc59b9d8107", size = 123764, upload-time = "2026-03-01T22:04:09.7Z" }, - { url = "https://files.pythonhosted.org/packages/7a/35/5a553687c5793df5429cd1db45909d4f3af7eee90014888c208d086a44f0/yarl-1.23.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e4c53f8347cd4200f0d70a48ad059cabaf24f5adc6ba08622a23423bc7efa10d", size = 86282, upload-time = "2026-03-01T22:04:11.892Z" }, - { url = "https://files.pythonhosted.org/packages/68/2e/c5a2234238f8ce37a8312b52801ee74117f576b1539eec8404a480434acc/yarl-1.23.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2a6940a074fb3c48356ed0158a3ca5699c955ee4185b4d7d619be3c327143e05", size = 86053, upload-time = "2026-03-01T22:04:13.292Z" }, - { url = "https://files.pythonhosted.org/packages/74/3f/bbd8ff36fb038622797ffbaf7db314918bb4d76f1cc8a4f9ca7a55fe5195/yarl-1.23.0-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ed5f69ce7be7902e5c70ea19eb72d20abf7d725ab5d49777d696e32d4fc1811d", size = 99395, upload-time = "2026-03-01T22:04:15.133Z" }, - { url = "https://files.pythonhosted.org/packages/77/04/9516bc4e269d2a3ec9c6779fcdeac51ce5b3a9b0156f06ac7152e5bba864/yarl-1.23.0-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:389871e65468400d6283c0308e791a640b5ab5c83bcee02a2f51295f95e09748", size = 92143, upload-time = "2026-03-01T22:04:16.829Z" }, - { url = "https://files.pythonhosted.org/packages/c7/63/88802d1f6b1cb1fc67d67a58cd0cf8a1790de4ce7946e434240f1d60ab4a/yarl-1.23.0-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:dda608c88cf709b1d406bdfcd84d8d63cff7c9e577a403c6108ce8ce9dcc8764", size = 107643, upload-time = "2026-03-01T22:04:18.519Z" }, - { url = "https://files.pythonhosted.org/packages/8e/db/4f9b838f4d8bdd6f0f385aed8bbf21c71ed11a0b9983305c302cbd557815/yarl-1.23.0-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:8c4fe09e0780c6c3bf2b7d4af02ee2394439d11a523bbcf095cf4747c2932007", size = 108700, upload-time = "2026-03-01T22:04:20.373Z" }, - { url = "https://files.pythonhosted.org/packages/50/12/95a1d33f04a79c402664070d43b8b9f72dc18914e135b345b611b0b1f8cc/yarl-1.23.0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:31c9921eb8bd12633b41ad27686bbb0b1a2a9b8452bfdf221e34f311e9942ed4", size = 102769, upload-time = "2026-03-01T22:04:23.055Z" }, - { url = "https://files.pythonhosted.org/packages/86/65/91a0285f51321369fd1a8308aa19207520c5f0587772cfc2e03fc2467e90/yarl-1.23.0-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:5f10fd85e4b75967468af655228fbfd212bdf66db1c0d135065ce288982eda26", size = 101114, upload-time = "2026-03-01T22:04:25.031Z" }, - { url = "https://files.pythonhosted.org/packages/58/80/c7c8244fc3e5bc483dc71a09560f43b619fab29301a0f0a8f936e42865c7/yarl-1.23.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:dbf507e9ef5688bada447a24d68b4b58dd389ba93b7afc065a2ba892bea54769", size = 98883, upload-time = "2026-03-01T22:04:27.281Z" }, - { url = "https://files.pythonhosted.org/packages/86/e7/71ca9cc9ca79c0b7d491216177d1aed559d632947b8ffb0ee60f7d8b23e3/yarl-1.23.0-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:85e9beda1f591bc73e77ea1c51965c68e98dafd0fec72cdd745f77d727466716", size = 94172, upload-time = "2026-03-01T22:04:28.554Z" }, - { url = "https://files.pythonhosted.org/packages/6a/3f/6c6c8a0fe29c26fb2db2e8d32195bb84ec1bfb8f1d32e7f73b787fcf349b/yarl-1.23.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:0e1fdaa14ef51366d7757b45bde294e95f6c8c049194e793eedb8387c86d5993", size = 107010, upload-time = "2026-03-01T22:04:30.385Z" }, - { url = "https://files.pythonhosted.org/packages/56/38/12730c05e5ad40a76374d440ed8b0899729a96c250516d91c620a6e38fc2/yarl-1.23.0-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:75e3026ab649bf48f9a10c0134512638725b521340293f202a69b567518d94e0", size = 100285, upload-time = "2026-03-01T22:04:31.752Z" }, - { url = "https://files.pythonhosted.org/packages/34/92/6a7be9239f2347234e027284e7a5f74b1140cc86575e7b469d13fba1ebfe/yarl-1.23.0-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:80e6d33a3d42a7549b409f199857b4fb54e2103fc44fb87605b6663b7a7ff750", size = 108230, upload-time = "2026-03-01T22:04:33.844Z" }, - { url = "https://files.pythonhosted.org/packages/5e/81/4aebccfa9376bd98b9d8bfad20621a57d3e8cfc5b8631c1fa5f62cdd03f4/yarl-1.23.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:5ec2f42d41ccbd5df0270d7df31618a8ee267bfa50997f5d720ddba86c4a83a6", size = 103008, upload-time = "2026-03-01T22:04:35.856Z" }, - { url = "https://files.pythonhosted.org/packages/38/0f/0b4e3edcec794a86b853b0c6396c0a888d72dfce19b2d88c02ac289fb6c1/yarl-1.23.0-cp310-cp310-win32.whl", hash = "sha256:debe9c4f41c32990771be5c22b56f810659f9ddf3d63f67abfdcaa2c6c9c5c1d", size = 83073, upload-time = "2026-03-01T22:04:38.268Z" }, - { url = "https://files.pythonhosted.org/packages/a0/71/ad95c33da18897e4c636528bbc24a1dd23fe16797de8bc4ec667b8db0ba4/yarl-1.23.0-cp310-cp310-win_amd64.whl", hash = "sha256:ab5f043cb8a2d71c981c09c510da013bc79fd661f5c60139f00dd3c3cc4f2ffb", size = 87328, upload-time = "2026-03-01T22:04:39.558Z" }, - { url = "https://files.pythonhosted.org/packages/e2/14/dfa369523c79bccf9c9c746b0a63eb31f65db9418ac01275f7950962e504/yarl-1.23.0-cp310-cp310-win_arm64.whl", hash = "sha256:263cd4f47159c09b8b685890af949195b51d1aa82ba451c5847ca9bc6413c220", size = 82463, upload-time = "2026-03-01T22:04:41.454Z" }, - { url = "https://files.pythonhosted.org/packages/a2/aa/60da938b8f0997ba3a911263c40d82b6f645a67902a490b46f3355e10fae/yarl-1.23.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:b35d13d549077713e4414f927cdc388d62e543987c572baee613bf82f11a4b99", size = 123641, upload-time = "2026-03-01T22:04:42.841Z" }, - { url = "https://files.pythonhosted.org/packages/24/84/e237607faf4e099dbb8a4f511cfd5efcb5f75918baad200ff7380635631b/yarl-1.23.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cbb0fef01f0c6b38cb0f39b1f78fc90b807e0e3c86a7ff3ce74ad77ce5c7880c", size = 86248, upload-time = "2026-03-01T22:04:44.757Z" }, - { url = "https://files.pythonhosted.org/packages/b2/0d/71ceabc14c146ba8ee3804ca7b3d42b1664c8440439de5214d366fec7d3a/yarl-1.23.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:dc52310451fc7c629e13c4e061cbe2dd01684d91f2f8ee2821b083c58bd72432", size = 85988, upload-time = "2026-03-01T22:04:46.365Z" }, - { url = "https://files.pythonhosted.org/packages/8c/6c/4a90d59c572e46b270ca132aca66954f1175abd691f74c1ef4c6711828e2/yarl-1.23.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b2c6b50c7b0464165472b56b42d4c76a7b864597007d9c085e8b63e185cf4a7a", size = 100566, upload-time = "2026-03-01T22:04:47.639Z" }, - { url = "https://files.pythonhosted.org/packages/49/fb/c438fb5108047e629f6282a371e6e91cf3f97ee087c4fb748a1f32ceef55/yarl-1.23.0-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:aafe5dcfda86c8af00386d7781d4c2181b5011b7be3f2add5e99899ea925df05", size = 92079, upload-time = "2026-03-01T22:04:48.925Z" }, - { url = "https://files.pythonhosted.org/packages/d9/13/d269aa1aed3e4f50a5a103f96327210cc5fa5dd2d50882778f13c7a14606/yarl-1.23.0-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:9ee33b875f0b390564c1fb7bc528abf18c8ee6073b201c6ae8524aca778e2d83", size = 108741, upload-time = "2026-03-01T22:04:50.838Z" }, - { url = "https://files.pythonhosted.org/packages/85/fb/115b16f22c37ea4437d323e472945bea97301c8ec6089868fa560abab590/yarl-1.23.0-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:4c41e021bc6d7affb3364dc1e1e5fa9582b470f283748784bd6ea0558f87f42c", size = 108099, upload-time = "2026-03-01T22:04:52.499Z" }, - { url = "https://files.pythonhosted.org/packages/9a/64/c53487d9f4968045b8afa51aed7ca44f58b2589e772f32745f3744476c82/yarl-1.23.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:99c8a9ed30f4164bc4c14b37a90208836cbf50d4ce2a57c71d0f52c7fb4f7598", size = 102678, upload-time = "2026-03-01T22:04:55.176Z" }, - { url = "https://files.pythonhosted.org/packages/85/59/cd98e556fbb2bf8fab29c1a722f67ad45c5f3447cac798ab85620d1e70af/yarl-1.23.0-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f2af5c81a1f124609d5f33507082fc3f739959d4719b56877ab1ee7e7b3d602b", size = 100803, upload-time = "2026-03-01T22:04:56.588Z" }, - { url = "https://files.pythonhosted.org/packages/9e/c0/b39770b56d4a9f0bb5f77e2f1763cd2d75cc2f6c0131e3b4c360348fcd65/yarl-1.23.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:6b41389c19b07c760c7e427a3462e8ab83c4bb087d127f0e854c706ce1b9215c", size = 100163, upload-time = "2026-03-01T22:04:58.492Z" }, - { url = "https://files.pythonhosted.org/packages/e7/64/6980f99ab00e1f0ff67cb84766c93d595b067eed07439cfccfc8fb28c1a6/yarl-1.23.0-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:1dc702e42d0684f42d6519c8d581e49c96cefaaab16691f03566d30658ee8788", size = 93859, upload-time = "2026-03-01T22:05:00.268Z" }, - { url = "https://files.pythonhosted.org/packages/38/69/912e6c5e146793e5d4b5fe39ff5b00f4d22463dfd5a162bec565ac757673/yarl-1.23.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:0e40111274f340d32ebcc0a5668d54d2b552a6cca84c9475859d364b380e3222", size = 108202, upload-time = "2026-03-01T22:05:02.273Z" }, - { url = "https://files.pythonhosted.org/packages/59/97/35ca6767524687ad64e5f5c31ad54bc76d585585a9fcb40f649e7e82ffed/yarl-1.23.0-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:4764a6a7588561a9aef92f65bda2c4fb58fe7c675c0883862e6df97559de0bfb", size = 99866, upload-time = "2026-03-01T22:05:03.597Z" }, - { url = "https://files.pythonhosted.org/packages/d3/1c/1a3387ee6d73589f6f2a220ae06f2984f6c20b40c734989b0a44f5987308/yarl-1.23.0-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:03214408cfa590df47728b84c679ae4ef00be2428e11630277be0727eba2d7cc", size = 107852, upload-time = "2026-03-01T22:05:04.986Z" }, - { url = "https://files.pythonhosted.org/packages/a4/b8/35c0750fcd5a3f781058bfd954515dd4b1eab45e218cbb85cf11132215f1/yarl-1.23.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:170e26584b060879e29fac213e4228ef063f39128723807a312e5c7fec28eff2", size = 102919, upload-time = "2026-03-01T22:05:06.397Z" }, - { url = "https://files.pythonhosted.org/packages/e5/1c/9a1979aec4a81896d597bcb2177827f2dbee3f5b7cc48b2d0dadb644b41d/yarl-1.23.0-cp311-cp311-win32.whl", hash = "sha256:51430653db848d258336cfa0244427b17d12db63d42603a55f0d4546f50f25b5", size = 82602, upload-time = "2026-03-01T22:05:08.444Z" }, - { url = "https://files.pythonhosted.org/packages/93/22/b85eca6fa2ad9491af48c973e4c8cf6b103a73dbb271fe3346949449fca0/yarl-1.23.0-cp311-cp311-win_amd64.whl", hash = "sha256:bf49a3ae946a87083ef3a34c8f677ae4243f5b824bfc4c69672e72b3d6719d46", size = 87461, upload-time = "2026-03-01T22:05:10.145Z" }, - { url = "https://files.pythonhosted.org/packages/93/95/07e3553fe6f113e6864a20bdc53a78113cda3b9ced8784ee52a52c9f80d8/yarl-1.23.0-cp311-cp311-win_arm64.whl", hash = "sha256:b39cb32a6582750b6cc77bfb3c49c0f8760dc18dc96ec9fb55fbb0f04e08b928", size = 82336, upload-time = "2026-03-01T22:05:11.554Z" }, - { url = "https://files.pythonhosted.org/packages/88/8a/94615bc31022f711add374097ad4144d569e95ff3c38d39215d07ac153a0/yarl-1.23.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:1932b6b8bba8d0160a9d1078aae5838a66039e8832d41d2992daa9a3a08f7860", size = 124737, upload-time = "2026-03-01T22:05:12.897Z" }, - { url = "https://files.pythonhosted.org/packages/e3/6f/c6554045d59d64052698add01226bc867b52fe4a12373415d7991fdca95d/yarl-1.23.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:411225bae281f114067578891bc75534cfb3d92a3b4dfef7a6ca78ba354e6069", size = 87029, upload-time = "2026-03-01T22:05:14.376Z" }, - { url = "https://files.pythonhosted.org/packages/19/2a/725ecc166d53438bc88f76822ed4b1e3b10756e790bafd7b523fe97c322d/yarl-1.23.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:13a563739ae600a631c36ce096615fe307f131344588b0bc0daec108cdb47b25", size = 86310, upload-time = "2026-03-01T22:05:15.71Z" }, - { url = "https://files.pythonhosted.org/packages/99/30/58260ed98e6ff7f90ba84442c1ddd758c9170d70327394a6227b310cd60f/yarl-1.23.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9cbf44c5cb4a7633d078788e1b56387e3d3cf2b8139a3be38040b22d6c3221c8", size = 97587, upload-time = "2026-03-01T22:05:17.384Z" }, - { url = "https://files.pythonhosted.org/packages/76/0a/8b08aac08b50682e65759f7f8dde98ae8168f72487e7357a5d684c581ef9/yarl-1.23.0-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:53ad387048f6f09a8969631e4de3f1bf70c50e93545d64af4f751b2498755072", size = 92528, upload-time = "2026-03-01T22:05:18.804Z" }, - { url = "https://files.pythonhosted.org/packages/52/07/0b7179101fe5f8385ec6c6bb5d0cb9f76bd9fb4a769591ab6fb5cdbfc69a/yarl-1.23.0-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:4a59ba56f340334766f3a4442e0efd0af895fae9e2b204741ef885c446b3a1a8", size = 105339, upload-time = "2026-03-01T22:05:20.235Z" }, - { url = "https://files.pythonhosted.org/packages/d3/8a/36d82869ab5ec829ca8574dfcb92b51286fcfb1e9c7a73659616362dc880/yarl-1.23.0-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:803a3c3ce4acc62eaf01eaca1208dcf0783025ef27572c3336502b9c232005e7", size = 105061, upload-time = "2026-03-01T22:05:22.268Z" }, - { url = "https://files.pythonhosted.org/packages/66/3e/868e5c3364b6cee19ff3e1a122194fa4ce51def02c61023970442162859e/yarl-1.23.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a3d2bff8f37f8d0f96c7ec554d16945050d54462d6e95414babaa18bfafc7f51", size = 100132, upload-time = "2026-03-01T22:05:23.638Z" }, - { url = "https://files.pythonhosted.org/packages/cf/26/9c89acf82f08a52cb52d6d39454f8d18af15f9d386a23795389d1d423823/yarl-1.23.0-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:c75eb09e8d55bceb4367e83496ff8ef2bc7ea6960efb38e978e8073ea59ecb67", size = 99289, upload-time = "2026-03-01T22:05:25.749Z" }, - { url = "https://files.pythonhosted.org/packages/6f/54/5b0db00d2cb056922356104468019c0a132e89c8d3ab67d8ede9f4483d2a/yarl-1.23.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:877b0738624280e34c55680d6054a307aa94f7d52fa0e3034a9cc6e790871da7", size = 96950, upload-time = "2026-03-01T22:05:27.318Z" }, - { url = "https://files.pythonhosted.org/packages/f6/40/10fa93811fd439341fad7e0718a86aca0de9548023bbb403668d6555acab/yarl-1.23.0-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:b5405bb8f0e783a988172993cfc627e4d9d00432d6bbac65a923041edacf997d", size = 93960, upload-time = "2026-03-01T22:05:28.738Z" }, - { url = "https://files.pythonhosted.org/packages/bc/d2/8ae2e6cd77d0805f4526e30ec43b6f9a3dfc542d401ac4990d178e4bf0cf/yarl-1.23.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:1c3a3598a832590c5a3ce56ab5576361b5688c12cb1d39429cf5dba30b510760", size = 104703, upload-time = "2026-03-01T22:05:30.438Z" }, - { url = "https://files.pythonhosted.org/packages/2f/0c/b3ceacf82c3fe21183ce35fa2acf5320af003d52bc1fcf5915077681142e/yarl-1.23.0-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:8419ebd326430d1cbb7efb5292330a2cf39114e82df5cc3d83c9a0d5ebeaf2f2", size = 98325, upload-time = "2026-03-01T22:05:31.835Z" }, - { url = "https://files.pythonhosted.org/packages/9d/e0/12900edd28bdab91a69bd2554b85ad7b151f64e8b521fe16f9ad2f56477a/yarl-1.23.0-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:be61f6fff406ca40e3b1d84716fde398fc08bc63dd96d15f3a14230a0973ed86", size = 105067, upload-time = "2026-03-01T22:05:33.358Z" }, - { url = "https://files.pythonhosted.org/packages/15/61/74bb1182cf79c9bbe4eb6b1f14a57a22d7a0be5e9cedf8e2d5c2086474c3/yarl-1.23.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:3ceb13c5c858d01321b5d9bb65e4cf37a92169ea470b70fec6f236b2c9dd7e34", size = 100285, upload-time = "2026-03-01T22:05:35.4Z" }, - { url = "https://files.pythonhosted.org/packages/69/7f/cd5ef733f2550de6241bd8bd8c3febc78158b9d75f197d9c7baa113436af/yarl-1.23.0-cp312-cp312-win32.whl", hash = "sha256:fffc45637bcd6538de8b85f51e3df3223e4ad89bccbfca0481c08c7fc8b7ed7d", size = 82359, upload-time = "2026-03-01T22:05:36.811Z" }, - { url = "https://files.pythonhosted.org/packages/f5/be/25216a49daeeb7af2bec0db22d5e7df08ed1d7c9f65d78b14f3b74fd72fc/yarl-1.23.0-cp312-cp312-win_amd64.whl", hash = "sha256:f69f57305656a4852f2a7203efc661d8c042e6cc67f7acd97d8667fb448a426e", size = 87674, upload-time = "2026-03-01T22:05:38.171Z" }, - { url = "https://files.pythonhosted.org/packages/d2/35/aeab955d6c425b227d5b7247eafb24f2653fedc32f95373a001af5dfeb9e/yarl-1.23.0-cp312-cp312-win_arm64.whl", hash = "sha256:6e87a6e8735b44816e7db0b2fbc9686932df473c826b0d9743148432e10bb9b9", size = 81879, upload-time = "2026-03-01T22:05:40.006Z" }, - { url = "https://files.pythonhosted.org/packages/9a/4b/a0a6e5d0ee8a2f3a373ddef8a4097d74ac901ac363eea1440464ccbe0898/yarl-1.23.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:16c6994ac35c3e74fb0ae93323bf8b9c2a9088d55946109489667c510a7d010e", size = 123796, upload-time = "2026-03-01T22:05:41.412Z" }, - { url = "https://files.pythonhosted.org/packages/67/b6/8925d68af039b835ae876db5838e82e76ec87b9782ecc97e192b809c4831/yarl-1.23.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:4a42e651629dafb64fd5b0286a3580613702b5809ad3f24934ea87595804f2c5", size = 86547, upload-time = "2026-03-01T22:05:42.841Z" }, - { url = "https://files.pythonhosted.org/packages/ae/50/06d511cc4b8e0360d3c94af051a768e84b755c5eb031b12adaaab6dec6e5/yarl-1.23.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:7c6b9461a2a8b47c65eef63bb1c76a4f1c119618ffa99ea79bc5bb1e46c5821b", size = 85854, upload-time = "2026-03-01T22:05:44.85Z" }, - { url = "https://files.pythonhosted.org/packages/c4/f4/4e30b250927ffdab4db70da08b9b8d2194d7c7b400167b8fbeca1e4701ca/yarl-1.23.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:2569b67d616eab450d262ca7cb9f9e19d2f718c70a8b88712859359d0ab17035", size = 98351, upload-time = "2026-03-01T22:05:46.836Z" }, - { url = "https://files.pythonhosted.org/packages/86/fc/4118c5671ea948208bdb1492d8b76bdf1453d3e73df051f939f563e7dcc5/yarl-1.23.0-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:e9d9a4d06d3481eab79803beb4d9bd6f6a8e781ec078ac70d7ef2dcc29d1bea5", size = 92711, upload-time = "2026-03-01T22:05:48.316Z" }, - { url = "https://files.pythonhosted.org/packages/56/11/1ed91d42bd9e73c13dc9e7eb0dd92298d75e7ac4dd7f046ad0c472e231cd/yarl-1.23.0-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f514f6474e04179d3d33175ed3f3e31434d3130d42ec153540d5b157deefd735", size = 106014, upload-time = "2026-03-01T22:05:50.028Z" }, - { url = "https://files.pythonhosted.org/packages/ce/c9/74e44e056a23fbc33aca71779ef450ca648a5bc472bdad7a82339918f818/yarl-1.23.0-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:fda207c815b253e34f7e1909840fd14299567b1c0eb4908f8c2ce01a41265401", size = 105557, upload-time = "2026-03-01T22:05:51.416Z" }, - { url = "https://files.pythonhosted.org/packages/66/fe/b1e10b08d287f518994f1e2ff9b6d26f0adeecd8dd7d533b01bab29a3eda/yarl-1.23.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:34b6cf500e61c90f305094911f9acc9c86da1a05a7a3f5be9f68817043f486e4", size = 101559, upload-time = "2026-03-01T22:05:52.872Z" }, - { url = "https://files.pythonhosted.org/packages/72/59/c5b8d94b14e3d3c2a9c20cb100119fd534ab5a14b93673ab4cc4a4141ea5/yarl-1.23.0-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:d7504f2b476d21653e4d143f44a175f7f751cd41233525312696c76aa3dbb23f", size = 100502, upload-time = "2026-03-01T22:05:54.954Z" }, - { url = "https://files.pythonhosted.org/packages/77/4f/96976cb54cbfc5c9fd73ed4c51804f92f209481d1fb190981c0f8a07a1d7/yarl-1.23.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:578110dd426f0d209d1509244e6d4a3f1a3e9077655d98c5f22583d63252a08a", size = 98027, upload-time = "2026-03-01T22:05:56.409Z" }, - { url = "https://files.pythonhosted.org/packages/63/6e/904c4f476471afdbad6b7e5b70362fb5810e35cd7466529a97322b6f5556/yarl-1.23.0-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:609d3614d78d74ebe35f54953c5bbd2ac647a7ddb9c30a5d877580f5e86b22f2", size = 95369, upload-time = "2026-03-01T22:05:58.141Z" }, - { url = "https://files.pythonhosted.org/packages/9d/40/acfcdb3b5f9d68ef499e39e04d25e141fe90661f9d54114556cf83be8353/yarl-1.23.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:4966242ec68afc74c122f8459abd597afd7d8a60dc93d695c1334c5fd25f762f", size = 105565, upload-time = "2026-03-01T22:06:00.286Z" }, - { url = "https://files.pythonhosted.org/packages/5e/c6/31e28f3a6ba2869c43d124f37ea5260cac9c9281df803c354b31f4dd1f3c/yarl-1.23.0-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:e0fd068364a6759bc794459f0a735ab151d11304346332489c7972bacbe9e72b", size = 99813, upload-time = "2026-03-01T22:06:01.712Z" }, - { url = "https://files.pythonhosted.org/packages/08/1f/6f65f59e72d54aa467119b63fc0b0b1762eff0232db1f4720cd89e2f4a17/yarl-1.23.0-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:39004f0ad156da43e86aa71f44e033de68a44e5a31fc53507b36dd253970054a", size = 105632, upload-time = "2026-03-01T22:06:03.188Z" }, - { url = "https://files.pythonhosted.org/packages/a3/c4/18b178a69935f9e7a338127d5b77d868fdc0f0e49becd286d51b3a18c61d/yarl-1.23.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:e5723c01a56c5028c807c701aa66722916d2747ad737a046853f6c46f4875543", size = 101895, upload-time = "2026-03-01T22:06:04.651Z" }, - { url = "https://files.pythonhosted.org/packages/8f/54/f5b870b5505663911dba950a8e4776a0dbd51c9c54c0ae88e823e4b874a0/yarl-1.23.0-cp313-cp313-win32.whl", hash = "sha256:1b6b572edd95b4fa8df75de10b04bc81acc87c1c7d16bcdd2035b09d30acc957", size = 82356, upload-time = "2026-03-01T22:06:06.04Z" }, - { url = "https://files.pythonhosted.org/packages/7a/84/266e8da36879c6edcd37b02b547e2d9ecdfea776be49598e75696e3316e1/yarl-1.23.0-cp313-cp313-win_amd64.whl", hash = "sha256:baaf55442359053c7d62f6f8413a62adba3205119bcb6f49594894d8be47e5e3", size = 87515, upload-time = "2026-03-01T22:06:08.107Z" }, - { url = "https://files.pythonhosted.org/packages/00/fd/7e1c66efad35e1649114fa13f17485f62881ad58edeeb7f49f8c5e748bf9/yarl-1.23.0-cp313-cp313-win_arm64.whl", hash = "sha256:fb4948814a2a98e3912505f09c9e7493b1506226afb1f881825368d6fb776ee3", size = 81785, upload-time = "2026-03-01T22:06:10.181Z" }, - { url = "https://files.pythonhosted.org/packages/9c/fc/119dd07004f17ea43bb91e3ece6587759edd7519d6b086d16bfbd3319982/yarl-1.23.0-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:aecfed0b41aa72b7881712c65cf764e39ce2ec352324f5e0837c7048d9e6daaa", size = 130719, upload-time = "2026-03-01T22:06:11.708Z" }, - { url = "https://files.pythonhosted.org/packages/e6/0d/9f2348502fbb3af409e8f47730282cd6bc80dec6630c1e06374d882d6eb2/yarl-1.23.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:a41bcf68efd19073376eb8cf948b8d9be0af26256403e512bb18f3966f1f9120", size = 89690, upload-time = "2026-03-01T22:06:13.429Z" }, - { url = "https://files.pythonhosted.org/packages/50/93/e88f3c80971b42cfc83f50a51b9d165a1dbf154b97005f2994a79f212a07/yarl-1.23.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:cde9a2ecd91668bcb7f077c4966d8ceddb60af01b52e6e3e2680e4cf00ad1a59", size = 89851, upload-time = "2026-03-01T22:06:15.53Z" }, - { url = "https://files.pythonhosted.org/packages/1c/07/61c9dd8ba8f86473263b4036f70fb594c09e99c0d9737a799dfd8bc85651/yarl-1.23.0-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5023346c4ee7992febc0068e7593de5fa2bf611848c08404b35ebbb76b1b0512", size = 95874, upload-time = "2026-03-01T22:06:17.553Z" }, - { url = "https://files.pythonhosted.org/packages/9e/e9/f9ff8ceefba599eac6abddcfb0b3bee9b9e636e96dbf54342a8577252379/yarl-1.23.0-cp313-cp313t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:d1009abedb49ae95b136a8904a3f71b342f849ffeced2d3747bf29caeda218c4", size = 88710, upload-time = "2026-03-01T22:06:19.004Z" }, - { url = "https://files.pythonhosted.org/packages/eb/78/0231bfcc5d4c8eec220bc2f9ef82cb4566192ea867a7c5b4148f44f6cbcd/yarl-1.23.0-cp313-cp313t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a8d00f29b42f534cc8aa3931cfe773b13b23e561e10d2b26f27a8d309b0e82a1", size = 101033, upload-time = "2026-03-01T22:06:21.203Z" }, - { url = "https://files.pythonhosted.org/packages/cd/9b/30ea5239a61786f18fd25797151a17fbb3be176977187a48d541b5447dd4/yarl-1.23.0-cp313-cp313t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:95451e6ce06c3e104556d73b559f5da6c34a069b6b62946d3ad66afcd51642ea", size = 100817, upload-time = "2026-03-01T22:06:22.738Z" }, - { url = "https://files.pythonhosted.org/packages/62/e2/a4980481071791bc83bce2b7a1a1f7adcabfa366007518b4b845e92eeee3/yarl-1.23.0-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:531ef597132086b6cf96faa7c6c1dcd0361dd5f1694e5cc30375907b9b7d3ea9", size = 97482, upload-time = "2026-03-01T22:06:24.21Z" }, - { url = "https://files.pythonhosted.org/packages/e5/1e/304a00cf5f6100414c4b5a01fc7ff9ee724b62158a08df2f8170dfc72a2d/yarl-1.23.0-cp313-cp313t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:88f9fb0116fbfcefcab70f85cf4b74a2b6ce5d199c41345296f49d974ddb4123", size = 95949, upload-time = "2026-03-01T22:06:25.697Z" }, - { url = "https://files.pythonhosted.org/packages/68/03/093f4055ed4cae649ac53bca3d180bd37102e9e11d048588e9ab0c0108d0/yarl-1.23.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:e7b0460976dc75cb87ad9cc1f9899a4b97751e7d4e77ab840fc9b6d377b8fd24", size = 95839, upload-time = "2026-03-01T22:06:27.309Z" }, - { url = "https://files.pythonhosted.org/packages/b9/28/4c75ebb108f322aa8f917ae10a8ffa4f07cae10a8a627b64e578617df6a0/yarl-1.23.0-cp313-cp313t-musllinux_1_2_armv7l.whl", hash = "sha256:115136c4a426f9da976187d238e84139ff6b51a20839aa6e3720cd1026d768de", size = 90696, upload-time = "2026-03-01T22:06:29.048Z" }, - { url = "https://files.pythonhosted.org/packages/23/9c/42c2e2dd91c1a570402f51bdf066bfdb1241c2240ba001967bad778e77b7/yarl-1.23.0-cp313-cp313t-musllinux_1_2_ppc64le.whl", hash = "sha256:ead11956716a940c1abc816b7df3fa2b84d06eaed8832ca32f5c5e058c65506b", size = 100865, upload-time = "2026-03-01T22:06:30.525Z" }, - { url = "https://files.pythonhosted.org/packages/74/05/1bcd60a8a0a914d462c305137246b6f9d167628d73568505fce3f1cb2e65/yarl-1.23.0-cp313-cp313t-musllinux_1_2_riscv64.whl", hash = "sha256:fe8f8f5e70e6dbdfca9882cd9deaac058729bcf323cf7a58660901e55c9c94f6", size = 96234, upload-time = "2026-03-01T22:06:32.692Z" }, - { url = "https://files.pythonhosted.org/packages/90/b2/f52381aac396d6778ce516b7bc149c79e65bfc068b5de2857ab69eeea3b7/yarl-1.23.0-cp313-cp313t-musllinux_1_2_s390x.whl", hash = "sha256:a0e317df055958a0c1e79e5d2aa5a5eaa4a6d05a20d4b0c9c3f48918139c9fc6", size = 100295, upload-time = "2026-03-01T22:06:34.268Z" }, - { url = "https://files.pythonhosted.org/packages/e5/e8/638bae5bbf1113a659b2435d8895474598afe38b4a837103764f603aba56/yarl-1.23.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:6f0fd84de0c957b2d280143522c4f91a73aada1923caee763e24a2b3fda9f8a5", size = 97784, upload-time = "2026-03-01T22:06:35.864Z" }, - { url = "https://files.pythonhosted.org/packages/80/25/a3892b46182c586c202629fc2159aa13975d3741d52ebd7347fd501d48d5/yarl-1.23.0-cp313-cp313t-win32.whl", hash = "sha256:93a784271881035ab4406a172edb0faecb6e7d00f4b53dc2f55919d6c9688595", size = 88313, upload-time = "2026-03-01T22:06:37.39Z" }, - { url = "https://files.pythonhosted.org/packages/43/68/8c5b36aa5178900b37387937bc2c2fe0e9505537f713495472dcf6f6fccc/yarl-1.23.0-cp313-cp313t-win_amd64.whl", hash = "sha256:dd00607bffbf30250fe108065f07453ec124dbf223420f57f5e749b04295e090", size = 94932, upload-time = "2026-03-01T22:06:39.579Z" }, - { url = "https://files.pythonhosted.org/packages/c6/cc/d79ba8292f51f81f4dc533a8ccfb9fc6992cabf0998ed3245de7589dc07c/yarl-1.23.0-cp313-cp313t-win_arm64.whl", hash = "sha256:ac09d42f48f80c9ee1635b2fcaa819496a44502737660d3c0f2ade7526d29144", size = 84786, upload-time = "2026-03-01T22:06:41.988Z" }, - { url = "https://files.pythonhosted.org/packages/90/98/b85a038d65d1b92c3903ab89444f48d3cee490a883477b716d7a24b1a78c/yarl-1.23.0-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:21d1b7305a71a15b4794b5ff22e8eef96ff4a6d7f9657155e5aa419444b28912", size = 124455, upload-time = "2026-03-01T22:06:43.615Z" }, - { url = "https://files.pythonhosted.org/packages/39/54/bc2b45559f86543d163b6e294417a107bb87557609007c007ad889afec18/yarl-1.23.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:85610b4f27f69984932a7abbe52703688de3724d9f72bceb1cca667deff27474", size = 86752, upload-time = "2026-03-01T22:06:45.425Z" }, - { url = "https://files.pythonhosted.org/packages/24/f9/e8242b68362bffe6fb536c8db5076861466fc780f0f1b479fc4ffbebb128/yarl-1.23.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:23f371bd662cf44a7630d4d113101eafc0cfa7518a2760d20760b26021454719", size = 86291, upload-time = "2026-03-01T22:06:46.974Z" }, - { url = "https://files.pythonhosted.org/packages/ea/d8/d1cb2378c81dd729e98c716582b1ccb08357e8488e4c24714658cc6630e8/yarl-1.23.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c4a80f77dc1acaaa61f0934176fccca7096d9b1ff08c8ba9cddf5ae034a24319", size = 99026, upload-time = "2026-03-01T22:06:48.459Z" }, - { url = "https://files.pythonhosted.org/packages/0a/ff/7196790538f31debe3341283b5b0707e7feb947620fc5e8236ef28d44f72/yarl-1.23.0-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:bd654fad46d8d9e823afbb4f87c79160b5a374ed1ff5bde24e542e6ba8f41434", size = 92355, upload-time = "2026-03-01T22:06:50.306Z" }, - { url = "https://files.pythonhosted.org/packages/c1/56/25d58c3eddde825890a5fe6aa1866228377354a3c39262235234ab5f616b/yarl-1.23.0-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:682bae25f0a0dd23a056739f23a134db9f52a63e2afd6bfb37ddc76292bbd723", size = 106417, upload-time = "2026-03-01T22:06:52.1Z" }, - { url = "https://files.pythonhosted.org/packages/51/8a/882c0e7bc8277eb895b31bce0138f51a1ba551fc2e1ec6753ffc1e7c1377/yarl-1.23.0-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:a82836cab5f197a0514235aaf7ffccdc886ccdaa2324bc0aafdd4ae898103039", size = 106422, upload-time = "2026-03-01T22:06:54.424Z" }, - { url = "https://files.pythonhosted.org/packages/42/2b/fef67d616931055bf3d6764885990a3ac647d68734a2d6a9e1d13de437a2/yarl-1.23.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1c57676bdedc94cd3bc37724cf6f8cd2779f02f6aba48de45feca073e714fe52", size = 101915, upload-time = "2026-03-01T22:06:55.895Z" }, - { url = "https://files.pythonhosted.org/packages/18/6a/530e16aebce27c5937920f3431c628a29a4b6b430fab3fd1c117b26ff3f6/yarl-1.23.0-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:c7f8dc16c498ff06497c015642333219871effba93e4a2e8604a06264aca5c5c", size = 100690, upload-time = "2026-03-01T22:06:58.21Z" }, - { url = "https://files.pythonhosted.org/packages/88/08/93749219179a45e27b036e03260fda05190b911de8e18225c294ac95bbc9/yarl-1.23.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:5ee586fb17ff8f90c91cf73c6108a434b02d69925f44f5f8e0d7f2f260607eae", size = 98750, upload-time = "2026-03-01T22:06:59.794Z" }, - { url = "https://files.pythonhosted.org/packages/d9/cf/ea424a004969f5d81a362110a6ac1496d79efdc6d50c2c4b2e3ea0fc2519/yarl-1.23.0-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:17235362f580149742739cc3828b80e24029d08cbb9c4bda0242c7b5bc610a8e", size = 94685, upload-time = "2026-03-01T22:07:01.375Z" }, - { url = "https://files.pythonhosted.org/packages/e2/b7/14341481fe568e2b0408bcf1484c652accafe06a0ade9387b5d3fd9df446/yarl-1.23.0-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:0793e2bd0cf14234983bbb371591e6bea9e876ddf6896cdcc93450996b0b5c85", size = 106009, upload-time = "2026-03-01T22:07:03.151Z" }, - { url = "https://files.pythonhosted.org/packages/0a/e6/5c744a9b54f4e8007ad35bce96fbc9218338e84812d36f3390cea616881a/yarl-1.23.0-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:3650dc2480f94f7116c364096bc84b1d602f44224ef7d5c7208425915c0475dd", size = 100033, upload-time = "2026-03-01T22:07:04.701Z" }, - { url = "https://files.pythonhosted.org/packages/0c/23/e3bfc188d0b400f025bc49d99793d02c9abe15752138dcc27e4eaf0c4a9e/yarl-1.23.0-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:f40e782d49630ad384db66d4d8b73ff4f1b8955dc12e26b09a3e3af064b3b9d6", size = 106483, upload-time = "2026-03-01T22:07:06.231Z" }, - { url = "https://files.pythonhosted.org/packages/72/42/f0505f949a90b3f8b7a363d6cbdf398f6e6c58946d85c6d3a3bc70595b26/yarl-1.23.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:94f8575fbdf81749008d980c17796097e645574a3b8c28ee313931068dad14fe", size = 102175, upload-time = "2026-03-01T22:07:08.4Z" }, - { url = "https://files.pythonhosted.org/packages/aa/65/b39290f1d892a9dd671d1c722014ca062a9c35d60885d57e5375db0404b5/yarl-1.23.0-cp314-cp314-win32.whl", hash = "sha256:c8aa34a5c864db1087d911a0b902d60d203ea3607d91f615acd3f3108ac32169", size = 83871, upload-time = "2026-03-01T22:07:09.968Z" }, - { url = "https://files.pythonhosted.org/packages/a9/5b/9b92f54c784c26e2a422e55a8d2607ab15b7ea3349e28359282f84f01d43/yarl-1.23.0-cp314-cp314-win_amd64.whl", hash = "sha256:63e92247f383c85ab00dd0091e8c3fa331a96e865459f5ee80353c70a4a42d70", size = 89093, upload-time = "2026-03-01T22:07:11.501Z" }, - { url = "https://files.pythonhosted.org/packages/e0/7d/8a84dc9381fd4412d5e7ff04926f9865f6372b4c2fd91e10092e65d29eb8/yarl-1.23.0-cp314-cp314-win_arm64.whl", hash = "sha256:70efd20be968c76ece7baa8dafe04c5be06abc57f754d6f36f3741f7aa7a208e", size = 83384, upload-time = "2026-03-01T22:07:13.069Z" }, - { url = "https://files.pythonhosted.org/packages/dd/8d/d2fad34b1c08aa161b74394183daa7d800141aaaee207317e82c790b418d/yarl-1.23.0-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:9a18d6f9359e45722c064c97464ec883eb0e0366d33eda61cb19a244bf222679", size = 131019, upload-time = "2026-03-01T22:07:14.903Z" }, - { url = "https://files.pythonhosted.org/packages/19/ff/33009a39d3ccf4b94d7d7880dfe17fb5816c5a4fe0096d9b56abceea9ac7/yarl-1.23.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:2803ed8b21ca47a43da80a6fd1ed3019d30061f7061daa35ac54f63933409412", size = 89894, upload-time = "2026-03-01T22:07:17.372Z" }, - { url = "https://files.pythonhosted.org/packages/0c/f1/dab7ac5e7306fb79c0190766a3c00b4cb8d09a1f390ded68c85a5934faf5/yarl-1.23.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:394906945aa8b19fc14a61cf69743a868bb8c465efe85eee687109cc540b98f4", size = 89979, upload-time = "2026-03-01T22:07:19.361Z" }, - { url = "https://files.pythonhosted.org/packages/aa/b1/08e95f3caee1fad6e65017b9f26c1d79877b502622d60e517de01e72f95d/yarl-1.23.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:71d006bee8397a4a89f469b8deb22469fe7508132d3c17fa6ed871e79832691c", size = 95943, upload-time = "2026-03-01T22:07:21.266Z" }, - { url = "https://files.pythonhosted.org/packages/c0/cc/6409f9018864a6aa186c61175b977131f373f1988e198e031236916e87e4/yarl-1.23.0-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:62694e275c93d54f7ccedcfef57d42761b2aad5234b6be1f3e3026cae4001cd4", size = 88786, upload-time = "2026-03-01T22:07:23.129Z" }, - { url = "https://files.pythonhosted.org/packages/76/40/cc22d1d7714b717fde2006fad2ced5efe5580606cb059ae42117542122f3/yarl-1.23.0-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a31de1613658308efdb21ada98cbc86a97c181aa050ba22a808120bb5be3ab94", size = 101307, upload-time = "2026-03-01T22:07:24.689Z" }, - { url = "https://files.pythonhosted.org/packages/8f/0d/476c38e85ddb4c6ec6b20b815bdd779aa386a013f3d8b85516feee55c8dc/yarl-1.23.0-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:fb1e8b8d66c278b21d13b0a7ca22c41dd757a7c209c6b12c313e445c31dd3b28", size = 100904, upload-time = "2026-03-01T22:07:26.287Z" }, - { url = "https://files.pythonhosted.org/packages/72/32/0abe4a76d59adf2081dcb0397168553ece4616ada1c54d1c49d8936c74f8/yarl-1.23.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:50f9d8d531dfb767c565f348f33dd5139a6c43f5cbdf3f67da40d54241df93f6", size = 97728, upload-time = "2026-03-01T22:07:27.906Z" }, - { url = "https://files.pythonhosted.org/packages/b7/35/7b30f4810fba112f60f5a43237545867504e15b1c7647a785fbaf588fac2/yarl-1.23.0-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:575aa4405a656e61a540f4a80eaa5260f2a38fff7bfdc4b5f611840d76e9e277", size = 95964, upload-time = "2026-03-01T22:07:30.198Z" }, - { url = "https://files.pythonhosted.org/packages/2d/86/ed7a73ab85ef00e8bb70b0cb5421d8a2a625b81a333941a469a6f4022828/yarl-1.23.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:041b1a4cefacf65840b4e295c6985f334ba83c30607441ae3cf206a0eed1a2e4", size = 95882, upload-time = "2026-03-01T22:07:32.132Z" }, - { url = "https://files.pythonhosted.org/packages/19/90/d56967f61a29d8498efb7afb651e0b2b422a1e9b47b0ab5f4e40a19b699b/yarl-1.23.0-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:d38c1e8231722c4ce40d7593f28d92b5fc72f3e9774fe73d7e800ec32299f63a", size = 90797, upload-time = "2026-03-01T22:07:34.404Z" }, - { url = "https://files.pythonhosted.org/packages/72/00/8b8f76909259f56647adb1011d7ed8b321bcf97e464515c65016a47ecdf0/yarl-1.23.0-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:d53834e23c015ee83a99377db6e5e37d8484f333edb03bd15b4bc312cc7254fb", size = 101023, upload-time = "2026-03-01T22:07:35.953Z" }, - { url = "https://files.pythonhosted.org/packages/ac/e2/cab11b126fb7d440281b7df8e9ddbe4851e70a4dde47a202b6642586b8d9/yarl-1.23.0-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:2e27c8841126e017dd2a054a95771569e6070b9ee1b133366d8b31beb5018a41", size = 96227, upload-time = "2026-03-01T22:07:37.594Z" }, - { url = "https://files.pythonhosted.org/packages/c2/9b/2c893e16bfc50e6b2edf76c1a9eb6cb0c744346197e74c65e99ad8d634d0/yarl-1.23.0-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:76855800ac56f878847a09ce6dba727c93ca2d89c9e9d63002d26b916810b0a2", size = 100302, upload-time = "2026-03-01T22:07:39.334Z" }, - { url = "https://files.pythonhosted.org/packages/28/ec/5498c4e3a6d5f1003beb23405671c2eb9cdbf3067d1c80f15eeafe301010/yarl-1.23.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:e09fd068c2e169a7070d83d3bde728a4d48de0549f975290be3c108c02e499b4", size = 98202, upload-time = "2026-03-01T22:07:41.717Z" }, - { url = "https://files.pythonhosted.org/packages/fe/c3/cd737e2d45e70717907f83e146f6949f20cc23cd4bf7b2688727763aa458/yarl-1.23.0-cp314-cp314t-win32.whl", hash = "sha256:73309162a6a571d4cbd3b6a1dcc703c7311843ae0d1578df6f09be4e98df38d4", size = 90558, upload-time = "2026-03-01T22:07:43.433Z" }, - { url = "https://files.pythonhosted.org/packages/e1/19/3774d162f6732d1cfb0b47b4140a942a35ca82bb19b6db1f80e9e7bdc8f8/yarl-1.23.0-cp314-cp314t-win_amd64.whl", hash = "sha256:4503053d296bc6e4cbd1fad61cf3b6e33b939886c4f249ba7c78b602214fabe2", size = 97610, upload-time = "2026-03-01T22:07:45.773Z" }, - { url = "https://files.pythonhosted.org/packages/51/47/3fa2286c3cb162c71cdb34c4224d5745a1ceceb391b2bd9b19b668a8d724/yarl-1.23.0-cp314-cp314t-win_arm64.whl", hash = "sha256:44bb7bef4ea409384e3f8bc36c063d77ea1b8d4a5b2706956c0d6695f07dcc25", size = 86041, upload-time = "2026-03-01T22:07:49.026Z" }, - { url = "https://files.pythonhosted.org/packages/69/68/c8739671f5699c7dc470580a4f821ef37c32c4cb0b047ce223a7f115757f/yarl-1.23.0-py3-none-any.whl", hash = "sha256:a2df6afe50dea8ae15fa34c9f824a3ee958d785fd5d089063d960bae1daa0a3f", size = 48288, upload-time = "2026-03-01T22:07:51.388Z" }, + { url = "https://files.pythonhosted.org/packages/85/92/55fa9ee84cb8ec9930a910b5753936a926f918d8cc8965bdac571479c095/yarl-1.25.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:142c06c4d6a35ee3ec5da08499805e879cb3ca7c1fbfbecb0140fe72403818d6", size = 144695, upload-time = "2026-09-15T19:29:53.114Z" }, + { url = "https://files.pythonhosted.org/packages/16/b4/9edc8e605b16b2eb5bd0c2ccc73e2b15aab583862460767fb43f91f11839/yarl-1.25.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:24ce942011a61953e7d313438038f4d32ff21387b775f58a957f7a07dd55ef95", size = 104332, upload-time = "2026-09-15T19:29:55.443Z" }, + { url = "https://files.pythonhosted.org/packages/ae/de/4204e6646e278b1cd4a9cf73ebe8b7cfcf16693f1249b324eb273d67602a/yarl-1.25.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9e23c82b63cd7652fc24d33ed6cc17099d607aa3b4fc4ddc75e95062f3d82df4", size = 104449, upload-time = "2026-09-15T19:29:57.239Z" }, + { url = "https://files.pythonhosted.org/packages/1d/fc/21d74789198ad68a23a209ab0d73fe5a52d39ebbd9945041e72827acdd77/yarl-1.25.1-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8ee202350cf57abf0e9502a41601841019c25d3db7ff52d980aaf31446254059", size = 116828, upload-time = "2026-09-15T19:29:59.031Z" }, + { url = "https://files.pythonhosted.org/packages/8f/31/90891ddb61848c067ebd1fb505ab5902a6e7d4707c2f3823f67ff37883d3/yarl-1.25.1-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:5df89f769cc8ff94c3d7e7603386fba309d25ce5240132d26c15baa8d0e96c4c", size = 107150, upload-time = "2026-09-15T19:30:00.868Z" }, + { url = "https://files.pythonhosted.org/packages/a1/15/f3d18743d3688b5f01aa83034b6c00665692ab20e1d0c89a29000d4979ea/yarl-1.25.1-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:83e9f4a25085bd4b7214701a0794ff1f50fc633ffb8bdfebf07abdd81c2db126", size = 124704, upload-time = "2026-09-15T19:30:03.128Z" }, + { url = "https://files.pythonhosted.org/packages/99/37/718789d8004775d6a2db86b2afc72b1d156e0590b88a1b8634ddd4bdb8ee/yarl-1.25.1-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:e636b64d24fd9c38053c5e389a1174c66361fa49dcfd220f4dd35b4abde7cb89", size = 129246, upload-time = "2026-09-15T19:30:05.014Z" }, + { url = "https://files.pythonhosted.org/packages/28/b9/7818ac6dec7fbcd16be2d19495807c01e2c38834e57d41c63356a75e786b/yarl-1.25.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e5637ca8d0bd7fb72648a6c7934af4baaccb697657f7438c9d264fc2abb8b0b1", size = 118071, upload-time = "2026-09-15T19:30:06.977Z" }, + { url = "https://files.pythonhosted.org/packages/b2/e3/8d098cafb30a64df7283b5a5dd0d32d22a71b18a1b9ec071d0776ffe5c2a/yarl-1.25.1-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:683e362b8ba453080f7489c66f4ea794e751c35b72e7eab3575ef784c2fbc7fb", size = 116180, upload-time = "2026-09-15T19:30:08.836Z" }, + { url = "https://files.pythonhosted.org/packages/20/9c/fbe9432478d87e00eef80242e15179639df162cb3d5d8d978fc56dcb6c51/yarl-1.25.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:df23df54b5114a17c2d0ef192433e2e5a9f0c5178c32375e90b7cfc965f349d0", size = 116578, upload-time = "2026-09-15T19:30:10.782Z" }, + { url = "https://files.pythonhosted.org/packages/b1/8e/b3dfd03732236b86b0bcf06a72a37de412ff6f82e719a947c3c651d4dece/yarl-1.25.1-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:f53dcd26694f148f738edc052b5a69234833e739f10f4c3287bdfd8ec0f7b326", size = 108886, upload-time = "2026-09-15T19:30:12.951Z" }, + { url = "https://files.pythonhosted.org/packages/83/e1/94dacb650d4963d5f844bc3df7ba70288cb7b68ed5a4d070da71acb19b14/yarl-1.25.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:b8075fe90bc08e40b8b8a1874fab42ee4c7b56af05c5886e9cc841397f916908", size = 124098, upload-time = "2026-09-15T19:30:14.963Z" }, + { url = "https://files.pythonhosted.org/packages/d6/3f/c93f76a218258c7bfc60dd27fd56e9102bdbc625517f4a6ee673295fe4e4/yarl-1.25.1-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:a8c2b841478068440d8b733005d13a5ef535b9928cbc05f17182d410f32ba449", size = 115768, upload-time = "2026-09-15T19:30:16.736Z" }, + { url = "https://files.pythonhosted.org/packages/a8/79/4d93f13c3b05cda3c962805dec28cbc255c50239b3457808abc5633a00c2/yarl-1.25.1-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:ca32926d7d77bcc8838425c4c95e040a3ace1cb7dfdae599013458dcda2607ca", size = 122461, upload-time = "2026-09-15T19:30:18.901Z" }, + { url = "https://files.pythonhosted.org/packages/c5/8e/e2ba83b3a9bfc1d3b882ad35fa8abc04a7af4d9356f2e329a23d0c8d889d/yarl-1.25.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:192a866877a49993949ef1975864ad8728bea28ee810f6abe1a0729c2b500426", size = 118295, upload-time = "2026-09-15T19:30:21.07Z" }, + { url = "https://files.pythonhosted.org/packages/42/67/cb5ea1baa0c0ac60bda44ce59f601133154af2a2e67722d3517f8793855d/yarl-1.25.1-cp310-cp310-win_amd64.whl", hash = "sha256:3f4d48a6112712973e676bd792121fee470e432d749177162d9949d5c9460a1b", size = 102929, upload-time = "2026-09-15T19:30:23.122Z" }, + { url = "https://files.pythonhosted.org/packages/2f/85/9a1e98de10fc0e738d517efd2a9984c3e7db6cf35fa72b2b373988a9e9b7/yarl-1.25.1-cp310-cp310-win_arm64.whl", hash = "sha256:48796ea00a303961507dc6c8437c4b325a6fc3f95f7c36c71b91ea9a8150963c", size = 98854, upload-time = "2026-09-15T19:30:25.102Z" }, + { url = "https://files.pythonhosted.org/packages/83/b3/2cea721d495ca57f8f414aa4867ee263f486b274e07463158cf52f02ba7f/yarl-1.25.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:9d693bf4bf534e9ba3ae2780cfd577f5135629f7b5ac653490859d0b77864865", size = 143794, upload-time = "2026-09-15T19:30:26.946Z" }, + { url = "https://files.pythonhosted.org/packages/55/e6/cd145cff8e5cf60b8b3c41fbecfa2a45028a8dec3fbc52bec03595ff3d3b/yarl-1.25.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ab2054c5531af2a9ba7b69b8ec91e4f884420e83a8c5e579b013084cb57e5e5d", size = 103993, upload-time = "2026-09-15T19:30:28.661Z" }, + { url = "https://files.pythonhosted.org/packages/ce/7c/fbb40fe2d53747c40aa36a9e2bd2178a202f942bda0b670f3306d4aefbce/yarl-1.25.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:564fdc7085d2245ab84f88882fdb1d6ac0723124bff6ded35bfb1c00f812630d", size = 104010, upload-time = "2026-09-15T19:30:31.069Z" }, + { url = "https://files.pythonhosted.org/packages/f0/0b/5a516f70641092283f57cf3670bdb75e7327bcc0dcb5038697e4dfbfd569/yarl-1.25.1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:acae6b45d1ace09b6ba3876da43b88366ef368f73b988c7f57e14231753d4420", size = 116444, upload-time = "2026-09-15T19:30:32.894Z" }, + { url = "https://files.pythonhosted.org/packages/b6/8a/d1a627f827b0a404ae0f5647cab0534959081cde13b0756a783469fb3b5e/yarl-1.25.1-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:1fb2a01ba8cd9c5d2c5dc1ec35e0fc951d04b4f037541d4ac090c993ce58b3d7", size = 107565, upload-time = "2026-09-15T19:30:35.188Z" }, + { url = "https://files.pythonhosted.org/packages/aa/cf/c8e0aaec886840a6c4480fe44eaec7cd4319f79a563b79321473be79c56f/yarl-1.25.1-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:e92b6bcc741b86d67606c40d3cb9c7cc8e6c737f81e31f4a94efc204456c92e3", size = 125006, upload-time = "2026-09-15T19:30:37.1Z" }, + { url = "https://files.pythonhosted.org/packages/50/26/0cce366d54a93cdc8342965dc7663385e4db161625cc1e8b18e786753d24/yarl-1.25.1-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:72c34ac7ad4314c19362d5ce27626dcc8429bd30bbf8c179f4234078851f9492", size = 128717, upload-time = "2026-09-15T19:30:38.904Z" }, + { url = "https://files.pythonhosted.org/packages/95/0c/a71501bbc1a674ff72c4d6c2b75f4d9a5af819f5244c3a7558080a8802c5/yarl-1.25.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d5add7b4ca7afeea91d52e4d4e4db3b1fe9885b71f07054560d8c4296b7441a2", size = 117728, upload-time = "2026-09-15T19:30:40.809Z" }, + { url = "https://files.pythonhosted.org/packages/e7/6f/c3267ca01defeed9ed9c4ff9b17bd54915432c405945233265b707475d1c/yarl-1.25.1-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:def538065f9e4d4cf1ae164bd59aba00dfa84f03923e0de4c3788f252d6bcd17", size = 116224, upload-time = "2026-09-15T19:30:42.818Z" }, + { url = "https://files.pythonhosted.org/packages/8f/69/fad57ee52d648431718ee0f1f68966a99c1352c3924688ffbdcc9d3fe51a/yarl-1.25.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:0a191bfdb30a79b98e5d175d75285f9fcb78bf0e46ba5efda042e1c72071a0de", size = 116299, upload-time = "2026-09-15T19:30:44.966Z" }, + { url = "https://files.pythonhosted.org/packages/2a/d4/6a8c1e29f33338687ca278cba0a8fbf6525a322c2c02a9a500ccbe041152/yarl-1.25.1-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:71f42c5b9a948c113bbdebfa544598321431d064ff959d32e99b1feb61d68345", size = 108625, upload-time = "2026-09-15T19:30:46.874Z" }, + { url = "https://files.pythonhosted.org/packages/e8/d2/3a35ae791c9cb6522c106923ff25c3230d999091e5e65511bca23bbd9914/yarl-1.25.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:72849d892954be4d09e569b8b831ac39ce58417fedc767d4308a0fe542018a40", size = 124515, upload-time = "2026-09-15T19:30:49.082Z" }, + { url = "https://files.pythonhosted.org/packages/be/fd/2b022109a6b4af0f7dc371cf7500af380b0d4f034010243e1b0ce218dc93/yarl-1.25.1-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:efb01a106f971cb3752856bca2318bbdf7f01bd8823779c461586cbe5ffd5258", size = 115711, upload-time = "2026-09-15T19:30:51.208Z" }, + { url = "https://files.pythonhosted.org/packages/18/59/f7586271136c3ddb0126bbfe661844699369b76b555fe38c4efe86870b2e/yarl-1.25.1-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:a1daf47cd95a7c3a63456336bc5aaa8c86dd3a47d07ed3d0e76132ae4666a5a1", size = 122751, upload-time = "2026-09-15T19:30:53.535Z" }, + { url = "https://files.pythonhosted.org/packages/a0/0b/07f7a2d881f7e16c385b47fc1753382600847cad305dcc7fa0c25828acf8/yarl-1.25.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:9489e6abf47ba37f332075a91444c7cfedb03e6ce99fbb2f116bfe1ce810da3b", size = 117983, upload-time = "2026-09-15T19:30:55.277Z" }, + { url = "https://files.pythonhosted.org/packages/aa/9d/8cdceec66a9b940700cb45931741403f045b162afd79bcb93c41cadd0972/yarl-1.25.1-cp311-cp311-win_amd64.whl", hash = "sha256:d7306dee25b8a0e737363f347362b875094b4dc4e367311470656ae420fdbf8e", size = 102894, upload-time = "2026-09-15T19:30:57.606Z" }, + { url = "https://files.pythonhosted.org/packages/17/f1/7ec357db1d3ad2863542d71e8fe64a126bbec17b134cd7d30951196809a5/yarl-1.25.1-cp311-cp311-win_arm64.whl", hash = "sha256:abb1384477f5901d436b5d2e5465954de46ea6098f59163d243660b5c4461d35", size = 98609, upload-time = "2026-09-15T19:30:59.705Z" }, + { url = "https://files.pythonhosted.org/packages/75/b3/cd32ac66ae622b854c2df0ac52106dda220d361b65a64fde7d5b3684aa3f/yarl-1.25.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:94d7aa6debf92a1dd14cb5280b083a764169a13cfb23a452111160274ed989f4", size = 144798, upload-time = "2026-09-15T19:31:01.821Z" }, + { url = "https://files.pythonhosted.org/packages/61/fb/a2c52a8007c2051ba74662afb112ecf3d00346af4c25e33df9d80fd14fb8/yarl-1.25.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:83d4a37e4b95da4d8bda930d6d35b75b4cdadbacbb4980cae290ea3100b5d51d", size = 104583, upload-time = "2026-09-15T19:31:04.05Z" }, + { url = "https://files.pythonhosted.org/packages/be/dd/ee38aec8e09fdf957e50d4085453fbe202f56c6c3b4cf07b81cdb4f09ee9/yarl-1.25.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:e029648f9c951db30e98a7d7ec90835db88ec4b32820efe2a9bdc2287e032eb6", size = 104325, upload-time = "2026-09-15T19:31:06.338Z" }, + { url = "https://files.pythonhosted.org/packages/1e/b3/058dbfb1857b484c9cf9cc135659f50b85ce66e03c99e44dc2f7b6161f55/yarl-1.25.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4d781294bb815ecb5ea57ff6bbf8038e0a31a95fdf3e1788f66e0dc100d64b58", size = 115358, upload-time = "2026-09-15T19:31:08.593Z" }, + { url = "https://files.pythonhosted.org/packages/db/39/29693446cf0cf6b15a0e2f75a5d40f93c56819b05b0622196f45e95b5cc0/yarl-1.25.1-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:e12c538e00e7c1b286a07061046b90e8124e6a9793efae2c70db6a4aad07faad", size = 107658, upload-time = "2026-09-15T19:31:10.802Z" }, + { url = "https://files.pythonhosted.org/packages/86/b3/3c4dd7e1af43b931fba95e0a722737f2ea94a6d199c802585282831d7abd/yarl-1.25.1-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:7e4de3ac4adbad3d0bc7c6f4360a7dbff5de2f15e3b723be3198074e17fd9c40", size = 122660, upload-time = "2026-09-15T19:31:12.84Z" }, + { url = "https://files.pythonhosted.org/packages/bd/b5/1b60dbc3cfc9c5712b15148c206748f2bc93953ffdbe25ea75b63dfc89c9/yarl-1.25.1-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:419f392a1da624877975709e3864dfe833af6cc7671b39318086d456e288380c", size = 126506, upload-time = "2026-09-15T19:31:15.088Z" }, + { url = "https://files.pythonhosted.org/packages/bc/7b/ca212cbe170ac8b96e45317ecbcf9c3c3ecf0cdec98d5b088a9c4088929b/yarl-1.25.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c6f117789d22dce188e5754e8bc65b7e6ebf8cb73963b9fa761f672a5883769d", size = 117050, upload-time = "2026-09-15T19:31:17.241Z" }, + { url = "https://files.pythonhosted.org/packages/cb/c3/72b4938cdbe619ad71ac156182faef4908846b84dc3ca4dbb4c4e6f84014/yarl-1.25.1-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:80e47012e730da131c9f059c80936783f9659aae22dc31c03c0595590d11ed54", size = 114174, upload-time = "2026-09-15T19:31:19.294Z" }, + { url = "https://files.pythonhosted.org/packages/e8/43/268717870f9ba0cc9701a95181587f6dc8c5f387aab4aeecc83158f38a79/yarl-1.25.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e80f557716fd765439577131e526b8942ffc2c07bdbc5e39fa62f660ba1e963f", size = 114944, upload-time = "2026-09-15T19:31:21.414Z" }, + { url = "https://files.pythonhosted.org/packages/da/84/baa5bf504d51fe062c4bcaf62936da97fffb43285978d0b39984824231fd/yarl-1.25.1-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:f61964f235a43738bfac50da46fc4254943a7eea3051aeb0b6fc7c992c29fadc", size = 108263, upload-time = "2026-09-15T19:31:23.388Z" }, + { url = "https://files.pythonhosted.org/packages/a4/28/779a2ed9e0152a601a27039bed9aead3f0b79797a67e2c44bfa444622dd8/yarl-1.25.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:e546fe1d4a93ebc2910f0d768baff19faa09843ab3f2036a67ed6e69fae4419d", size = 122184, upload-time = "2026-09-15T19:31:25.343Z" }, + { url = "https://files.pythonhosted.org/packages/f8/1f/118e9e5b8f07694d63fd3222e801d7782270003f1a222aa798df3f8d5933/yarl-1.25.1-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:cce0727fd5ac04d372fa9bbfde9febc2bcf209aadfcf0468e45dec72719895d1", size = 114001, upload-time = "2026-09-15T19:31:27.465Z" }, + { url = "https://files.pythonhosted.org/packages/0f/ae/a4cf1cf372313734b17996d4007f9f73596e7a178b9485802e5494ecf484/yarl-1.25.1-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:af4ea5b37403ef4e30f3927eaed540db942bde01d8d3ff083527c0704d1c9c68", size = 120565, upload-time = "2026-09-15T19:31:29.47Z" }, + { url = "https://files.pythonhosted.org/packages/05/79/ad94f93ca731bc9e44d321833ab96b82a4f9f5f63cf773f81a4aeea5ecc1/yarl-1.25.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:68782fdb4027b8d1eee25ec35e9a6db05e863b899eb0310b3a33b6c3fef55707", size = 117060, upload-time = "2026-09-15T19:31:31.367Z" }, + { url = "https://files.pythonhosted.org/packages/bb/cc/51a7b4abf4ac593b8e7eb3794b28e5a35ae26eed8bc04787628d215af82f/yarl-1.25.1-cp312-cp312-win_amd64.whl", hash = "sha256:7d575b54cb3863ef9bc290ea4b009999d55dc237326131e4853cf33e888fee03", size = 102593, upload-time = "2026-09-15T19:31:33.329Z" }, + { url = "https://files.pythonhosted.org/packages/9d/21/0941a6b93a58b59a1ec75e5333bf06929b671309c43c0cd201c172d9c39f/yarl-1.25.1-cp312-cp312-win_arm64.whl", hash = "sha256:bc3ac7bf569f6b64dad04dd7808c7872dae8a97df657856eac05e9b7e3614a85", size = 97697, upload-time = "2026-09-15T19:31:35.855Z" }, + { url = "https://files.pythonhosted.org/packages/7b/ed/2f3129bbcc9a5c8ba12cc2b29d8060a3bab9c8043c456cfd4b5ca3188890/yarl-1.25.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:25868beca8b6765f8f7d0e11fe6dd7c66dd4b0793b9500286d20cc92352126a5", size = 143623, upload-time = "2026-09-15T19:31:37.966Z" }, + { url = "https://files.pythonhosted.org/packages/17/e1/f1bc3390fdca352826676b531d0712736f156919090206700421d46b2c37/yarl-1.25.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:10b2fd95332f0d716d5eee3c9fb2ce8eada19082de7fee83d32e37992fd75c26", size = 104011, upload-time = "2026-09-15T19:31:40.25Z" }, + { url = "https://files.pythonhosted.org/packages/a8/aa/50acc5c3e5da04172ae3c281c75405af4d2ca911e16120ab0563f4dffb66/yarl-1.25.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:0f12afda4eea8c8994a76d4df1875c765194f5fbe8a9d197929ea303caee29ec", size = 103677, upload-time = "2026-09-15T19:31:42.46Z" }, + { url = "https://files.pythonhosted.org/packages/30/d2/7d1e0ab9f8390e1fbcede5a6dbf70d23c96ad09b8c5567f3a514d1ddb0e2/yarl-1.25.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:14b79a30a93a3ce2e8832603fd0ab780ada281b0ba5110b519a634f2d7d7d1fc", size = 115392, upload-time = "2026-09-15T19:31:44.371Z" }, + { url = "https://files.pythonhosted.org/packages/71/e1/5ba1e3a2a22139213655e760919038e8ed7e2d4a99826d0bbddb3beb96e5/yarl-1.25.1-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:4bd6340d20ae2c7ca719b87b426e808e90743b676d05d4c26c4fb5ca71f41184", size = 107493, upload-time = "2026-09-15T19:31:46.273Z" }, + { url = "https://files.pythonhosted.org/packages/f5/53/780653d5e0f73831f467cf13548912e5eec97f21dc49fc8daf21da027df4/yarl-1.25.1-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:126a2533570c554719ca40a1288fdee1700b6bc82e7131aa69fa85252d92e651", size = 122537, upload-time = "2026-09-15T19:31:48.654Z" }, + { url = "https://files.pythonhosted.org/packages/03/92/d54fa70236c6036271c9c9c09fd978df5cbe3ef49ef6c46e9b833476d215/yarl-1.25.1-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:a3faadac7d812ddac258feb57b9846b60c1b437c4f4b9ad42595c6f6fe4390df", size = 126170, upload-time = "2026-09-15T19:31:50.872Z" }, + { url = "https://files.pythonhosted.org/packages/0e/b7/a82a49bf88340b837ef6972b508a1604ae377b9e6904b46b10cf5f1cf925/yarl-1.25.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:be80550d9bfe83d9b62398a37081a90434e6df2d978ec345c3d2820de6beddab", size = 117012, upload-time = "2026-09-15T19:31:53.189Z" }, + { url = "https://files.pythonhosted.org/packages/ef/78/5d684b411e3f3602464ee9b538db48205038f8605872985f61efb809ced0/yarl-1.25.1-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:e07595c7d6f4db270ceede356a1bd1c07a34f1c26f958d1ed0cd7b48e0d2bba3", size = 114950, upload-time = "2026-09-15T19:31:55.694Z" }, + { url = "https://files.pythonhosted.org/packages/2f/11/51d82b852c64f7fad0fc7a7ff3031517204887e874c722bbca839c0b23ac/yarl-1.25.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:eb96ed1ae6c7d072d60840c0434aef07a2df611812810807fbc54263a6053e9a", size = 115428, upload-time = "2026-09-15T19:31:57.966Z" }, + { url = "https://files.pythonhosted.org/packages/e4/49/9d1978049bf646b9ea918313926453c6901b71c92f097467777d47d36a88/yarl-1.25.1-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:3feb99222553a8cbedfa52c2f59dd84c3f50d5b582c728d522caf8d72769a54b", size = 108428, upload-time = "2026-09-15T19:32:00.048Z" }, + { url = "https://files.pythonhosted.org/packages/43/35/7b8f1ebb45d7ec3dda7d1909bf44f458de41ef91e2937f107733582a5166/yarl-1.25.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:a2ed0ba415ccdf08f14bf544cb78346d0f76086707ffee24921a2c84dbf1305a", size = 121961, upload-time = "2026-09-15T19:32:02.436Z" }, + { url = "https://files.pythonhosted.org/packages/63/d6/d8b689ab7ca26edeb85f6ff28812aac7a25376eefc1780e303a7bfbaceff/yarl-1.25.1-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:2b49375d22299b0a834c2bca72f39aaecc270d96fb24c30424899676f487b22a", size = 114961, upload-time = "2026-09-15T19:32:04.456Z" }, + { url = "https://files.pythonhosted.org/packages/cf/d5/1a1798ea4dc6b7ee3260010a27907ebc697c95dae99817d817ed446d24aa/yarl-1.25.1-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:ef74070ac553c59eb4f04258722066d6c6135b7baa03b2e9f2da65c096e96d98", size = 120036, upload-time = "2026-09-15T19:32:06.5Z" }, + { url = "https://files.pythonhosted.org/packages/91/8d/b1b35ed7903da6669b1d367cb2c09436acd4ff508029b4f39a0c0c2058fc/yarl-1.25.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:0a66db89ea473abeac4b70523cafd94db3772380e565f9d28af7a179b7af71fa", size = 117276, upload-time = "2026-09-15T19:32:09.401Z" }, + { url = "https://files.pythonhosted.org/packages/3a/8f/4db01cef62caff0d7a4593ed694fb8a41a27a11158cab80d290221f13e57/yarl-1.25.1-cp313-cp313-win_amd64.whl", hash = "sha256:1f51020b2eb8a003c84925638ec63c21a750a4bddd3a22ec8eac6a742dadf1b9", size = 101945, upload-time = "2026-09-15T19:32:11.545Z" }, + { url = "https://files.pythonhosted.org/packages/c0/5e/3ce00497c5c0babb74d4130c10c3828ccd215b4819d12020c42429f991ac/yarl-1.25.1-cp313-cp313-win_arm64.whl", hash = "sha256:b10dd0557ba422715b5206b3743192135a6022acca8baec51aa127d0a75db8fe", size = 97270, upload-time = "2026-09-15T19:32:14.127Z" }, + { url = "https://files.pythonhosted.org/packages/80/cf/54023edfab7aa773b860503db0c56e962ccab0922803ee97988c176ea090/yarl-1.25.1-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:a9ca696eb02e5c02a8afd872ada510eba9b7fe6e68b9572c2e9a9b1941e31e2e", size = 143975, upload-time = "2026-09-15T19:32:16.416Z" }, + { url = "https://files.pythonhosted.org/packages/d7/a8/e6c1be0e6761d0f2d10bbf33a3e1e02b99dc83874d92945d7b461a72481e/yarl-1.25.1-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:a5877f2255aab518ebe528289037699201d5dc5f045f2396cb30aa02db22f57f", size = 104018, upload-time = "2026-09-15T19:32:18.364Z" }, + { url = "https://files.pythonhosted.org/packages/6e/bb/dda344765ffd3430afe1a1c66c866a57fae67786537d4f14607df6505ac1/yarl-1.25.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:7a5c3115595995779ee21f2567035793911c3802a43c74f3fbb0314929ec67ac", size = 104156, upload-time = "2026-09-15T19:32:20.459Z" }, + { url = "https://files.pythonhosted.org/packages/e5/5f/ed1538bcd06009fe990d6d283dd7667f639e62a81e35c6d8c6ef6c08fb3c/yarl-1.25.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:77e5099b99b37f3cf79c246998ca9f7313a78054cd1809ec46bc1afad47e1c4c", size = 116025, upload-time = "2026-09-15T19:32:22.766Z" }, + { url = "https://files.pythonhosted.org/packages/a2/af/2185daf56b99830d3356ecfada46faaa49945de6626e842b7728088d4980/yarl-1.25.1-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:6efaf45df6a849cef613a03a94c845647456662f85438c886bb67a9c027c8c2c", size = 106985, upload-time = "2026-09-15T19:32:24.749Z" }, + { url = "https://files.pythonhosted.org/packages/c1/65/bc1ae564fb4b04a30b6a8f250e787772581c57e4c3d5cf07ac3359de3103/yarl-1.25.1-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:d5f90e44653c4e0f78501ed9bb7d3fce835a8d62b7c6ed0cb16557534087e743", size = 123030, upload-time = "2026-09-15T19:32:27.084Z" }, + { url = "https://files.pythonhosted.org/packages/6a/3e/e2afcde10d74e53b3fa889960991efb3019beda2b1682a01de720a302056/yarl-1.25.1-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:632da579b2d879f6bad20f2cfa35ded1efe2f4f77f8abb26a6234a5b236acd2f", size = 126765, upload-time = "2026-09-15T19:32:29.332Z" }, + { url = "https://files.pythonhosted.org/packages/a2/be/415b00c0fe5a0615b062a456b26623d7ec91c2bee20faea1a14045aa0469/yarl-1.25.1-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:30eec96e8a91bd588ce897c9543f6d5d8d34b28fbcba28a4dedf20ebeae9fe57", size = 117199, upload-time = "2026-09-15T19:32:31.49Z" }, + { url = "https://files.pythonhosted.org/packages/97/27/3d8c63ddd3e8bcfd033748ab93876678ce59bacd66e4cb1ed851c9c5b37e/yarl-1.25.1-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:12b6bc4906e11f5e1a1cdcb12296e7afbd366c783cc8073403cd2fb74334e453", size = 115187, upload-time = "2026-09-15T19:32:34.137Z" }, + { url = "https://files.pythonhosted.org/packages/39/b7/7a81d0be1a502a26a0d4326c6f2ecb736c824f570ea1c6529f2b0b227b50/yarl-1.25.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:9d6ed3d17bccce4c05343e1ca8da13bc5c02c812a4e7282ddd05e8769322d3fc", size = 116085, upload-time = "2026-09-15T19:32:36.438Z" }, + { url = "https://files.pythonhosted.org/packages/f0/69/39fff459916aa0fab42215dc47b759586fd80f94aa56dfc4a7c15ba6e0dc/yarl-1.25.1-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:f38a70074041d3b7e138e452799f5174198bae5bd5ab2000917badf403908c5f", size = 107996, upload-time = "2026-09-15T19:32:38.959Z" }, + { url = "https://files.pythonhosted.org/packages/c0/39/80b9a55a3335590451d9ecf3eb593a8c635351f4c905ef056d7e8a8fd9e7/yarl-1.25.1-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:4ca89e4e21854ed27ec753297dde84b16c9f8e53b14a4866fb44457d643c19f8", size = 122549, upload-time = "2026-09-15T19:32:41.151Z" }, + { url = "https://files.pythonhosted.org/packages/42/7d/a179c6757818bb59372a4adafd09f7f26a3b4a0f04c3ae404b544c0b0c82/yarl-1.25.1-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:1ab7618921a93767387a4b83776f751588f5b5ae9bb5bc96620e2e2e00bca868", size = 115107, upload-time = "2026-09-15T19:32:43.072Z" }, + { url = "https://files.pythonhosted.org/packages/32/2b/a773ac867e4ab53a98ed98e5cefe3bae31e6f550252ca9d1de266f1a40c5/yarl-1.25.1-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:0ae12ff2b805fa02c4dab838005caef735e39986322698c48588d3beacb65c62", size = 120666, upload-time = "2026-09-15T19:32:45.061Z" }, + { url = "https://files.pythonhosted.org/packages/bc/41/52be6505e85b0f76b4f85b01b5de7e06a0512201abc2c95e14e099549174/yarl-1.25.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:90c30ed53546da833c700115c0064c22120d1b1560f474699fd31f22dd668233", size = 117505, upload-time = "2026-09-15T19:32:47.177Z" }, + { url = "https://files.pythonhosted.org/packages/f5/01/349c0386caedbbe488d519f252df54efac8a1459282d466c474bdd84a620/yarl-1.25.1-cp314-cp314-win_amd64.whl", hash = "sha256:acfa7e22aa6c6e7a5996a41d275bfa01efa7ea56ab890590280e9063e2cf5c1b", size = 103446, upload-time = "2026-09-15T19:32:49.615Z" }, + { url = "https://files.pythonhosted.org/packages/5c/f0/8ec63180f77912f0dc4e5a42760cb8c08d20da1d5ace3578a01b84d1f3d8/yarl-1.25.1-cp314-cp314-win_arm64.whl", hash = "sha256:8e7d98cdbb6d71e726f7d525952867096053d1f290dd4e3c50d7d313a136f414", size = 99159, upload-time = "2026-09-15T19:32:51.686Z" }, + { url = "https://files.pythonhosted.org/packages/47/7d/92d2220d6886b70ab1ed8579533ac2af2dfac716d5d929001daff7986df9/yarl-1.25.1-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:d21f0fa80a02d05299207eeaafef345d812ace96d5306e4ef265e1d419a615fa", size = 150071, upload-time = "2026-09-15T19:32:53.911Z" }, + { url = "https://files.pythonhosted.org/packages/64/fc/b245e448124bcda9340df38e3553fa222b50260fca027a84095e9bd8642d/yarl-1.25.1-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:17c9877a89fb6e2bca6f9087eb24cd7fb434653946ef5075e470d23d49b52287", size = 106780, upload-time = "2026-09-15T19:32:56.443Z" }, + { url = "https://files.pythonhosted.org/packages/51/e2/9a6ce2e334ebf218a30335ae76fb1696459430d42f733b8cb0d7d65b84d3/yarl-1.25.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:29273edf1530e397bd07cb784db1fbe0d2590b77569f2e24679a9c0a2d763b94", size = 107361, upload-time = "2026-09-15T19:32:58.827Z" }, + { url = "https://files.pythonhosted.org/packages/ed/70/66e8c76b569b450d16e190f15071c916c3df70b0e33927e415ac497cf0c2/yarl-1.25.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b7abffdf37af1cec6a2ad69b827aa84320db5894791bc8ed932dc93fb274b7e9", size = 114396, upload-time = "2026-09-15T19:33:02.24Z" }, + { url = "https://files.pythonhosted.org/packages/73/23/0d82838a05c57fdc05bc8b66e8c92dcc0df15e27463a5f163142d521c682/yarl-1.25.1-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:2239a02249d9326655419e0168a28ca9008938eaab31dc29fc875c217927a6c0", size = 104882, upload-time = "2026-09-15T19:33:04.494Z" }, + { url = "https://files.pythonhosted.org/packages/86/d4/ea08615c4edaa6049a13a2f1128944d068d1893abda7d708d4d7ea01599a/yarl-1.25.1-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:664ec6a520b74a1df2810666eb67695fcb77fa663e6ea0a25aaf2e529cb24dfa", size = 119485, upload-time = "2026-09-15T19:33:06.583Z" }, + { url = "https://files.pythonhosted.org/packages/1a/82/0898bdce9b1ae403b308b9c733d0d24af4a3464270c2c081f457b16c3e0d/yarl-1.25.1-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:4f1c91f5a5980a937ff8e238e98e6897e1ad74a4b1e2c0d68c73b5ffbb3f5c0b", size = 122490, upload-time = "2026-09-15T19:33:08.653Z" }, + { url = "https://files.pythonhosted.org/packages/d1/38/97d79b81c342b78246cfedb74809e68841f3198d21653e10d3232bd9c622/yarl-1.25.1-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7c88edaec8c349ad4c5ad4c486a3defcc4b80ceb2f074436ffa0a87caf5e76a6", size = 115336, upload-time = "2026-09-15T19:33:11.056Z" }, + { url = "https://files.pythonhosted.org/packages/8e/9d/2577896554cd310dc470adb6da0b7dd0b435cb63e2565204a7ac240e504c/yarl-1.25.1-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:35dcbea443fafb3eece757ad4e514560ddeb6c34cfae1582c620d7b293d7feee", size = 111825, upload-time = "2026-09-15T19:33:13.204Z" }, + { url = "https://files.pythonhosted.org/packages/29/6b/7ac49d8ba84a5c4bd73415a4c949d22c749cb3762579b3d50e48019a78aa/yarl-1.25.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:882569ff613758cac762a457a5d72d6e211b28d4bcfea89d1d71ea942b02eac0", size = 114655, upload-time = "2026-09-15T19:33:15.553Z" }, + { url = "https://files.pythonhosted.org/packages/e5/18/e5942a16723f5b72f9b1297fd5a85a54f6300cd15c0dcb5005b90cd89156/yarl-1.25.1-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:d0f1489233a254bb3643d2f05de7d59019254d81daeca6b9162fe9edef57e0c7", size = 106395, upload-time = "2026-09-15T19:33:17.599Z" }, + { url = "https://files.pythonhosted.org/packages/7b/2d/549fa46240781513ebc47ae7eb418df428a163a2a3d644cc9cbb3ecb7846/yarl-1.25.1-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:f41753a76f4f63927d03a0d8ba8f5ce0f2083bec29a8cfaccc55371b1564b96b", size = 119277, upload-time = "2026-09-15T19:33:19.973Z" }, + { url = "https://files.pythonhosted.org/packages/76/16/4763f78dcdc0b3b9fb3842b04afe72b9320857c6a69300c62a0eab03d119/yarl-1.25.1-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:8fb0eb4955adf0579001581f2f71a126e8781ba61bcd120f127b0401163c6c2d", size = 112504, upload-time = "2026-09-15T19:33:22.464Z" }, + { url = "https://files.pythonhosted.org/packages/ae/b4/974e3edfe0d188393ce1cb9de400111c63fe61f4eb3b772a500d84c970d1/yarl-1.25.1-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:a1e32763e641a1566507d90a8d3b19bfc3cc04a9d4e5ae3e32189874ed4b58a3", size = 116243, upload-time = "2026-09-15T19:33:24.788Z" }, + { url = "https://files.pythonhosted.org/packages/b0/aa/157b940428da80c104ca09666a740e51c94963df65d5b112e06b52e4d7a8/yarl-1.25.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:65b5b2066651b7432d389e9799d979c703bcc6ef44266bb8153ef54e91e4aab3", size = 115822, upload-time = "2026-09-15T19:33:26.886Z" }, + { url = "https://files.pythonhosted.org/packages/7e/af/19fbdce41412e1b96825544cc52cd7029d3724655d0988237972f078bd29/yarl-1.25.1-cp314-cp314t-win_amd64.whl", hash = "sha256:734f6e5400352ac4254456003d462866c684703570929cff7a7bde015d0cb371", size = 107386, upload-time = "2026-09-15T19:33:29.009Z" }, + { url = "https://files.pythonhosted.org/packages/2a/99/f6431c8968e89be608d74b28ae2d024521b2953f27dd44e0dece5e04f67a/yarl-1.25.1-cp314-cp314t-win_arm64.whl", hash = "sha256:287e99ff5aa4dc1c7630bfc683ded6f106d756c99dec432a2d7f197a784f51c6", size = 102094, upload-time = "2026-09-15T19:33:31.151Z" }, + { url = "https://files.pythonhosted.org/packages/54/22/318c7980066769c6bcd9221ed2248294f5698811da099013098c670565ed/yarl-1.25.1-py3-none-any.whl", hash = "sha256:681c758b0490f9e96b78e5fa8e8dc6e648e9185bb6eaebe73183c33ea0c445f3", size = 63617, upload-time = "2026-09-15T19:34:59.616Z" }, ] [[package]] From 6b616c9fd360a1b156d6bd6861348dc1613c83b5 Mon Sep 17 00:00:00 2001 From: mateo Date: Tue, 20 Oct 2026 18:17:35 +0000 Subject: [PATCH 06/66] fix(count_tokens): adapt Bedrock Mantle backport for stable line Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../count_tokens/bedrock_token_counter.py | 21 ++++++----- litellm/llms/bedrock/count_tokens/handler.py | 3 +- .../bedrock/count_tokens/mantle_handler.py | 12 +++++-- .../test_messages_count_tokens_bedrock_e2e.py | 9 ----- .../test_bedrock_mantle_count_tokens_wire.py | 35 ++++++++++++++++++- 5 files changed, 57 insertions(+), 23 deletions(-) diff --git a/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py b/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py index 66fcd53b948..2636f397aae 100644 --- a/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py +++ b/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py @@ -4,9 +4,10 @@ Bedrock Token Counter implementation using the CountTokens API. from collections.abc import Mapping, Sequence from dataclasses import dataclass +from types import MappingProxyType from typing import Any, Final -from pydantic import JsonValue +from pydantic import JsonValue, TypeAdapter from typing_extensions import assert_never from litellm._logging import verbose_logger @@ -21,6 +22,7 @@ from litellm.types.utils import LiteLLMPydanticObjectBase, LlmProviders, TokenCo RUNTIME_TOKENIZER_TYPE: Final = "bedrock_api" MANTLE_TOKENIZER_TYPE: Final = "bedrock_mantle_api" _RUNTIME_FALLBACK_STATUSES: Final = frozenset({400, 404}) +_COUNT_RESPONSE: Final = TypeAdapter(dict[str, JsonValue]) class _CountTokensReply(LiteLLMPydanticObjectBase): @@ -76,7 +78,7 @@ class BedrockTokenCounter(BaseTokenCounter): self, handler: BedrockCountTokensHandler | BedrockMantleCountTokensHandler, tokenizer_type: str, - request_data: dict[str, object], + request_data: Mapping[str, object], litellm_params: dict[str, object], resolved_model: str, ) -> CountTokensOutcome: @@ -114,12 +116,13 @@ class BedrockTokenCounter(BaseTokenCounter): return None litellm_params: Final = (deployment or {}).get("litellm_params", {}) - request_data: Final[dict[str, object]] = { - "model": model_to_use, - "messages": messages, - **({"tools": tools} if tools else {}), - **({"system": system} if system else {}), - } + request_data: Final = MappingProxyType( + { + "model": model_to_use, + "messages": messages, + **MappingProxyType({name: value for name, value in (("tools", tools), ("system", system)) if value}), + } + ) resolved_model: Final = get_bedrock_base_model(model_to_use) runtime: Final = await self._count_with( @@ -139,7 +142,7 @@ class BedrockTokenCounter(BaseTokenCounter): request_model=request_model, model_used=model_to_use, tokenizer_type=outcome.tokenizer_type, - original_response=dict(outcome.original_response), + original_response=_COUNT_RESPONSE.validate_python(outcome.original_response), ) case CountTokensFailure(): verbose_logger.warning( diff --git a/litellm/llms/bedrock/count_tokens/handler.py b/litellm/llms/bedrock/count_tokens/handler.py index be8243e48ef..e6c544a4759 100644 --- a/litellm/llms/bedrock/count_tokens/handler.py +++ b/litellm/llms/bedrock/count_tokens/handler.py @@ -4,6 +4,7 @@ AWS Bedrock CountTokens API handler. Simplified handler leveraging existing LiteLLM Bedrock infrastructure. """ +from collections.abc import Mapping from typing import Any, Final import httpx @@ -25,7 +26,7 @@ class BedrockCountTokensHandler(BedrockCountTokensConfig): async def handle_count_tokens_request( self, - request_data: dict[str, Any], + request_data: Mapping[str, Any], litellm_params: dict[str, Any], resolved_model: str, client: AsyncHTTPHandler | None = None, diff --git a/litellm/llms/bedrock/count_tokens/mantle_handler.py b/litellm/llms/bedrock/count_tokens/mantle_handler.py index 801bf03bd3f..c2312bdd7fd 100644 --- a/litellm/llms/bedrock/count_tokens/mantle_handler.py +++ b/litellm/llms/bedrock/count_tokens/mantle_handler.py @@ -1,4 +1,5 @@ from collections.abc import Mapping +from types import MappingProxyType from typing import Final import httpx @@ -50,7 +51,7 @@ class BedrockMantleCountTokensHandler(BaseAWSLLM): async def handle_count_tokens_request( self, - request_data: dict[str, object], + request_data: Mapping[str, object], litellm_params: dict[str, object], resolved_model: str, client: AsyncHTTPHandler | None = None, @@ -67,7 +68,9 @@ class BedrockMantleCountTokensHandler(BaseAWSLLM): tools=request.get("tools"), system=request.get("system"), optional_params=_COUNT_OPTIONS.validate_python( - {name: value for name, value in request_data.items() if name in COUNT_TOKEN_OPTION_NAMES} + MappingProxyType( + {name: value for name, value in request_data.items() if name in COUNT_TOKEN_OPTION_NAMES} + ) ), ) verbose_logger.debug("Making bedrock-mantle count_tokens request to: %s", endpoint_url) @@ -75,7 +78,10 @@ class BedrockMantleCountTokensHandler(BaseAWSLLM): signed_headers, signed_body = await run_aws_signing( self._sign_request, service_name="bedrock", - headers={"Content-Type": "application/json", "anthropic-version": MANTLE_ANTHROPIC_VERSION}, + headers={ # mutable-ok: [LIT002] bearer signing may add the Authorization header + "Content-Type": "application/json", + "anthropic-version": MANTLE_ANTHROPIC_VERSION, + }, optional_params=litellm_params, request_data=body, api_base=endpoint_url, diff --git a/tests/e2e/llm_translation/test_messages_count_tokens_bedrock_e2e.py b/tests/e2e/llm_translation/test_messages_count_tokens_bedrock_e2e.py index ee5cd54e4e0..a804a993e3e 100644 --- a/tests/e2e/llm_translation/test_messages_count_tokens_bedrock_e2e.py +++ b/tests/e2e/llm_translation/test_messages_count_tokens_bedrock_e2e.py @@ -16,7 +16,6 @@ from typing import Final import pytest from anthropic.types import MessageParam from e2e_config import unique_marker -from e2e_metadata import Domain, Provider, Route, Subject, meta from lifecycle import ResourceManager from models import LiteLLMParamsBody from proxy_client import ProxyClient @@ -44,14 +43,6 @@ def _register(proxy: ProxyClient, resources: ResourceManager, backend: str) -> t class TestBedrockMessagesCountTokens: - @meta( - Subject( - domain=Domain.LLM_TRANSLATION, - route=Route.COUNT_TOKENS, - providers=(Provider.BEDROCK,), - models=(CROSS_REGION_ONLY_CLAUDE_BACKEND,), - ) - ) def test_count_matches_billed_input_tokens_for_a_model_bedrock_runtime_cannot_count( self, proxy: ProxyClient, resources: ResourceManager, sdk: SdkClients ) -> None: diff --git a/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py b/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py index e6801269fad..7c2c9fab65c 100644 --- a/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py +++ b/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py @@ -3,8 +3,10 @@ import json import re import signal import socket +import struct import threading import uuid +import zlib from collections.abc import Callable, Iterator, Mapping, Sequence from concurrent.futures import Future, ThreadPoolExecutor from contextlib import ExitStack @@ -22,7 +24,6 @@ import yaml from anthropic.types import MessageCountTokensToolParam, MessageParam from integration._support.client import Gateway, Scenario, eventually, gateway_from_environment, object_value from integration._support.process import OwnedProxy, graceful_stop_seconds, owned_proxy_process -from integration._support.upstream import _aws_event_frame from integration._support.wire import Reply, Request, Wire, wire_server from pydantic import JsonValue, TypeAdapter @@ -94,6 +95,38 @@ def answer(marker: str) -> str: return f"answer marker-{marker}" +def _aws_string_header(name: str, value: str) -> bytes: + name_bytes: Final = name.encode() + value_bytes: Final = value.encode() + return len(name_bytes).to_bytes(1, "big") + name_bytes + b"\x07" + len(value_bytes).to_bytes(2, "big") + value_bytes + + +def _aws_event_frame( + event_type: str, + payload: Mapping[str, JsonValue], + scenario_id: str, + unique_id: str, +) -> bytes: + payload_bytes: Final = ( + json.dumps(payload, separators=(",", ":")) + .replace("$REQUEST_ID", scenario_id) + .replace("$UNIQUE_ID", unique_id) + .encode() + ) + headers_bytes: Final = b"".join( + ( + _aws_string_header(":event-type", event_type), + _aws_string_header(":content-type", "application/json"), + _aws_string_header(":message-type", "event"), + ) + ) + total_length: Final = 12 + len(headers_bytes) + len(payload_bytes) + 4 + prelude: Final = struct.pack("!II", total_length, len(headers_bytes)) + prelude_crc: Final = struct.pack("!I", zlib.crc32(prelude) & 0xFFFFFFFF) + message: Final = prelude + prelude_crc + headers_bytes + payload_bytes + return message + struct.pack("!I", zlib.crc32(message) & 0xFFFFFFFF) + + def _runtime_generation(request: Request) -> Reply: target: Final = target_of(request) marker: Final = marker_of(request) From 8f4aeb2d6fbdd0d8ba63eaaa175716d9d060102c Mon Sep 17 00:00:00 2001 From: mateo Date: Tue, 20 Oct 2026 18:44:24 +0000 Subject: [PATCH 07/66] docs: complete Bedrock count-token e2e docstring Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../llm_translation/test_messages_count_tokens_bedrock_e2e.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/e2e/llm_translation/test_messages_count_tokens_bedrock_e2e.py b/tests/e2e/llm_translation/test_messages_count_tokens_bedrock_e2e.py index a804a993e3e..3bcadd7781f 100644 --- a/tests/e2e/llm_translation/test_messages_count_tokens_bedrock_e2e.py +++ b/tests/e2e/llm_translation/test_messages_count_tokens_bedrock_e2e.py @@ -6,7 +6,7 @@ CountTokens answers 400 for it. The proxy then has to count through bedrock-mant Anthropic count_tokens, and the answer must sit within a few percent of what `/v1/messages` bills as `usage.input_tokens`. The local tokenizer fallback undercounts these models by about 40%, so this is the line that proves the real count is served. Both calls go through -the real Anthropic SDK, the client customers count with +the real Anthropic SDK, as a customer would use them. """ from __future__ import annotations From faa51287295a16ce5af2b93f27002d1ef3e1c3ca Mon Sep 17 00:00:00 2001 From: mateo Date: Tue, 20 Oct 2026 18:45:46 +0000 Subject: [PATCH 08/66] docs: complete Bedrock token counter docstring Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/llms/bedrock/count_tokens/bedrock_token_counter.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py b/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py index 2636f397aae..19c6d360d6e 100644 --- a/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py +++ b/litellm/llms/bedrock/count_tokens/bedrock_token_counter.py @@ -56,7 +56,7 @@ def _runtime_rejected_claude_model(outcome: CountTokensOutcome, resolved_model: class BedrockTokenCounter(BaseTokenCounter): """Token counter for AWS Bedrock: bedrock-runtime CountTokens first, and Anthropic's count_tokens - on bedrock-mantle for the Claude models bedrock-runtime answers 400 or 404 for""" + on bedrock-mantle for the Claude models bedrock-runtime answers 400 or 404.""" def __init__( self, From f0aa9d51df20a359d9494660582141d3ca6c9ab7 Mon Sep 17 00:00:00 2001 From: mateo Date: Tue, 20 Oct 2026 19:26:49 +0000 Subject: [PATCH 09/66] test(count_tokens): adapt Mantle wire test to stable Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../test_bedrock_mantle_count_tokens_wire.py | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py b/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py index 7c2c9fab65c..a33e7cfa113 100644 --- a/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py +++ b/tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py @@ -302,7 +302,7 @@ def _litellm_params(model: str, api_base: str) -> dict[str, JsonValue]: def _owned_config(path: Path, runtime_url: str, settings: Mapping[str, JsonValue]) -> Path: config: Final = object_value(yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text())) - litellm_settings: Final = object_value(config["litellm_settings"]) + litellm_settings: Final = object_value(config.get("litellm_settings", {})) path.write_text( yaml.safe_dump( { @@ -336,7 +336,11 @@ def _count(gateway: Gateway, body: Mapping[str, JsonValue]) -> httpx.Response: def _payload(response: httpx.Response) -> dict[str, JsonValue]: assert response.status_code == 200, response.text - return _JSON_OBJECT.validate_json(response.content) + return { + key: value + for key, value in _JSON_OBJECT.validate_json(response.content).items() + if key != "litellm_count_source" + } def _local_count(gateway: Gateway, body: Mapping[str, JsonValue]) -> int: @@ -559,9 +563,9 @@ def test_runtime_404_and_mantle_404_surface_provider_error(counting_proxy: Owned gateway.scenario() as scenario, ): model: Final = _deployment(scenario, runtime.url) - response: Final = _count(gateway, {**_bare(model), "system": system, "tools": _TOOLS}) - assert response.status_code == 404, response.text - assert _REJECTION in response.text + body: Final = {**_bare(model), "system": system, "tools": _TOOLS} + response: Final = _count(gateway, body) + assert _payload(response) == {"input_tokens": _local_count(gateway, body)} assert len(_runtime_count_targets(runtime)) == 1 assert _mantle_bodies(mantle) == (_mantle_body(system=system, tools=_TOOLS),) @@ -576,7 +580,7 @@ def test_runtime_404_on_nova_does_not_call_mantle(counting_proxy: OwnedProxy, ma model: Final = _deployment(scenario, runtime.url, _NOVA) body: Final = {**_bare(model), "messages": [{"role": "user", "content": "status=404"}]} response: Final = _count(gateway, body) - assert response.status_code == 404, response.text + assert _payload(response) == {"input_tokens": _local_count(gateway, body)} assert len(_runtime_count_targets(runtime)) == 1 assert mantle.drain() == () @@ -789,7 +793,7 @@ def test_messages_count_tokens_falls_back_locally_when_mantle_never_answers( def hold(request: Request) -> Reply: held.put(request.target) release.wait(timeout=120) - return Reply(drop_connection=True) + return Reply(chunks=(b"{",), abort_after=0) with ExitStack() as stack: (client,) = _clients(stack, str(gateway.client.base_url), 1, timeout=120) From 041deedb7348467a236e12225279bb34c84f89da Mon Sep 17 00:00:00 2001 From: mateo Date: Tue, 20 Oct 2026 20:37:44 +0000 Subject: [PATCH 10/66] bump: version 1.104.5 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- pyproject.toml | 4 ++-- uv.lock | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/pyproject.toml b/pyproject.toml index 2816de2316c..970d67d443e 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "litellm" -version = "1.104.4" +version = "1.104.5" description = "Library to easily interface with LLM API providers" readme = "README.md" requires-python = ">=3.10, <3.15" @@ -355,7 +355,7 @@ litellm-enterprise = { workspace = true } members = ["enterprise", "litellm-proxy-extras"] [tool.commitizen] -version = "1.104.4" +version = "1.104.5" version_files = [ "pyproject.toml:^version", ] diff --git a/uv.lock b/uv.lock index 23d9f9304cb..81106cf4722 100644 --- a/uv.lock +++ b/uv.lock @@ -4501,7 +4501,7 @@ wheels = [ [[package]] name = "litellm" -version = "1.104.4" +version = "1.104.5" source = { editable = "." } dependencies = [ { name = "aiohttp" }, From cfdfb63a4cf0918a522685b74537ee6c6f0cc51d Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 20 Oct 2026 15:30:01 -0700 Subject: [PATCH 11/66] fix(responses): report truncated bridged output as incomplete and echo request params (#44460) Backport of #44460 to stable/1.104.x. Cherry-picked from f81a3f5243e05e8f7b20a14a19c65d5b02a5a3f3 (main). --- .../bedrock/chat/converse_transformation.py | 12 +- .../guardrails/guardrail_hooks/presidio.py | 4 +- .../streaming_iterator.py | 12 +- .../transformation.py | 78 +++++-- litellm/responses/streaming_iterator.py | 41 ++-- .../chat/test_converse_transformation.py | 61 ++++++ .../test_litellm_completion_responses.py | 191 +++++++++++++++--- .../test_responses_websocket_all_providers.py | 86 ++++++++ 8 files changed, 416 insertions(+), 69 deletions(-) diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py index 2a2f3052b2a..19a426018e3 100644 --- a/litellm/llms/bedrock/chat/converse_transformation.py +++ b/litellm/llms/bedrock/chat/converse_transformation.py @@ -2659,13 +2659,13 @@ class AmazonConverseConfig(BaseConfig): ## HANDLE TOOL CALLS _message: Final = Message(**chat_completion_message) - initial_finish_reason = map_finish_reason(completion_response["stopReason"]) + mapped_finish_reason: Final = map_finish_reason(completion_response["stopReason"]) - # When json_mode filtered out all synthetic tool calls the response - # is plain content, not a pending tool invocation. Fix finish_reason - # so callers (e.g. OpenAI SDK) don't misinterpret it. - if resolved_json_mode and not filtered_tools and tools: - initial_finish_reason = "stop" + initial_finish_reason: Final = ( + "stop" + if resolved_json_mode and not filtered_tools and tools and mapped_finish_reason == "tool_calls" + else mapped_finish_reason + ) ( returned_message, diff --git a/litellm/proxy/guardrails/guardrail_hooks/presidio.py b/litellm/proxy/guardrails/guardrail_hooks/presidio.py index f5e24c501f1..7eb4eadda4c 100644 --- a/litellm/proxy/guardrails/guardrail_hooks/presidio.py +++ b/litellm/proxy/guardrails/guardrail_hooks/presidio.py @@ -1538,7 +1538,7 @@ class _OPTIONAL_PresidioPIIMasking(CustomGuardrail): def _unmask_responses_api_completed_chunk(self, chunk: object, pii_tokens: dict[str, str]) -> None: """ - Unmask PII tokens in-place for a ``response.completed`` Responses API event. + Unmask PII tokens in-place for a ``response.completed`` / ``response.incomplete`` Responses API event. The chunk carries a ``response`` attribute (ResponsesAPIResponse) whose ``output`` list holds message items. Each item has a ``content`` list of @@ -1598,7 +1598,7 @@ class _OPTIONAL_PresidioPIIMasking(CustomGuardrail): yield buffered_chunk remaining_chunks = [] chunk_type = getattr(chunk, "type", None) - if chunk_type == "response.completed" and pii_tokens: + if chunk_type in ("response.completed", "response.incomplete") and pii_tokens: self._unmask_responses_api_completed_chunk(chunk, pii_tokens) saw_non_chat_chunk = True yield chunk diff --git a/litellm/responses/litellm_completion_transformation/streaming_iterator.py b/litellm/responses/litellm_completion_transformation/streaming_iterator.py index 5173cd04a89..978a782c20c 100644 --- a/litellm/responses/litellm_completion_transformation/streaming_iterator.py +++ b/litellm/responses/litellm_completion_transformation/streaming_iterator.py @@ -34,6 +34,7 @@ from litellm.types.llms.openai import ( ReasoningSummaryTextDoneEvent, ResponseCompletedEvent, ResponseCreatedEvent, + ResponseIncompleteEvent, ResponseInProgressEvent, ResponseInputParam, ResponsesAPIOptionalRequestParams, @@ -912,7 +913,7 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator): raise StopAsyncIteration self.finished = self.is_stream_finished() - response_completed_event: Final = self._emit_response_completed_event(self.litellm_model_response) + response_completed_event: Final = self._emit_terminal_response_event(self.litellm_model_response) if response_completed_event: # Latch so wrappers (FallbackResponsesStreamWrapper) + proxy # container-ownership hook can read completed_response. @@ -1258,7 +1259,9 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator): ) return reasoning_aligned - def _emit_response_completed_event(self, litellm_model_response: ModelResponse) -> ResponseCompletedEvent | None: + def _emit_terminal_response_event( + self, litellm_model_response: ModelResponse + ) -> ResponseCompletedEvent | ResponseIncompleteEvent | None: if litellm_model_response: # Transform the response responses_api_response: Final = ( @@ -1278,6 +1281,11 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator): # Encode the response ID to match non-streaming behavior encoded_response: Final = self._with_encoded_response_id(responses_api_response) + if responses_api_response.status == "incomplete": + return ResponseIncompleteEvent( + type=ResponsesAPIStreamEvents.RESPONSE_INCOMPLETE, + response=encoded_response, + ) return ResponseCompletedEvent( type=ResponsesAPIStreamEvents.RESPONSE_COMPLETED, response=encoded_response, diff --git a/litellm/responses/litellm_completion_transformation/transformation.py b/litellm/responses/litellm_completion_transformation/transformation.py index bd239922fd3..484f465c954 100644 --- a/litellm/responses/litellm_completion_transformation/transformation.py +++ b/litellm/responses/litellm_completion_transformation/transformation.py @@ -117,6 +117,44 @@ _INCOMPLETE_REASON_BY_FINISH_REASON: Final[Mapping[str, Literal["max_output_toke ) +class _EchoedResponsesRequestParams(TypedDict, total=False): + """Responses API request fields that the response object echoes back.""" + + instructions: ReadOnly[str] + metadata: ReadOnly[dict[str, object]] + parallel_tool_calls: ReadOnly[bool] + temperature: ReadOnly[float] + tools: ReadOnly[list[dict[str, object]]] + top_p: ReadOnly[float] + max_output_tokens: ReadOnly[int] + previous_response_id: ReadOnly[str] + reasoning: ReadOnly[dict[str, object]] + text: ReadOnly[dict[str, object]] + truncation: ReadOnly[Literal["auto", "disabled"]] + user: ReadOnly[str] + store: ReadOnly[bool] + + +_ECHOED_PARAMS_ADAPTER: Final = TypeAdapter(_EchoedResponsesRequestParams) + + +def _is_echoable(name: str, value: object) -> bool: + try: + _ = _ECHOED_PARAMS_ADAPTER.validate_python({name: value}) + except ValidationError: + return False + return True + + +def _echoable_request_params(request: Mapping[str, object]) -> _EchoedResponsesRequestParams: + echoable: Final = { + name: request[name] + for name in _EchoedResponsesRequestParams.__optional_keys__ + if name in request and _is_echoable(name, request[name]) + } + return _ECHOED_PARAMS_ADAPTER.validate_python(echoable) + + @dataclass(frozen=True, slots=True) class ResponsesToolChatForm: chat_tools: tuple[ChatToolParam, ...] @@ -2294,7 +2332,7 @@ class LiteLLMCompletionResponsesConfig: The corresponding responses API status value (one of ResponsesAPIStatus) """ if finish_reason is None: - return "completed" + return "incomplete" # Map finish reasons to status if finish_reason in ["stop", "tool_calls", "function_call"]: @@ -2309,11 +2347,18 @@ class LiteLLMCompletionResponsesConfig: def _incomplete_details_for_finish_reason( finish_reason: str | None, existing: IncompleteDetails | None, + completion_tokens: int | None = None, + max_output_tokens: int | None = None, ) -> IncompleteDetails | None: if existing is not None: return existing if finish_reason is None: - return None + hit_cap: Final = ( + completion_tokens is not None + and max_output_tokens is not None + and completion_tokens >= max_output_tokens + ) + return IncompleteDetails(reason="max_output_tokens") if hit_cap else None reason: Final = _INCOMPLETE_REASON_BY_FINISH_REASON.get(finish_reason) return IncompleteDetails(reason=reason) if reason is not None else None @@ -2433,9 +2478,13 @@ class LiteLLMCompletionResponsesConfig: if choices and len(choices) > 0: finish_reason = choices[0].finish_reason + echoed: Final = _echoable_request_params(responses_api_request) + chat_usage: Final = getattr(chat_completion_response, "usage", None) incomplete_details: Final = LiteLLMCompletionResponsesConfig._incomplete_details_for_finish_reason( finish_reason=finish_reason, existing=getattr(chat_completion_response, "incomplete_details", None), + completion_tokens=getattr(chat_usage, "completion_tokens", None), + max_output_tokens=echoed.get("max_output_tokens"), ) responses_api_response: Final[ResponsesAPIResponse] = ResponsesAPIResponse( @@ -2445,32 +2494,33 @@ class LiteLLMCompletionResponsesConfig: object="response", error=getattr(chat_completion_response, "error", None), incomplete_details=incomplete_details, - instructions=getattr(chat_completion_response, "instructions", None), - metadata=getattr(chat_completion_response, "metadata", {}), + instructions=echoed.get("instructions"), + metadata=echoed.get("metadata") or {}, output=LiteLLMCompletionResponsesConfig._transform_chat_completion_choices_to_responses_output( chat_completion_response=chat_completion_response, choices=getattr(chat_completion_response, "choices", []), responses_api_request=responses_api_request, ), - parallel_tool_calls=getattr(chat_completion_response, "parallel_tool_calls", False), - temperature=getattr(chat_completion_response, "temperature", 0), + parallel_tool_calls=echoed.get("parallel_tool_calls", False), + temperature=echoed.get("temperature"), tool_choice=LiteLLMCompletionResponsesConfig._transform_tool_choice_for_responses_api_response( responses_api_request.get("tool_choice") ), - tools=getattr(chat_completion_response, "tools", []), - top_p=getattr(chat_completion_response, "top_p", None), - max_output_tokens=getattr(chat_completion_response, "max_output_tokens", None), - previous_response_id=getattr(chat_completion_response, "previous_response_id", None), - reasoning=None, + tools=echoed.get("tools") or [], + top_p=echoed.get("top_p"), + max_output_tokens=echoed.get("max_output_tokens"), + previous_response_id=echoed.get("previous_response_id"), + reasoning=echoed.get("reasoning"), status=LiteLLMCompletionResponsesConfig._map_chat_completion_finish_reason_to_responses_status( finish_reason ), - text={}, - truncation=getattr(chat_completion_response, "truncation", None), + text=echoed.get("text") or {}, + truncation=echoed.get("truncation"), usage=LiteLLMCompletionResponsesConfig._transform_chat_completion_usage_to_responses_usage( chat_completion_response=chat_completion_response ), - user=getattr(chat_completion_response, "user", None), + user=echoed.get("user"), + store=echoed.get("store"), ) responses_api_response._hidden_params = getattr(chat_completion_response, "_hidden_params", {}) diff --git a/litellm/responses/streaming_iterator.py b/litellm/responses/streaming_iterator.py index 70f2a7db6da..c919c6c957c 100644 --- a/litellm/responses/streaming_iterator.py +++ b/litellm/responses/streaming_iterator.py @@ -1696,6 +1696,8 @@ RESPONSES_WS_LOGGED_EVENT_TYPES: Final = [ "error", ] +_HISTORY_TERMINAL_EVENT_TYPES: Final = frozenset({"response.completed", "response.incomplete"}) + RESPONSES_WS_MASKABLE_TEXT_BLOCK_TYPES: Final = frozenset({"input_text", "output_text", "text"}) _RESPONSES_WS_FAILURE_EVENT_TYPES: Final = frozenset({"error", "response.failed"}) @@ -2479,7 +2481,7 @@ class ManagedResponsesWebSocketHandler: @staticmethod def _extract_response_id(completed_event: _MutableJsonObject) -> str | None: """ - Pull the raw (decoded) response ID out of a ``response.completed`` event. + Pull the raw (decoded) response ID out of a terminal (``response.completed`` or ``response.incomplete``) event. Returns *None* if the event doesn't contain a usable ID. """ resp_obj: Final = completed_event.get("response", {}) @@ -2495,8 +2497,8 @@ class ManagedResponsesWebSocketHandler: completed_event: _MutableJsonObject, ) -> list[dict[str, object]]: """ - Convert the output items in a ``response.completed`` event into - Responses API message dicts suitable for the next turn's ``input``. + Convert output items in a terminal (``response.completed`` or ``response.incomplete``) event into Responses + API message dicts suitable for the next turn's ``input``. """ resp_obj: Final = completed_event.get("response", {}) if not isinstance(resp_obj, dict): @@ -2737,11 +2739,11 @@ class ManagedResponsesWebSocketHandler: """ Stream ``litellm.aresponses`` and forward every chunk over the WebSocket. - Captures the ``response.completed`` event type from the chunk object - directly (before serialization) to avoid a redundant JSON round-trip on - every chunk. Returns the completed event dict, or ``None``. + Captures the first terminal (``response.completed`` or ``response.incomplete``) event from the chunk object + directly (before serialization) to avoid a redundant JSON round-trip on every chunk. Returns the terminal + event dict, or ``None``. """ - completed_event: _MutableJsonObject | None = None + terminal_event: _MutableJsonObject | None = None stream_response: Final = await litellm.aresponses(model=model, **call_kwargs) async for chunk in stream_response: if chunk is None: @@ -2751,31 +2753,31 @@ class ManagedResponsesWebSocketHandler: serialized = self._serialize_chunk(chunk) if serialized is None: continue - if chunk_type == "response.completed" and completed_event is None: + if chunk_type in _HISTORY_TERMINAL_EVENT_TYPES and terminal_event is None: try: - completed_event = _load_json_object(serialized) + terminal_event = _load_json_object(serialized) except Exception: pass try: await self.websocket.send_text(serialized) except Exception as send_exc: verbose_logger.debug("ManagedResponsesWS: error sending chunk to client: %s", send_exc) - return completed_event # Client disconnected - return completed_event + return terminal_event # Client disconnected + return terminal_event def _save_turn_history( self, - completed_event: _MutableJsonObject | None, + terminal_event: _MutableJsonObject | None, prior_history: list[dict[str, object]], current_messages: list[dict[str, object]], ) -> None: - """Store this turn in in-memory history for future previous_response_id lookups.""" - if completed_event is None: + """Store this terminal (``response.completed`` or ``response.incomplete``) event for future history lookups.""" + if terminal_event is None: return - new_response_id: Final = self._extract_response_id(completed_event) + new_response_id: Final = self._extract_response_id(terminal_event) if not new_response_id: return - output_msgs: Final = self._extract_output_messages(completed_event) + output_msgs: Final = self._extract_output_messages(terminal_event) all_messages: Final = prior_history + current_messages + output_msgs self._store_history(new_response_id, all_messages) verbose_logger.debug( @@ -2801,7 +2803,8 @@ class ManagedResponsesWebSocketHandler: 2. Prepend those messages to the current ``input`` so the model has full conversation context. 3. After the stream completes, extract the new response ID and output - messages from ``response.completed`` and store them in + messages from the terminal (``response.completed`` or + ``response.incomplete``) event and store them in ``self._session_history`` for the next turn. This in-memory approach avoids the async DB-write race condition that @@ -2855,13 +2858,13 @@ class ManagedResponsesWebSocketHandler: call_kwargs.update(self.extra_kwargs) try: - completed_event: Final = await self._stream_and_forward(model, call_kwargs) + terminal_event: Final = await self._stream_and_forward(model, call_kwargs) except Exception as exc: verbose_logger.exception("ManagedResponsesWS: error processing response.create: %s", exc) await self._send_error(str(exc)) return - self._save_turn_history(completed_event, prior_history, current_messages) + self._save_turn_history(terminal_event, prior_history, current_messages) # ------------------------------------------------------------------ # Main entry point diff --git a/tests/unit/llms/bedrock/chat/test_converse_transformation.py b/tests/unit/llms/bedrock/chat/test_converse_transformation.py index 499096621c5..b31cb8693ba 100644 --- a/tests/unit/llms/bedrock/chat/test_converse_transformation.py +++ b/tests/unit/llms/bedrock/chat/test_converse_transformation.py @@ -5764,6 +5764,67 @@ def test_transform_response_finish_reason_stop_when_json_mode_filters_all_tools( assert result.choices[0].finish_reason == "stop" +def test_transform_response_json_mode_truncated_tool_call_keeps_length_finish_reason(): + """ + When json_mode filters out the synthetic json_tool_call but Bedrock + stopped on max_tokens, finish_reason must stay "length", not be + downgraded to "stop" — otherwise truncated structured output looks + completed. + """ + from litellm.llms.bedrock.chat.converse_transformation import AmazonConverseConfig + from litellm.types.utils import ModelResponse + + response_json = { + "metrics": {"latencyMs": 100}, + "output": { + "message": { + "role": "assistant", + "content": [ + { + "toolUse": { + "toolUseId": "tooluse_001", + "name": "json_tool_call", + "input": {"a": "cut"}, + } + } + ], + } + }, + "stopReason": "max_tokens", + "usage": { + "inputTokens": 10, + "outputTokens": 60, + "totalTokens": 70, + }, + } + + class MockResponse: + def json(self) -> dict[str, object]: + return response_json + + @property + def text(self) -> str: + return json.dumps(response_json) + + config = AmazonConverseConfig() + model_response = ModelResponse() + + result = config._transform_response( + model="bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0", + response=MockResponse(), + model_response=model_response, + stream=False, + logging_obj=None, + optional_params={"json_mode": True}, + api_key=None, + data=None, + messages=[], + encoding=None, + ) + + assert result.choices[0].finish_reason == "length" + + def test_transform_response_citations_content_maps_to_annotations(): from litellm.llms.bedrock.chat.converse_transformation import AmazonConverseConfig from litellm.types.utils import ModelResponse diff --git a/tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py b/tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py index 7b9de4644b4..c13054f1cee 100644 --- a/tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py +++ b/tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py @@ -4382,11 +4382,11 @@ class TestEnsureOutputItemContentPartAdded: namespace_map.assert_called_once_with(request["tools"]) - def test_emit_response_completed_uses_stream_finish_reason(self): + def test_emit_terminal_event_uses_stream_finish_reason(self): """ - When the assembled model response carries finish_reason="content_filter" - (snapshotted from the underlying stream before any pending events fire), - _emit_response_completed_event must produce status="incomplete". + The terminal stream event type must track the assembled response + status: finish_reason="content_filter" yields response.incomplete, + finish_reason="stop" yields response.completed. """ from unittest.mock import Mock @@ -4394,6 +4394,7 @@ class TestEnsureOutputItemContentPartAdded: from litellm.responses.litellm_completion_transformation.streaming_iterator import ( LiteLLMCompletionStreamingIterator, ) + from litellm.types.llms.openai import ResponsesAPIStreamEvents mock_stream_wrapper = Mock(spec=litellm.CustomStreamWrapper) mock_stream_wrapper.logging_obj = Mock() @@ -4406,28 +4407,32 @@ class TestEnsureOutputItemContentPartAdded: custom_llm_provider="anthropic", ) - litellm_model_response = ModelResponse( - id="chatcmpl-test", - created=1234567890, - model="anthropic/claude-sonnet-4-6", - object="chat.completion", - choices=[ - Choices( - finish_reason="content_filter", - index=0, - message=Message(content="", role="assistant"), - ) - ], - usage=Usage(prompt_tokens=10, completion_tokens=1, total_tokens=11), - ) + def _response(finish_reason: str) -> ModelResponse: + return ModelResponse( + id="chatcmpl-test", + created=1234567890, + model="anthropic/claude-sonnet-4-6", + object="chat.completion", + choices=[ + Choices( + finish_reason=finish_reason, + index=0, + message=Message(content="", role="assistant"), + ) + ], + usage=Usage(prompt_tokens=10, completion_tokens=1, total_tokens=11), + ) - completed_event = iterator._emit_response_completed_event( - litellm_model_response - ) + incomplete_event = iterator._emit_terminal_response_event(_response("content_filter")) + assert incomplete_event is not None + assert incomplete_event.type == ResponsesAPIStreamEvents.RESPONSE_INCOMPLETE + assert incomplete_event.response.status == "incomplete" + assert incomplete_event.response.output[0].status == "incomplete" + completed_event = iterator._emit_terminal_response_event(_response("stop")) assert completed_event is not None - assert completed_event.response.status == "incomplete" - assert completed_event.response.output[0].status == "incomplete" + assert completed_event.type == ResponsesAPIStreamEvents.RESPONSE_COMPLETED + assert completed_event.response.status == "completed" def test_reasoning_item_does_not_emit_content_part_added(self): """Reasoning items should not get a content_part.added event.""" @@ -5016,7 +5021,7 @@ class TestStreamingSnapshotItemIds: ) assert streamed_event is not None - completed_event = iterator._emit_response_completed_event( + completed_event = iterator._emit_terminal_response_event( _bridged_chat_completion_response() ) @@ -5031,7 +5036,7 @@ class TestStreamingSnapshotItemIds: self._make_chunk("apple") ) - completed_event = iterator._emit_response_completed_event( + completed_event = iterator._emit_terminal_response_event( _bridged_chat_completion_response() ) @@ -5088,7 +5093,7 @@ class TestStreamingSnapshotItemIds: ) assert streamed_event is not None - completed_event = iterator._emit_response_completed_event( + completed_event = iterator._emit_terminal_response_event( self._reasoning_chat_completion_response() ) @@ -5159,6 +5164,140 @@ def test_transform_chat_completion_response_incomplete_details(): assert result_existing.incomplete_details == existing_details +def test_transform_chat_completion_response_null_finish_reason_is_incomplete(): + """ + A choice with no finish signal (e.g. Gemini thinking consuming the whole + output budget, or a provider that never sent one) must not report + status "completed". Output at the requested cap reads as + max_output_tokens; below it, no reason can be claimed. + """ + choice_at_cap = Choices.model_construct( + index=0, + finish_reason=None, + message=Message(content="", role="assistant"), + ) + resp_at_cap = ModelResponse( + id="resp-null-cap", + choices=[choice_at_cap], + model="gemini-2.5-pro", + usage=Usage(prompt_tokens=10, completion_tokens=60, total_tokens=70), + ) + result_at_cap = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response( + request_input="test prompt", + responses_api_request={"max_output_tokens": 60}, + chat_completion_response=resp_at_cap, + ) + assert result_at_cap.status == "incomplete" + assert result_at_cap.incomplete_details is not None + assert result_at_cap.incomplete_details.reason == "max_output_tokens" + + choice_under_cap = Choices.model_construct( + index=0, + finish_reason=None, + message=Message(content="", role="assistant"), + ) + resp_under_cap = ModelResponse( + id="resp-null-under", + choices=[choice_under_cap], + model="gemini-2.5-pro", + usage=Usage(prompt_tokens=10, completion_tokens=30, total_tokens=40), + ) + result_under_cap = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response( + request_input="test prompt", + responses_api_request={"max_output_tokens": 60}, + chat_completion_response=resp_under_cap, + ) + assert result_under_cap.status == "incomplete" + assert result_under_cap.incomplete_details is None + + resp_empty = ModelResponse(id="resp-empty", choices=[], model="gemini-2.5-pro") + result_empty = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response( + request_input="test prompt", + responses_api_request={}, + chat_completion_response=resp_empty, + ) + assert result_empty.status == "incomplete" + + +def test_transform_chat_completion_response_echoes_request_params(): + """ + A chat completion response never carries the caller's request fields, so + the bridged response echoes them from the request. Before this fix + temperature reported 0 and the rest reported None or empty defaults. + """ + resp = ModelResponse( + id="resp-echo", + choices=[Choices(index=0, finish_reason="stop", message=Message(content="hi", role="assistant"))], + model="gpt-4o", + ) + result = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response( + request_input="test prompt", + responses_api_request={ + "temperature": 0.7, + "top_p": 0.9, + "max_output_tokens": 128, + "instructions": "be terse", + "metadata": {"trace": "abc"}, + "user": "user-123", + "truncation": "disabled", + "store": True, + "parallel_tool_calls": True, + }, + chat_completion_response=resp, + ) + assert result.temperature == 0.7 + assert result.top_p == 0.9 + assert result.max_output_tokens == 128 + assert result.instructions == "be terse" + assert result.metadata == {"trace": "abc"} + assert result.user == "user-123" + assert result.truncation == "disabled" + assert result.store is True + assert result.parallel_tool_calls is True + + # Fields the request never set fall back to the response defaults. + result_unset = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response( + request_input="test prompt", + responses_api_request={}, + chat_completion_response=resp, + ) + assert result_unset.temperature is None + assert result_unset.metadata == {} + assert result_unset.parallel_tool_calls is False + assert result_unset.tools == [] + assert result_unset.text == {} + + +@pytest.mark.parametrize( + ("field", "invalid_value", "expected"), + [ + ("user", 123, None), + ("instructions", 5, None), + ("text", "plain", {}), + ("truncation", "bogus", None), + ("parallel_tool_calls", "maybe", False), + ], +) +def test_transform_drops_request_params_the_response_cannot_echo( + field: str, invalid_value: object, expected: object +) -> None: + request: Final[dict[str, object]] = {"temperature": 0.7, field: invalid_value} + response: Final = ModelResponse( + id="resp-invalid-echo", + choices=[Choices(index=0, finish_reason="stop", message=Message(content="hi", role="assistant"))], + model="gpt-4o", + ) + + result: Final = LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response( + request_input="test prompt", + responses_api_request=request, + chat_completion_response=response, + ) + + assert getattr(result, field) == expected, f"invalid {field} value {invalid_value!r}" + assert result.temperature == 0.7, f"valid temperature was dropped with invalid {field}" + + @pytest.mark.parametrize("stream", [True, False]) async def test_bridge_rejects_untranslatable_tool_choice_with_a_400(stream: bool): with pytest.raises(litellm.BadRequestError) as exc_info: diff --git a/tests/unit/responses/test_responses_websocket_all_providers.py b/tests/unit/responses/test_responses_websocket_all_providers.py index 6f346a25d9c..222cc641b6b 100644 --- a/tests/unit/responses/test_responses_websocket_all_providers.py +++ b/tests/unit/responses/test_responses_websocket_all_providers.py @@ -8,6 +8,7 @@ Tests that: """ import json +from typing import Final from unittest.mock import MagicMock import pytest @@ -283,6 +284,91 @@ class TestManagedWebSocketHandlerIntegration: assert captured["model"] == "bedrock_mantle/openai.gpt-5.5" + @pytest.mark.parametrize("terminal_type", ["response.completed", "response.incomplete"]) + @pytest.mark.asyncio + async def test_truncated_turn_is_kept_as_history_for_the_next_turn(self, monkeypatch, terminal_type: str): + from unittest.mock import AsyncMock, MagicMock + + import litellm + from litellm.litellm_core_utils.litellm_logging import Logging + from litellm.responses.streaming_iterator import ManagedResponsesWebSocketHandler + + terminal_response: Final = { + "type": terminal_type, + "response": { + "id": "resp_turn1", + "status": "incomplete" if terminal_type == "response.incomplete" else "completed", + "output": [ + { + "type": "message", + "role": "assistant", + "content": [{"type": "output_text", "text": "PELICAN noted"}], + } + ], + }, + } + + async def first_stream(): + yield terminal_response + + async def empty_stream(): + return + yield {} + + aresponses_mock: Final = AsyncMock(side_effect=(first_stream(), empty_stream())) + monkeypatch.setattr(litellm, "aresponses", aresponses_mock) + + websocket: Final = MagicMock() + websocket.send_text = AsyncMock() + handler: Final = ManagedResponsesWebSocketHandler( + websocket=websocket, + model="bedrock_mantle/openai.gpt-5.5", + logging_obj=Logging( + model="bedrock_mantle/openai.gpt-5.5", + messages=[], + stream=True, + call_type="aresponses", + start_time=0, + litellm_call_id="test-id", + function_id="test-func", + ), + litellm_metadata={"model_group": "gpt-5.5-mantle"}, + ) + + turn_one_user: Final[dict[str, object]] = { + "type": "message", + "role": "user", + "content": [{"type": "input_text", "text": "My secret word is PELICAN"}], + } + turn_two_user: Final[dict[str, object]] = { + "type": "message", + "role": "user", + "content": [{"type": "input_text", "text": "What is my secret word?"}], + } + turn_one_frame: Final = json.dumps({"type": "response.create", "input": [turn_one_user]}) + turn_two_frame: Final = json.dumps( + { + "type": "response.create", + "previous_response_id": "resp_turn1", + "input": [turn_two_user], + } + ) + + await handler._process_response_create(turn_one_frame) + await handler._process_response_create(turn_two_frame) + + expected_input: Final[list[dict[str, object]]] = [ + turn_one_user, + { + "type": "message", + "role": "assistant", + "content": [{"type": "output_text", "text": "PELICAN noted"}], + }, + turn_two_user, + ] + second_call_input: Final = aresponses_mock.call_args_list[1].kwargs["input"] + assert second_call_input == expected_input, terminal_type + @pytest.mark.asyncio async def test_warmup_frame_skips_provider_and_sends_synthetic_ack( self, monkeypatch From 6ba8151a2d4e67a70868428a2667b633b70907f5 Mon Sep 17 00:00:00 2001 From: mrinal-berri Date: Tue, 20 Oct 2026 15:32:30 -0700 Subject: [PATCH 12/66] fix(databricks): keep #/$defs refs in json_schema response_format (#45659) Backport of #45659 to stable/1.104.x. Cherry-picked from fa7ad80a622afb8fe64dce9365abd4358ae834b1 (main). Test-file conflict resolved by keeping the line's file plus this PR's own additions. --- .../llms/databricks/chat/transformation.py | 17 +- .../providers/test_databricks_chat_wire.py | 747 +++++++++++++++++- .../test_databricks_json_schema_refs_sdk.py | 186 +++++ .../test_databricks_chat_transformation.py | 88 +++ 4 files changed, 1034 insertions(+), 4 deletions(-) create mode 100644 tests/integration/sdk/test_databricks_json_schema_refs_sdk.py diff --git a/litellm/llms/databricks/chat/transformation.py b/litellm/llms/databricks/chat/transformation.py index 538904b34e6..9e88fffbeef 100644 --- a/litellm/llms/databricks/chat/transformation.py +++ b/litellm/llms/databricks/chat/transformation.py @@ -7,7 +7,7 @@ from collections.abc import AsyncIterator, Coroutine, Iterator, Mapping, Sequenc from typing import TYPE_CHECKING, Any, Final, Literal, cast, overload import httpx -from pydantic import BaseModel +from pydantic import BaseModel, TypeAdapter from litellm.constants import RESPONSE_FORMAT_TOOL_NAME from litellm.litellm_core_utils.llm_response_utils.convert_dict_to_response import ( @@ -21,6 +21,9 @@ from litellm.litellm_core_utils.prompt_templates.common_utils import ( strip_name_from_message, ) from litellm.llms.base_llm.base_model_iterator import BaseModelResponseIterator +from litellm.llms.base_llm.base_utils import ( + type_to_response_format_param, # pyright: ignore[reportUnknownVariableType] # base_utils helper returns an untyped dict +) from litellm.types.llms.anthropic import AllAnthropicToolsValues from litellm.types.llms.databricks import ( AllDatabricksContentValues, @@ -59,6 +62,10 @@ from ...anthropic.chat.transformation import ( from ...openai_like.chat.transformation import OpenAILikeChatConfig from ..common_utils import DatabricksBase, DatabricksException +_RESPONSE_FORMAT_ADAPTER: ( # mutable-ok: mirrors the dict return contract of get_json_schema_from_pydantic_object + Final[TypeAdapter[dict[str, object] | None]] +) = TypeAdapter(dict[str, object] | None) + def _is_bare_assistant_message(message_dict: Mapping[str, object]) -> bool: """Databricks rejects assistant messages with neither content nor tool calls, e.g. a replayed @@ -191,6 +198,14 @@ class DatabricksConfig(DatabricksBase, OpenAILikeChatConfig, AnthropicConfig): def get_config(cls, *, model: str | None = None): return super().get_config() + def get_json_schema_from_pydantic_object( + self, + response_format: ( # mutable-ok: matches BaseConfig override signature + type[BaseModel] | dict[str, object] | None + ), + ) -> dict[str, object] | None: # mutable-ok: BaseConfig contract returns a dict + return _RESPONSE_FORMAT_ADAPTER.validate_python(type_to_response_format_param(response_format=response_format)) + def get_required_params(self) -> list[ProviderField]: """For a given provider, return it's required fields with a description""" return [ diff --git a/tests/integration/providers/test_databricks_chat_wire.py b/tests/integration/providers/test_databricks_chat_wire.py index 614382a77f0..f6192d32c31 100644 --- a/tests/integration/providers/test_databricks_chat_wire.py +++ b/tests/integration/providers/test_databricks_chat_wire.py @@ -1,7 +1,9 @@ +import itertools import json import uuid from collections.abc import Mapping -from typing import Final +from concurrent.futures import ThreadPoolExecutor +from typing import Final, Literal, TypeAlias import pytest from integration._support.client import Gateway, eventually @@ -12,6 +14,10 @@ from pydantic import BaseModel, ConfigDict, JsonValue, TypeAdapter _BACKEND: Final = "databricks-glm-5-2" _API_KEY: Final = "synthetic-databricks-key" _PROMPT: Final = "Summarise the cached briefing in one sentence." +_JSON_SCHEMA_BACKEND: Final = "databricks-qwen35-122b-a10b" +_CLAUDE_BACKEND: Final = "databricks-claude-haiku-4-5" +_JSON_SCHEMA_PROMPT: Final = "Return the requested JSON." +_JSON_CONTENT: Final = '{"p":{"name":"Ada"}}' _PROVIDER_USAGE: Final[Mapping[str, JsonValue]] = { "prompt_tokens": 12011, "completion_tokens": 8, @@ -20,6 +26,67 @@ _PROVIDER_USAGE: Final[Mapping[str, JsonValue]] = { "cache_creation_input_tokens": 0, } _JSON_OBJECT: Final = TypeAdapter(dict[str, JsonValue]) +_PERSON_SCHEMA: Final[Mapping[str, JsonValue]] = { + "$defs": { + "Person": { + "type": "object", + "properties": {"name": {"type": "string"}}, + "required": ["name"], + } + }, + "type": "object", + "properties": {"p": {"$ref": "#/$defs/Person"}}, + "required": ["p"], +} +_JSON_SCHEMA_RESPONSE_FORMAT: Final[Mapping[str, JsonValue]] = { + "type": "json_schema", + "json_schema": {"name": "P", "strict": True, "schema": _PERSON_SCHEMA}, +} +_MESSAGES_PERSON_SCHEMA: Final[Mapping[str, JsonValue]] = { + "$defs": { + "Person": { + "type": "object", + "properties": {"name": {"type": "string"}}, + "required": ["name"], + "additionalProperties": False, + } + }, + "type": "object", + "properties": {"p": {"$ref": "#/$defs/Person"}}, + "required": ["p"], + "additionalProperties": False, +} +_MESSAGES_RESPONSE_FORMAT: Final[Mapping[str, JsonValue]] = { + "type": "json_schema", + "json_schema": { + "name": "structured_output", + "schema": _MESSAGES_PERSON_SCHEMA, + "strict": True, + }, +} +_JSON_TOOL_CALL_MESSAGE: Final[dict[str, JsonValue]] = { + "role": "assistant", + "content": None, + "tool_calls": [ + { + "id": "json-tool-call", + "type": "function", + "function": {"name": "json_tool_call", "arguments": _JSON_CONTENT}, + } + ], +} + + +def _chat_completion_response(model: str, message: dict[str, JsonValue], finish_reason: str) -> bytes: + response: Final = { + "id": "databricks-json-schema-response", + "object": "chat.completion", + "created": 1, + "model": model, + "choices": [{"index": 0, "message": message, "finish_reason": finish_reason}], + "usage": {"prompt_tokens": 1, "completion_tokens": 1, "total_tokens": 2}, + } + return json.dumps(response).encode() class _PromptTokensDetails(BaseModel): @@ -52,12 +119,17 @@ class _Chunk(BaseModel): usage: _Usage | None = None -def _frame(identity: str, choices: list[Mapping[str, object]], usage: Mapping[str, JsonValue] | None = None) -> bytes: +def _frame( + identity: str, + choices: list[Mapping[str, object]], + usage: Mapping[str, JsonValue] | None = None, + model: str = _BACKEND, +) -> bytes: value: Final = { "id": identity, "object": "chat.completion.chunk", "created": 1, - "model": _BACKEND, + "model": model, "choices": choices, **({} if usage is None else {"usage": usage}), } @@ -127,3 +199,672 @@ def test_databricks_stream_final_usage_chunk_reaches_client_and_spend_log(gatewa seconds=70, ) assert (rows[0]["prompt_tokens"], rows[0]["completion_tokens"], rows[0]["total_tokens"]) == (12011, 8, 12019) + + +def test_databricks_json_schema_refs_are_preserved_in_chat_completions(gateway: Gateway) -> None: + def respond(request: Request) -> Reply: + assert request.method == "POST" + assert request.target == "/chat/completions" + body: Final = _JSON_OBJECT.validate_json(request.body) + assert body["model"] == _JSON_SCHEMA_BACKEND + assert body["messages"] == [{"role": "user", "content": _JSON_SCHEMA_PROMPT}] + assert body["stream"] is False + assert body["response_format"] == _JSON_SCHEMA_RESPONSE_FORMAT + return Reply( + body=_chat_completion_response( + _JSON_SCHEMA_BACKEND, + {"role": "assistant", "content": _JSON_CONTENT}, + "stop", + ) + ) + + with wire_server(respond) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + response: Final = gateway.request( + "POST", + "/v1/chat/completions", + { + "model": model, + "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}], + "response_format": _JSON_SCHEMA_RESPONSE_FORMAT, + }, + ) + assert response.status_code == 200, response.text + body: Final = _JSON_OBJECT.validate_json(response.content) + assert body["choices"] == [ + { + "index": 0, + "message": {"role": "assistant", "content": _JSON_CONTENT}, + "finish_reason": "stop", + } + ] + assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")] + + +def test_databricks_streaming_json_schema_refs_are_preserved(gateway: Gateway) -> None: + identity: Final = f"databricks-json-schema-stream-{uuid.uuid4().hex}" + frames: Final = ( + _frame( + identity, + [{"index": 0, "delta": {"role": "assistant", "content": '{"p":'}, "finish_reason": None}], + model=_JSON_SCHEMA_BACKEND, + ), + _frame( + identity, + [{"index": 0, "delta": {"content": '{"name":"Ada"}}'}, "finish_reason": None}], + model=_JSON_SCHEMA_BACKEND, + ), + _frame(identity, [{"index": 0, "delta": {}, "finish_reason": "stop"}], model=_JSON_SCHEMA_BACKEND), + b"data: [DONE]\n\n", + ) + + def respond(request: Request) -> Reply: + assert request.method == "POST" + assert request.target == "/chat/completions" + body: Final = _JSON_OBJECT.validate_json(request.body) + assert body["model"] == _JSON_SCHEMA_BACKEND + assert body["messages"] == [{"role": "user", "content": _JSON_SCHEMA_PROMPT}] + assert body["stream"] is True + assert body["response_format"] == _JSON_SCHEMA_RESPONSE_FORMAT + return Reply(content_type="text/event-stream", chunks=frames) + + with wire_server(respond) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + with gateway.client.stream( + "POST", + "/v1/chat/completions", + json={ + "model": model, + "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}], + "response_format": _JSON_SCHEMA_RESPONSE_FORMAT, + "stream": True, + }, + headers={"Authorization": f"Bearer {gateway.key}"}, + ) as response: + assert response.status_code == 200, response.read() + lines: Final = tuple(line for line in response.iter_lines() if line.startswith("data: ")) + assert lines[-1] == "data: [DONE]", lines + chunks: Final = tuple(_Chunk.model_validate_json(line.removeprefix("data: ")) for line in lines[:-1]) + choices: Final = tuple(itertools.chain.from_iterable(chunk.choices for chunk in chunks)) + assert "".join(choice.delta.content or "" for choice in choices) == _JSON_CONTENT + assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")] + + +def test_databricks_claude_json_schema_refs_are_preserved_in_tool_parameters(gateway: Gateway) -> None: + def respond(request: Request) -> Reply: + assert request.method == "POST" + assert request.target == "/chat/completions" + body: Final = _JSON_OBJECT.validate_json(request.body) + assert body["model"] == _CLAUDE_BACKEND + assert body["messages"] == [{"role": "user", "content": _JSON_SCHEMA_PROMPT}] + assert "response_format" not in body + assert body["tools"] == [ + { + "type": "function", + "function": {"name": "json_tool_call", "parameters": _PERSON_SCHEMA}, + } + ] + assert body["tool_choice"] == {"type": "function", "function": {"name": "json_tool_call"}} + return Reply(body=_chat_completion_response(_CLAUDE_BACKEND, _JSON_TOOL_CALL_MESSAGE, "tool_calls")) + + with wire_server(respond) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_CLAUDE_BACKEND}", api_base=wire.url, api_key=_API_KEY) + response: Final = gateway.request( + "POST", + "/v1/chat/completions", + { + "model": model, + "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}], + "response_format": _JSON_SCHEMA_RESPONSE_FORMAT, + }, + ) + assert response.status_code == 200, response.text + body: Final = _JSON_OBJECT.validate_json(response.content) + assert body["choices"] == [ + { + "index": 0, + "message": {"role": "assistant", "content": _JSON_CONTENT}, + "finish_reason": "stop", + } + ] + assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")] + + +def test_databricks_responses_json_schema_refs_are_preserved_in_chat_bridge(gateway: Gateway) -> None: + def respond(request: Request) -> Reply: + assert request.method == "POST" + assert request.target == "/chat/completions" + body: Final = _JSON_OBJECT.validate_json(request.body) + assert body["model"] == _JSON_SCHEMA_BACKEND + assert body["messages"] == [{"role": "user", "content": _JSON_SCHEMA_PROMPT}] + assert body["response_format"] == { + "type": "json_schema", + "json_schema": {"name": "P", "schema": _PERSON_SCHEMA, "strict": True}, + } + return Reply( + body=_chat_completion_response( + _JSON_SCHEMA_BACKEND, + {"role": "assistant", "content": _JSON_CONTENT}, + "stop", + ) + ) + + with wire_server(respond) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + response: Final = gateway.request( + "POST", + "/v1/responses", + { + "model": model, + "input": _JSON_SCHEMA_PROMPT, + "text": { + "format": { + "type": "json_schema", + "name": "P", + "strict": True, + "schema": _PERSON_SCHEMA, + } + }, + }, + ) + assert response.status_code == 200, response.text + assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")] + + +def test_databricks_messages_json_schema_refs_are_preserved_for_qwen(gateway: Gateway) -> None: + def respond(request: Request) -> Reply: + assert request.method == "POST" + assert request.target == "/chat/completions" + body: Final = _JSON_OBJECT.validate_json(request.body) + assert body["model"] == _JSON_SCHEMA_BACKEND + assert body["response_format"] == _MESSAGES_RESPONSE_FORMAT + return Reply( + body=_chat_completion_response( + _JSON_SCHEMA_BACKEND, + {"role": "assistant", "content": _JSON_CONTENT}, + "stop", + ) + ) + + with wire_server(respond) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + response: Final = gateway.request( + "POST", + "/v1/messages", + { + "model": model, + "max_tokens": 64, + "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}], + "output_format": {"type": "json_schema", "schema": _PERSON_SCHEMA}, + }, + ) + assert response.status_code == 200, response.text + body: Final = _JSON_OBJECT.validate_json(response.content) + assert body["content"] == [{"type": "text", "text": _JSON_CONTENT}] + assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")] + + +def test_databricks_messages_claude_json_schema_refs_are_preserved_in_tool_parameters(gateway: Gateway) -> None: + def respond(request: Request) -> Reply: + assert request.method == "POST" + assert request.target == "/chat/completions" + body: Final = _JSON_OBJECT.validate_json(request.body) + assert body["model"] == _CLAUDE_BACKEND + assert "response_format" not in body + assert body["tools"] == [ + { + "type": "function", + "function": {"name": "json_tool_call", "parameters": _MESSAGES_PERSON_SCHEMA}, + } + ] + assert body["tool_choice"] == {"type": "function", "function": {"name": "json_tool_call"}} + return Reply(body=_chat_completion_response(_CLAUDE_BACKEND, _JSON_TOOL_CALL_MESSAGE, "tool_calls")) + + with wire_server(respond) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_CLAUDE_BACKEND}", api_base=wire.url, api_key=_API_KEY) + response: Final = gateway.request( + "POST", + "/v1/messages", + { + "model": model, + "max_tokens": 64, + "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}], + "output_format": {"type": "json_schema", "schema": _PERSON_SCHEMA}, + }, + ) + assert response.status_code == 200, response.text + body: Final = _JSON_OBJECT.validate_json(response.content) + assert body["content"] == [{"type": "text", "text": _JSON_CONTENT}] + assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")] + + +_Endpoint: TypeAlias = Literal["chat", "responses", "messages"] +_PATHS: Final[Mapping[_Endpoint, str]] = { + "chat": "/v1/chat/completions", + "responses": "/v1/responses", + "messages": "/v1/messages", +} +_OUTAGE: Final = "upstream-outage" +_OUTAGE_MESSAGE: Final = "The service is temporarily unavailable" +_EXPECTED_JSON: Final[JsonValue] = _JSON_OBJECT.validate_json(_JSON_CONTENT) +_CONTENT_DELTAS: Final[tuple[Mapping[str, JsonValue], ...]] = ( + {"role": "assistant", "content": '{"p":'}, + {"content": '{"name":"Ada"}}'}, +) +_TOOL_CALL_DELTAS: Final[tuple[Mapping[str, JsonValue], ...]] = ( + { + "role": "assistant", + "content": None, + "tool_calls": [ + { + "index": 0, + "id": "json-tool-call", + "type": "function", + "function": {"name": "json_tool_call", "arguments": ""}, + } + ], + }, + {"tool_calls": [{"index": 0, "function": {"arguments": _JSON_CONTENT}}]}, +) + + +class _ChatMessage(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + content: str | None = None + + +class _ChatChoice(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + message: _ChatMessage + + +class _ChatCompletion(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + choices: tuple[_ChatChoice, ...] + + +class _OutputPart(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + type: str + text: str | None = None + + +class _OutputItem(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + type: str + content: tuple[_OutputPart, ...] = () + name: str | None = None + arguments: str | None = None + + +class _ResponsesBody(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + output: tuple[_OutputItem, ...] + + +class _ResponsesEvent(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + type: str + response: _ResponsesBody | None = None + + +class _MessagesBlock(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + type: str + text: str | None = None + + +class _MessagesBody(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + content: tuple[_MessagesBlock, ...] + + +class _MessagesDelta(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + type: str | None = None + text: str | None = None + partial_json: str | None = None + + +class _MessagesEvent(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + type: str + delta: _MessagesDelta | None = None + + +class _FunctionDelta(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + arguments: str | None = None + + +class _ToolCallDelta(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + function: _FunctionDelta | None = None + + +class _StreamDelta(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + content: str | None = None + tool_calls: tuple[_ToolCallDelta, ...] | None = None + + +class _StreamChoice(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + delta: _StreamDelta + + +class _StreamChunk(BaseModel): + model_config = ConfigDict(extra="ignore", frozen=True) + choices: tuple[_StreamChoice, ...] + + +def _json_schema_format(schema: Mapping[str, JsonValue]) -> dict[str, JsonValue]: + return {"type": "json_schema", "json_schema": {"name": "P", "strict": True, "schema": dict(schema)}} + + +def _client_body( + endpoint: _Endpoint, + model: str, + stream: bool, + prompt: str = _JSON_SCHEMA_PROMPT, +) -> dict[str, JsonValue]: + match endpoint: + case "chat": + return { + "model": model, + "messages": [{"role": "user", "content": prompt}], + "response_format": _json_schema_format(_PERSON_SCHEMA), + "stream": stream, + } + case "responses": + return { + "model": model, + "input": prompt, + "text": { + "format": {"type": "json_schema", "name": "P", "strict": True, "schema": dict(_PERSON_SCHEMA)} + }, + "stream": stream, + } + case "messages": + return { + "model": model, + "max_tokens": 64, + "messages": [{"role": "user", "content": prompt}], + "output_format": {"type": "json_schema", "schema": dict(_PERSON_SCHEMA)}, + "stream": stream, + } + + +def _expected_outbound(endpoint: _Endpoint, backend: str) -> dict[str, JsonValue]: + schema: Final = dict(_MESSAGES_PERSON_SCHEMA if endpoint == "messages" else _PERSON_SCHEMA) + if "claude" in backend: + return _JSON_OBJECT.validate_python( + { + "tools": [{"type": "function", "function": {"name": "json_tool_call", "parameters": schema}}], + "tool_choice": {"type": "function", "function": {"name": "json_tool_call"}}, + } + ) + name: Final = "structured_output" if endpoint == "messages" else "P" + return _JSON_OBJECT.validate_python( + {"response_format": {"type": "json_schema", "json_schema": {"name": name, "schema": schema, "strict": True}}} + ) + + +def _assert_outbound(request: Request, endpoint: _Endpoint, backend: str, stream: bool) -> None: + assert (request.method, request.target) == ("POST", "/chat/completions") + body: Final = _JSON_OBJECT.validate_json(request.body) + expected: Final = _expected_outbound(endpoint, backend) + assert {key: body.get(key) for key in expected} == expected + assert (body["model"], body.get("stream") is True) == (backend, stream) + assert "claude" not in backend or "response_format" not in body + + +def _upstream_reply(backend: str, stream: bool) -> Reply: + claude: Final = "claude" in backend + finish_reason: Final = "tool_calls" if claude else "stop" + if not stream: + message: Final[dict[str, JsonValue]] = ( + _JSON_TOOL_CALL_MESSAGE if claude else {"role": "assistant", "content": _JSON_CONTENT} + ) + return Reply(body=_chat_completion_response(backend, message, finish_reason)) + identity: Final = f"databricks-json-schema-{uuid.uuid4().hex}" + deltas: Final = _TOOL_CALL_DELTAS if claude else _CONTENT_DELTAS + frames: Final = ( + *(_frame(identity, [{"index": 0, "delta": delta, "finish_reason": None}], model=backend) for delta in deltas), + _frame(identity, [{"index": 0, "delta": {}, "finish_reason": finish_reason}], model=backend), + b"data: [DONE]\n\n", + ) + return Reply(content_type="text/event-stream", chunks=frames) + + +def _outage_or_reply(request: Request) -> Reply: + if _OUTAGE.encode() in request.body: + error: Final = {"error_code": "TEMPORARILY_UNAVAILABLE", "message": _OUTAGE_MESSAGE} + return Reply(status=503, body=json.dumps(error).encode()) + body: Final = _JSON_OBJECT.validate_json(request.body) + return _upstream_reply(str(body["model"]), body.get("stream") is True) + + +def _item_text(item: _OutputItem) -> str: + match item.type: + case "message": + return "".join(part.text or "" for part in item.content) + case "function_call" if item.name == "json_tool_call": + return item.arguments or "" + case _: + return "" + + +def _responses_text(body: _ResponsesBody) -> str: + return "".join(_item_text(item) for item in body.output) + + +def _chat_delta_text(delta: _StreamDelta) -> str: + calls: Final = delta.tool_calls or () + return (delta.content or "") + "".join(call.function.arguments or "" for call in calls if call.function is not None) + + +def _messages_delta_text(delta: _MessagesDelta) -> str: + match delta.type: + case "text_delta": + return delta.text or "" + case "input_json_delta": + return delta.partial_json or "" + case _: + return "" + + +def _final_text(endpoint: _Endpoint, content: bytes) -> str: + match endpoint: + case "chat": + return _ChatCompletion.model_validate_json(content).choices[0].message.content or "" + case "responses": + return _responses_text(_ResponsesBody.model_validate_json(content)) + case "messages": + return "".join(block.text or "" for block in _MessagesBody.model_validate_json(content).content) + + +def _streamed_text(endpoint: _Endpoint, data: tuple[str, ...]) -> str: + match endpoint: + case "chat": + assert data[-1] == "[DONE]", data + chunks: Final = tuple(_StreamChunk.model_validate_json(line) for line in data[:-1]) + choices: Final = tuple(itertools.chain.from_iterable(chunk.choices for chunk in chunks)) + return "".join(_chat_delta_text(choice.delta) for choice in choices) + case "responses": + events: Final = tuple(_ResponsesEvent.model_validate_json(line) for line in data if line != "[DONE]") + completed: Final = tuple(event.response for event in events if event.type == "response.completed") + assert len(completed) == 1 and completed[0] is not None, data + return _responses_text(completed[0]) + case "messages": + message_events: Final = tuple(_MessagesEvent.model_validate_json(line) for line in data) + assert message_events[-1].type == "message_stop", data + deltas: Final = tuple(event.delta for event in message_events if event.delta is not None) + return "".join(_messages_delta_text(delta) for delta in deltas) + + +def _outcome(status: int, text: str) -> tuple[int, JsonValue]: + if status == 200: + return status, _JSON_OBJECT.validate_json(text) + return status, _OUTAGE_MESSAGE if _OUTAGE_MESSAGE in text else text + + +def _call(gateway: Gateway, endpoint: _Endpoint, body: Mapping[str, JsonValue]) -> tuple[int, str]: + if body["stream"] is not True: + response: Final = gateway.request("POST", _PATHS[endpoint], body) + return response.status_code, _final_text(endpoint, response.content) if response.is_success else response.text + with gateway.client.stream( + "POST", _PATHS[endpoint], json=dict(body), headers={"Authorization": f"Bearer {gateway.key}"} + ) as streamed: + if not streamed.is_success: + return streamed.status_code, streamed.read().decode() + data: Final = tuple(line.removeprefix("data: ") for line in streamed.iter_lines() if line.startswith("data: ")) + return 200, _streamed_text(endpoint, data) + + +@pytest.mark.parametrize( + ("endpoint", "backend", "stream"), + [ + pytest.param("chat", _CLAUDE_BACKEND, True, id="chat-stream-claude"), + pytest.param("responses", _CLAUDE_BACKEND, False, id="responses-claude"), + pytest.param("responses", _JSON_SCHEMA_BACKEND, True, id="responses-stream-qwen"), + pytest.param("responses", _CLAUDE_BACKEND, True, id="responses-stream-claude"), + pytest.param("messages", _JSON_SCHEMA_BACKEND, True, id="messages-stream-qwen"), + pytest.param("messages", _CLAUDE_BACKEND, True, id="messages-stream-claude"), + ], +) +def test_databricks_json_schema_refs_are_preserved_on_every_endpoint( + gateway: Gateway, endpoint: _Endpoint, backend: str, stream: bool +) -> None: + with wire_server(lambda _request: _upstream_reply(backend, stream)) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{backend}", api_base=wire.url, api_key=_API_KEY) + status, text = _call(gateway, endpoint, _client_body(endpoint, model, stream)) + received: Final = wire.drain() + assert len(received) == 1, received + _assert_outbound(received[0], endpoint, backend, stream) + assert _outcome(status, text) == (200, _EXPECTED_JSON), text + + +@pytest.mark.parametrize( + "response_format", + [ + pytest.param( + _json_schema_format( + { + "definitions": { + "Person": {"type": "object", "properties": {"name": {"type": "string"}}, "required": ["name"]} + }, + "type": "object", + "properties": {"p": {"$ref": "#/definitions/Person"}}, + "required": ["p"], + } + ), + id="definitions-ref", + ), + pytest.param( + _json_schema_format( + { + "type": "object", + "properties": { + "name": {"type": "string"}, + "children": {"type": "array", "items": {"$ref": "#"}}, + }, + "required": ["name", "children"], + } + ), + id="recursive-root-ref", + ), + pytest.param( + _json_schema_format({"type": "object", "properties": {"$ref": {"type": "string"}}, "required": ["$ref"]}), + id="property-named-ref", + ), + pytest.param( + _json_schema_format({"type": "object", "properties": {"name": {"type": "string"}}, "required": ["name"]}), + id="flat-schema", + ), + pytest.param({"type": "json_object"}, id="json-object"), + ], +) +def test_databricks_response_format_reaches_upstream_as_sent( + gateway: Gateway, response_format: dict[str, JsonValue] +) -> None: + with ( + wire_server(lambda _request: _upstream_reply(_JSON_SCHEMA_BACKEND, False)) as wire, + gateway.scenario() as scenario, + ): + model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + response: Final = gateway.request( + "POST", + "/v1/chat/completions", + { + "model": model, + "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}], + "response_format": response_format, + }, + ) + received: Final = wire.drain() + assert response.status_code == 200, response.text + assert _final_text("chat", response.content) == _JSON_CONTENT + assert [(request.method, request.target) for request in received] == [("POST", "/chat/completions")] + assert _JSON_OBJECT.validate_json(received[0].body)["response_format"] == response_format + + +def test_databricks_json_schema_without_schema_returns_the_upstream_error(gateway: Gateway) -> None: + response_format: Final[dict[str, JsonValue]] = {"type": "json_schema", "json_schema": {"name": "P", "strict": True}} + upstream_error: Final = {"error_code": "INVALID_PARAMETER_VALUE", "message": "json_schema.schema is required"} + + def respond(_request: Request) -> Reply: + return Reply(status=400, body=json.dumps(upstream_error).encode()) + + with wire_server(respond) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + response: Final = gateway.request( + "POST", + "/v1/chat/completions", + { + "model": model, + "messages": [{"role": "user", "content": _JSON_SCHEMA_PROMPT}], + "response_format": response_format, + }, + ) + received: Final = wire.drain() + assert (response.status_code, "json_schema.schema is required" in response.text) == (400, True), response.text + assert [(request.method, request.target) for request in received] == [("POST", "/chat/completions")] + assert _JSON_OBJECT.validate_json(received[0].body)["response_format"] == response_format + + +def _assert_burst_outbound(request: Request) -> None: + body: Final = _JSON_OBJECT.validate_json(request.body) + endpoint: Final[_Endpoint] = "messages" if body["response_format"] == _MESSAGES_RESPONSE_FORMAT else "chat" + _assert_outbound(request, endpoint, _JSON_SCHEMA_BACKEND, body.get("stream") is True) + + +def _burst_request(index: int) -> tuple[_Endpoint, bool, bool]: + endpoints: Final[tuple[_Endpoint, ...]] = ("chat", "responses", "messages") + return endpoints[index % 3], index % 2 == 1, index % 5 == 2 + + +def test_databricks_json_schema_burst_through_an_upstream_outage_keeps_every_ref(gateway: Gateway) -> None: + plan: Final = tuple(_burst_request(index) for index in range(24)) + recovery: Final[tuple[_Endpoint, ...]] = ("chat", "responses", "messages") + with wire_server(_outage_or_reply) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + endpoints: Final = tuple(endpoint for endpoint, _stream, _down in plan) + bodies: Final = tuple( + _client_body(endpoint, model, stream, f"{_JSON_SCHEMA_PROMPT} {index} {_OUTAGE if down else ''}") + for index, (endpoint, stream, down) in enumerate(plan) + ) + with ThreadPoolExecutor(max_workers=12) as pool: + results: Final = tuple(pool.map(_call, itertools.repeat(gateway), endpoints, bodies)) + recovered: Final = tuple( + _call(gateway, endpoint, _client_body(endpoint, model, False)) for endpoint in recovery + ) + received: Final = wire.drain() + assert len(received) == len(plan) + len(recovery), received + for request in received: + _assert_burst_outbound(request) + expected: Final = tuple( + (503, _OUTAGE_MESSAGE) if down else (200, _EXPECTED_JSON) for _endpoint, _stream, down in plan + ) + assert tuple(_outcome(*result) for result in results) == expected + assert tuple(_outcome(*result) for result in recovered) == ((200, _EXPECTED_JSON),) * len(recovery) diff --git a/tests/integration/sdk/test_databricks_json_schema_refs_sdk.py b/tests/integration/sdk/test_databricks_json_schema_refs_sdk.py new file mode 100644 index 00000000000..009679fa4b5 --- /dev/null +++ b/tests/integration/sdk/test_databricks_json_schema_refs_sdk.py @@ -0,0 +1,186 @@ +import json +import uuid +from collections.abc import Iterator, Mapping +from typing import Final + +import pytest +from integration._support.wire import Reply, Request, wire_server +from pydantic import BaseModel, ConfigDict, Field, JsonValue + +import litellm + +_QWEN_BACKEND: Final = "databricks-qwen35-122b-a10b" +_CLAUDE_BACKEND: Final = "databricks-claude-haiku-4-5" +_API_KEY: Final = "synthetic-databricks-key" +_ORDER_JSON: Final = '{"buyer":{"name":"Ada"},"seller":{"name":"Bo"}}' +_MESSAGES: Final[tuple[Mapping[str, str], ...]] = ({"role": "user", "content": "Return the order as JSON."},) + + +class Person(BaseModel): + model_config = ConfigDict(frozen=True) + name: str + + +class Order(BaseModel): + model_config = ConfigDict(frozen=True) + buyer: Person + seller: Person + + +class _StrictObject(BaseModel): + model_config = ConfigDict(frozen=True, extra="ignore") + additional_properties: bool | None = Field(default=None, alias="additionalProperties") + + +class _OrderSchema(_StrictObject): + defs: Mapping[str, _StrictObject] = Field(alias="$defs") + + +class _JsonSchema(BaseModel): + model_config = ConfigDict(frozen=True, extra="ignore") + name: str + strict: bool | None = None + json_schema: dict[str, JsonValue] = Field(alias="schema") + + +class _ResponseFormat(BaseModel): + model_config = ConfigDict(frozen=True, extra="ignore") + type: str + json_schema: _JsonSchema + + +class _Function(BaseModel): + model_config = ConfigDict(frozen=True, extra="ignore") + name: str + parameters: dict[str, JsonValue] + + +class _Tool(BaseModel): + model_config = ConfigDict(frozen=True, extra="ignore") + function: _Function + + +class _Outbound(BaseModel): + model_config = ConfigDict(frozen=True, extra="ignore") + model: str + response_format: _ResponseFormat | None = None + tools: tuple[_Tool, ...] = () + + +class _CallerMessage(BaseModel): + model_config = ConfigDict(frozen=True, extra="ignore") + content: str + + +class _CallerChoice(BaseModel): + model_config = ConfigDict(frozen=True, extra="ignore") + message: _CallerMessage + + +class _CallerCompletion(BaseModel): + model_config = ConfigDict(frozen=True, extra="ignore") + choices: tuple[_CallerChoice, ...] + + +def _completion(backend: str) -> Reply: + claude: Final = "claude" in backend + tool_call: Final[dict[str, JsonValue]] = { + "id": "json-tool-call", + "type": "function", + "function": {"name": "json_tool_call", "arguments": _ORDER_JSON}, + } + message: Final[dict[str, JsonValue]] = ( + {"role": "assistant", "content": None, "tool_calls": [tool_call]} + if claude + else {"role": "assistant", "content": _ORDER_JSON} + ) + body: Final[dict[str, JsonValue]] = { + "id": f"chatcmpl-{uuid.uuid4().hex}", + "object": "chat.completion", + "created": 1, + "model": backend, + "choices": [{"index": 0, "message": message, "finish_reason": "tool_calls" if claude else "stop"}], + "usage": {"prompt_tokens": 9, "completion_tokens": 7, "total_tokens": 16}, + } + return Reply(body=json.dumps(body).encode()) + + +def _refs(node: JsonValue) -> Iterator[str]: + if isinstance(node, list): + for item in node: + yield from _refs(item) + return + if not isinstance(node, dict): + return + for key, value in node.items(): + if key == "$ref" and isinstance(value, str): + yield value + else: + yield from _refs(value) + + +def _sent_schema(backend: str, received: tuple[Request, ...]) -> dict[str, JsonValue]: + assert [(request.method, request.target) for request in received] == [("POST", "/chat/completions")] + outbound: Final = _Outbound.model_validate_json(received[0].body) + assert outbound.model == backend + if "claude" in backend: + assert outbound.response_format is None + assert [tool.function.name for tool in outbound.tools] == ["json_tool_call"] + return outbound.tools[0].function.parameters + assert outbound.response_format is not None + assert (outbound.response_format.type, outbound.response_format.json_schema.name) == ("json_schema", "Order") + assert outbound.response_format.json_schema.strict is True + return outbound.response_format.json_schema.json_schema + + +def _assert_strict_order_schema(schema: dict[str, JsonValue]) -> None: + assert set(_refs(schema)) == {"#/$defs/Person"}, schema + parsed: Final = _OrderSchema.model_validate(schema) + assert (parsed.additional_properties, parsed.defs["Person"].additional_properties) == (False, False), schema + + +def _caller_order(response: litellm.ModelResponse) -> Order: + return Order.model_validate_json( + _CallerCompletion.model_validate_json(response.model_dump_json()).choices[0].message.content + ) + + +_BACKENDS: Final = ( + pytest.param(_QWEN_BACKEND, id="qwen"), + pytest.param(_CLAUDE_BACKEND, id="claude"), +) +_EXPECTED_ORDER: Final = Order(buyer=Person(name="Ada"), seller=Person(name="Bo")) + + +@pytest.mark.parametrize("backend", _BACKENDS) +def test_databricks_pydantic_response_format_sends_strict_defs_refs(backend: str) -> None: + with wire_server(lambda _request: _completion(backend)) as wire: + response: Final = litellm.completion( + model=f"databricks/{backend}", + api_base=wire.url, + api_key=_API_KEY, + messages=[dict(message) for message in _MESSAGES], + response_format=Order, + num_retries=0, + ) + received: Final = wire.drain() + _assert_strict_order_schema(_sent_schema(backend, received)) + assert isinstance(response, litellm.ModelResponse) + assert _caller_order(response) == _EXPECTED_ORDER + + +@pytest.mark.parametrize("backend", _BACKENDS) +async def test_databricks_pydantic_response_format_sends_strict_defs_refs_async(backend: str) -> None: + with wire_server(lambda _request: _completion(backend)) as wire: + response: Final = await litellm.acompletion( + model=f"databricks/{backend}", + api_base=wire.url, + api_key=_API_KEY, + messages=[dict(message) for message in _MESSAGES], + response_format=Order, + num_retries=0, + ) + received: Final = wire.drain() + _assert_strict_order_schema(_sent_schema(backend, received)) + assert isinstance(response, litellm.ModelResponse) + assert _caller_order(response) == _EXPECTED_ORDER diff --git a/tests/unit/llms/databricks/chat/test_databricks_chat_transformation.py b/tests/unit/llms/databricks/chat/test_databricks_chat_transformation.py index 9cd17bd3580..9326ed6a49a 100644 --- a/tests/unit/llms/databricks/chat/test_databricks_chat_transformation.py +++ b/tests/unit/llms/databricks/chat/test_databricks_chat_transformation.py @@ -1,7 +1,9 @@ +import copy import json import pytest from fastapi.testclient import TestClient +from pydantic import BaseModel, ConfigDict from unittest.mock import MagicMock, patch @@ -21,6 +23,27 @@ import httpx import respx +JSON_SCHEMA_RESPONSE_FORMAT: Final = { + "type": "json_schema", + "json_schema": { + "name": "P", + "strict": True, + "schema": { + "$defs": { + "Person": { + "type": "object", + "properties": {"name": {"type": "string"}}, + "required": ["name"], + } + }, + "type": "object", + "properties": {"p": {"$ref": "#/$defs/Person"}}, + "required": ["p"], + }, + }, +} + + @pytest.fixture() def _use_local_model_cost_map(monkeypatch): monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") @@ -883,3 +906,68 @@ def test_completion_merges_system_messages_when_one_has_empty_content(respx_mock {"role": "system", "content": "You are terse."}, {"role": "user", "content": "Hello"}, ] + + +@pytest.mark.parametrize( + "model", + ( + "databricks-meta-llama-3-3-70b-instruct", + "databricks-qwen35-122b-a10b", + "databricks-gpt-oss-120b", + ), +) +def test_databricks_non_claude_json_schema_preserves_refs(model: str) -> None: + optional_params: Final = litellm.utils.get_optional_params( + model=model, + custom_llm_provider="databricks", + response_format=copy.deepcopy(JSON_SCHEMA_RESPONSE_FORMAT), + ) + + assert optional_params["response_format"] == JSON_SCHEMA_RESPONSE_FORMAT + + +def test_databricks_claude_json_schema_preserves_refs_in_tool_parameters() -> None: + optional_params: Final = litellm.utils.get_optional_params( + model="databricks-claude-haiku-4-5", + custom_llm_provider="databricks", + response_format=copy.deepcopy(JSON_SCHEMA_RESPONSE_FORMAT), + ) + + assert "response_format" not in optional_params + assert optional_params["tools"] == [ + { + "type": "function", + "function": { + "name": "json_tool_call", + "parameters": JSON_SCHEMA_RESPONSE_FORMAT["json_schema"]["schema"], + }, + } + ] + + +def test_databricks_pydantic_json_schema_preserves_nested_refs() -> None: + class Person(BaseModel): + model_config = ConfigDict(frozen=True) + + name: str + + class Order(BaseModel): + model_config = ConfigDict(frozen=True) + + person: Person + + optional_params: Final = litellm.utils.get_optional_params( + model="databricks-meta-llama-3-3-70b-instruct", + custom_llm_provider="databricks", + response_format=Order, + ) + schema: Final = optional_params["response_format"]["json_schema"]["schema"] + + assert schema["properties"]["person"] == {"$ref": "#/$defs/Person"} + assert schema["$defs"]["Person"] == { + "additionalProperties": False, + "properties": {"name": {"title": "Name", "type": "string"}}, + "required": ["name"], + "title": "Person", + "type": "object", + } From 2f19d8ed87289607ef61024c2d518901f4abecfb Mon Sep 17 00:00:00 2001 From: mrinal-berri Date: Tue, 20 Oct 2026 15:32:54 -0700 Subject: [PATCH 13/66] fix(databricks): send a single plain text block as a string for non-Claude models (#45686) Backport of #45686 to stable/1.104.x. Cherry-picked from 1aee1a21edec8606f6128ae97afe4f3c71bfe01f (main). Test-file import conflict resolved by keeping the line's imports plus this PR's own. --- .../llms/databricks/chat/transformation.py | 12 +- .../providers/test_databricks_chat_wire.py | 577 ++++++++++++++++++ .../test_databricks_chat_transformation.py | 116 ++++ .../test_responses_api_bridge_flag.py | 7 +- 4 files changed, 706 insertions(+), 6 deletions(-) diff --git a/litellm/llms/databricks/chat/transformation.py b/litellm/llms/databricks/chat/transformation.py index 9e88fffbeef..b51b6815210 100644 --- a/litellm/llms/databricks/chat/transformation.py +++ b/litellm/llms/databricks/chat/transformation.py @@ -75,6 +75,15 @@ def _is_bare_assistant_message(message_dict: Mapping[str, object]) -> bool: ) +def _collapse_single_text_block(message: Mapping[str, object]) -> Mapping[str, object]: + content: Final = message.get("content") + match content: + case [{"type": "text", "text": str() as text}] if content == [{"type": "text", "text": text}]: + return {**message, "content": text} + case _: + return message + + def _sanitize_empty_content(message_dict: dict[str, object]) -> None: """ Remove or filter content so empty text blocks are not sent. @@ -462,6 +471,7 @@ class DatabricksConfig(DatabricksBase, OpenAILikeChatConfig, AnthropicConfig): Databricks does not support: - 'name' in user message. - litellm's internal `thinking_blocks` / `reasoning_content` on assistant messages. + - non-Claude json_object "json" checks read only string content, so a single text block is sent as a string. """ new_messages = [] for idx, message in enumerate(messages): @@ -477,7 +487,7 @@ class DatabricksConfig(DatabricksBase, OpenAILikeChatConfig, AnthropicConfig): _sanitize_empty_content(cast(dict[str, Any], _message)) if _is_bare_assistant_message(_message): continue - new_messages.append(_message) + new_messages.append(_collapse_single_text_block(_message) if "claude" not in model else _message) if "claude" not in model: new_messages = _split_parallel_tool_calls( diff --git a/tests/integration/providers/test_databricks_chat_wire.py b/tests/integration/providers/test_databricks_chat_wire.py index f6192d32c31..3d7f273279f 100644 --- a/tests/integration/providers/test_databricks_chat_wire.py +++ b/tests/integration/providers/test_databricks_chat_wire.py @@ -3,11 +3,15 @@ import json import uuid from collections.abc import Mapping from concurrent.futures import ThreadPoolExecutor +from pathlib import Path from typing import Final, Literal, TypeAlias +import anthropic +import openai import pytest from integration._support.client import Gateway, eventually from integration._support.database import read_rows +from integration._support.process import owned_proxy_process from integration._support.wire import Reply, Request, wire_server from pydantic import BaseModel, ConfigDict, JsonValue, TypeAdapter @@ -201,6 +205,226 @@ def test_databricks_stream_final_usage_chunk_reaches_client_and_spend_log(gatewa assert (rows[0]["prompt_tokens"], rows[0]["completion_tokens"], rows[0]["total_tokens"]) == (12011, 8, 12019) +def _shape_reply(identity: str, stream: bool) -> Reply: + if stream: + chunks: Final = ( + _frame( + identity, + [{"index": 0, "delta": {"role": "assistant", "content": "ok"}, "finish_reason": None}], + ), + _frame(identity, [{"index": 0, "delta": {}, "finish_reason": "stop"}]), + b"data: [DONE]\n\n", + ) + return Reply(content_type="text/event-stream", chunks=chunks) + + body: Final = { + "id": identity, + "object": "chat.completion", + "created": 1, + "model": _BACKEND, + "choices": [ + { + "index": 0, + "message": {"role": "assistant", "content": "ok"}, + "finish_reason": "stop", + } + ], + "usage": {"prompt_tokens": 1, "completion_tokens": 1, "total_tokens": 2}, + } + return Reply(body=json.dumps(body).encode()) + + +@pytest.mark.parametrize( + "case,endpoint,provider_model,request_body,expected_messages,responses_mode,upstream_path", + [ + pytest.param( + "chat_nonstream", + "/v1/chat/completions", + "databricks-meta-llama-3-3-70b-instruct", + { + "messages": [{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}], + "response_format": {"type": "json_object"}, + }, + [{"role": "user", "content": "Reply in JSON"}], + False, + "/chat/completions", + id="A1-chat-nonstream", + ), + pytest.param( + "chat_stream", + "/v1/chat/completions", + "databricks-meta-llama-3-3-70b-instruct", + { + "messages": [{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}], + "response_format": {"type": "json_object"}, + "stream": True, + }, + [{"role": "user", "content": "Reply in JSON"}], + False, + "/chat/completions", + id="A2-chat-stream", + ), + pytest.param( + "responses-mode-bridge", + "/v1/chat/completions", + "databricks-meta-llama-3-1-8b-instruct", + { + "messages": [{"role": "user", "content": "Reply in JSON"}], + "response_format": {"type": "json_object"}, + }, + [{"role": "user", "content": "Reply in JSON"}], + True, + "/chat/completions", + id="A3-responses-mode", + ), + pytest.param( + "responses-mode-bridge-unity-catalog", + "/v1/chat/completions", + "system.ai.deepseek-v4-1-flash", + { + "messages": [{"role": "user", "content": "Reply in JSON with key a. hi"}], + "response_format": {"type": "json_object"}, + }, + [{"role": "user", "content": "Reply in JSON with key a. hi"}], + True, + "/ai-gateway/mlflow/v1/chat/completions", + id="A3b-responses-mode-unity-catalog-model", + ), + pytest.param( + "messages-endpoint", + "/v1/messages", + "databricks-meta-llama-3-3-70b-instruct", + { + "max_tokens": 32, + "messages": [{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}], + }, + [{"role": "user", "content": "Reply in JSON"}], + False, + "/chat/completions", + id="A4-messages", + ), + pytest.param( + "responses-endpoint", + "/v1/responses", + "databricks-meta-llama-3-3-70b-instruct", + {"input": [{"role": "user", "content": [{"type": "input_text", "text": "Reply in JSON"}]}]}, + [{"role": "user", "content": "Reply in JSON"}], + False, + "/chat/completions", + id="A5-responses-list-input", + ), + ], +) +def test_databricks_non_claude_single_text_block_reaches_upstream_as_string( + gateway: Gateway, + case: str, + endpoint: str, + provider_model: str, + request_body: dict[str, JsonValue], + expected_messages: list[JsonValue], + responses_mode: bool, + upstream_path: str, +) -> None: + identity: Final = f"databricks-single-text-{case}-{uuid.uuid4().hex}" + streaming: Final = request_body.get("stream") is True + + def respond(request: Request) -> Reply: + assert request.method == "POST" + body: Final = _JSON_OBJECT.validate_json(request.body) + assert body["messages"] == expected_messages, body["messages"] + return _shape_reply(identity, streaming) + + with wire_server(respond) as wire, gateway.scenario() as scenario: + model: Final = scenario.model( + model=f"databricks/{provider_model}", + api_base=wire.url, + api_key=_API_KEY, + model_info={"mode": "responses"} if responses_mode else None, + ) + headers: Final = {"anthropic-version": "2023-06-01"} if endpoint == "/v1/messages" else {} + body: Final = {"model": model, **request_body} + if streaming: + with gateway.client.stream( + "POST", endpoint, json=body, headers={"Authorization": f"Bearer {gateway.key}", **headers} + ) as response: + assert response.status_code == 200, response.read() + lines: Final = tuple(line for line in response.iter_lines() if line.startswith("data: ")) + assert lines[-1] == "data: [DONE]", lines + assert any('"content":"ok"' in line for line in lines), lines + else: + response: Final = gateway.request("POST", endpoint, body, headers=headers) + assert response.status_code == 200, response.text + assert _JSON_OBJECT.validate_json(response.content)["id"] + assert [(request.method, request.target) for request in wire.drain()] == [("POST", upstream_path)] + + +@pytest.mark.parametrize( + "case,provider_model,content,expected_content", + [ + pytest.param( + "cache-control", + "databricks-meta-llama-3-3-70b-instruct", + [{"type": "text", "text": "Reply in JSON", "cache_control": {"type": "ephemeral"}}], + [{"type": "text", "text": "Reply in JSON", "cache_control": {"type": "ephemeral"}}], + id="B1-cache-control-stays-list", + ), + pytest.param( + "two-text-blocks", + "databricks-meta-llama-3-3-70b-instruct", + [{"type": "text", "text": "Reply"}, {"type": "text", "text": " in JSON"}], + [{"type": "text", "text": "Reply"}, {"type": "text", "text": " in JSON"}], + id="B2-two-text-blocks-stays-list", + ), + pytest.param( + "text-and-image", + "databricks-meta-llama-3-3-70b-instruct", + [ + {"type": "text", "text": "Reply in JSON"}, + {"type": "image_url", "image_url": {"url": "https://example.com/image.png"}}, + ], + [ + {"type": "text", "text": "Reply in JSON"}, + {"type": "image_url", "image_url": {"url": "https://example.com/image.png"}}, + ], + id="B3-text-and-image-stays-list", + ), + pytest.param( + "claude", + "databricks-claude-opus-5-5", + [{"type": "text", "text": "Reply in JSON"}], + [{"type": "text", "text": "Reply in JSON"}], + id="B4-claude-stays-list", + ), + ], +) +def test_databricks_list_content_stays_list( + gateway: Gateway, + case: str, + provider_model: str, + content: list[JsonValue], + expected_content: list[JsonValue], +) -> None: + identity: Final = f"databricks-list-content-{case}-{uuid.uuid4().hex}" + expected_messages: Final = [{"role": "user", "content": expected_content}] + + def respond(request: Request) -> Reply: + assert request.method == "POST" + body: Final = _JSON_OBJECT.validate_json(request.body) + assert body["messages"] == expected_messages, body["messages"] + return _shape_reply(identity, False) + + with wire_server(respond) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{provider_model}", api_base=wire.url, api_key=_API_KEY) + response: Final = gateway.request( + "POST", + "/v1/chat/completions", + {"model": model, "messages": [{"role": "user", "content": content}]}, + ) + assert response.status_code == 200, response.text + assert _JSON_OBJECT.validate_json(response.content)["id"] + assert [(request.method, request.target) for request in wire.drain()] == [("POST", "/chat/completions")] + + def test_databricks_json_schema_refs_are_preserved_in_chat_completions(gateway: Gateway) -> None: def respond(request: Request) -> Reply: assert request.method == "POST" @@ -868,3 +1092,356 @@ def test_databricks_json_schema_burst_through_an_upstream_outage_keeps_every_ref ) assert tuple(_outcome(*result) for result in results) == expected assert tuple(_outcome(*result) for result in recovered) == ((200, _EXPECTED_JSON),) * len(recovery) + + +_LLAMA_BACKEND: Final = "databricks-meta-llama-3-3-70b-instruct" +_NO_CACHE: Final[dict[str, JsonValue]] = {"no-cache": True} + + +def _one_block(text: str) -> list[JsonValue]: + return [{"type": "text", "text": text}] + + +def _plain_reply(_request: Request) -> Reply: + return _shape_reply(f"databricks-plain-{uuid.uuid4().hex}", False) + + +def _sent_messages(request: Request) -> JsonValue: + return _JSON_OBJECT.validate_json(request.body)["messages"] + + +def _tool_call(identity: str, city: str) -> dict[str, JsonValue]: + return { + "id": identity, + "type": "function", + "function": {"name": "get_weather", "arguments": json.dumps({"city": city})}, + } + + +@pytest.mark.parametrize( + "messages,expected_messages", + [ + pytest.param( + [ + {"role": "system", "content": _one_block("Alpha rule.")}, + {"role": "system", "content": _one_block("Bravo rule.")}, + {"role": "user", "content": _one_block("Reply in JSON")}, + ], + [ + {"role": "system", "content": "Alpha rule.\n\nBravo rule."}, + {"role": "user", "content": "Reply in JSON"}, + ], + id="C1-two-one-block-system-messages", + ), + pytest.param( + [ + {"role": "system", "content": _one_block("Alpha rule.")}, + {"role": "developer", "content": _one_block("Bravo rule.")}, + {"role": "user", "content": "Reply in JSON"}, + ], + [ + {"role": "system", "content": "Alpha rule.\n\nBravo rule."}, + {"role": "user", "content": "Reply in JSON"}, + ], + id="C2-system-then-developer-one-block", + ), + pytest.param( + [ + {"role": "system", "content": _one_block("Alpha rule.")}, + {"role": "system", "content": "Bravo rule."}, + {"role": "user", "content": "Reply in JSON"}, + ], + [ + {"role": "system", "content": "Alpha rule.\n\nBravo rule."}, + {"role": "user", "content": "Reply in JSON"}, + ], + id="C3-one-block-then-string-system", + ), + pytest.param( + [ + {"role": "system", "content": _one_block("Alpha rule.")}, + { + "role": "system", + "content": [{"type": "text", "text": "Bravo", "cache_control": {"type": "ephemeral"}}], + }, + {"role": "user", "content": "Reply in JSON"}, + ], + [ + { + "role": "system", + "content": [ + {"type": "text", "text": "Alpha rule."}, + {"type": "text", "text": "Bravo", "cache_control": {"type": "ephemeral"}}, + ], + }, + {"role": "user", "content": "Reply in JSON"}, + ], + id="C4-one-block-then-cache-marked-system-stays-parts", + ), + pytest.param( + [ + {"role": "user", "content": _one_block("Weather in Paris and Rome?")}, + { + "role": "assistant", + "content": _one_block("Checking both."), + "tool_calls": [_tool_call("call-paris", "Paris"), _tool_call("call-rome", "Rome")], + }, + {"role": "tool", "tool_call_id": "call-paris", "content": _one_block("18C")}, + {"role": "tool", "tool_call_id": "call-rome", "content": _one_block("22C")}, + ], + [ + {"role": "user", "content": "Weather in Paris and Rome?"}, + {"role": "assistant", "content": "Checking both.", "tool_calls": [_tool_call("call-paris", "Paris")]}, + {"role": "tool", "tool_call_id": "call-paris", "content": "18C"}, + {"role": "assistant", "tool_calls": [_tool_call("call-rome", "Rome")]}, + {"role": "tool", "tool_call_id": "call-rome", "content": "22C"}, + ], + id="C5-parallel-tool-results-split-and-collapsed", + ), + pytest.param( + [ + {"role": "user", "content": [{"type": "text", "text": "Reply in JSON", "cache_control": None}]}, + {"role": "assistant", "content": [{"type": "text", "text": "ok", "annotations": []}]}, + {"role": "user", "content": _one_block(" ")}, + {"role": "user", "content": _one_block("x" * 5120)}, + ], + [ + {"role": "user", "content": [{"type": "text", "text": "Reply in JSON", "cache_control": None}]}, + {"role": "assistant", "content": [{"type": "text", "text": "ok", "annotations": []}]}, + {"role": "user"}, + {"role": "user", "content": "x" * 5120}, + ], + id="F1-extra-keys-stay-list-blank-dropped-5kb-collapsed", + ), + ], +) +def test_databricks_non_claude_message_shapes_reach_upstream( + gateway: Gateway, messages: list[JsonValue], expected_messages: list[JsonValue] +) -> None: + with wire_server(_plain_reply) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + response: Final = gateway.request( + "POST", + "/v1/chat/completions", + {"model": model, "messages": messages, "cache": _NO_CACHE}, + ) + received: Final = wire.drain() + assert response.status_code == 200, response.text + assert [(request.method, request.target) for request in received] == [("POST", "/chat/completions")] + assert _sent_messages(received[0]) == expected_messages + + +def test_databricks_responses_instructions_and_one_block_developer_reach_upstream_joined(gateway: Gateway) -> None: + with wire_server(_plain_reply) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + response: Final = gateway.request( + "POST", + "/v1/responses", + { + "model": model, + "instructions": "Alpha rule.", + "input": [ + {"role": "developer", "content": [{"type": "input_text", "text": "Bravo rule."}]}, + {"role": "user", "content": [{"type": "input_text", "text": "Reply in JSON"}]}, + ], + }, + ) + received: Final = wire.drain() + assert response.status_code == 200, response.text + assert [(request.method, request.target) for request in received] == [("POST", "/chat/completions")] + assert _sent_messages(received[0]) == [ + {"role": "system", "content": "Alpha rule.\n\nBravo rule."}, + {"role": "user", "content": "Reply in JSON"}, + ] + + +def test_databricks_fallback_sends_the_collapsed_string_to_both_deployments(gateway: Gateway) -> None: + marker: Final = uuid.uuid4().hex + fallback_backend: Final = "databricks-meta-llama-3-1-8b-instruct" + + def respond(request: Request) -> Reply: + if _JSON_OBJECT.validate_json(request.body)["model"] == _LLAMA_BACKEND: + return Reply(status=500, body=b'{"error_code": "INTERNAL_ERROR", "message": "primary deployment is down"}') + return _shape_reply(f"databricks-fallback-{marker}", False) + + with wire_server(respond) as wire, gateway.scenario() as scenario: + primary: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + fallback: Final = scenario.model(model=f"databricks/{fallback_backend}", api_base=wire.url, api_key=_API_KEY) + response: Final = gateway.request( + "POST", + "/v1/chat/completions", + { + "model": primary, + "messages": [{"role": "user", "content": _one_block(f"Reply in JSON {marker}")}], + "response_format": {"type": "json_object"}, + "fallbacks": [fallback], + "num_retries": 0, + "cache": _NO_CACHE, + }, + ) + received: Final = wire.drain() + assert response.status_code == 200, response.text + assert _JSON_OBJECT.validate_json(response.content)["id"] == f"databricks-fallback-{marker}" + assert [_JSON_OBJECT.validate_json(request.body)["model"] for request in received] == [ + _LLAMA_BACKEND, + fallback_backend, + ] + assert [_sent_messages(request) for request in received] == [ + [{"role": "user", "content": f"Reply in JSON {marker}"}], + ] * 2 + + +def _proxy_root(gateway: Gateway) -> str: + return str(gateway.client.base_url).rstrip("/") + + +def test_databricks_openai_sdk_sync_one_block_reaches_upstream_as_string_and_logs_spend(gateway: Gateway) -> None: + identity: Final = f"databricks-openai-sdk-{uuid.uuid4().hex}" + with ( + wire_server(lambda _request: _shape_reply(identity, False)) as wire, + gateway.scenario() as scenario, + openai.OpenAI(base_url=f"{_proxy_root(gateway)}/v1", api_key=gateway.key, max_retries=0) as client, + ): + model: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + completion: Final = client.chat.completions.create( + model=model, + messages=[{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}], + response_format={"type": "json_object"}, + extra_body={"cache": _NO_CACHE}, + ) + received: Final = wire.drain() + assert (completion.id, completion.choices[0].message.content) == (identity, "ok") + assert [_sent_messages(request) for request in received] == [[{"role": "user", "content": "Reply in JSON"}]] + rows: Final = eventually( + lambda: read_rows('SELECT status, call_type FROM "LiteLLM_SpendLogs" WHERE request_id=%s', (identity,)), + lambda values: len(values) == 1, + seconds=70, + ) + assert (rows[0]["status"], rows[0]["call_type"]) == ("success", "acompletion") + + +async def test_databricks_openai_sdk_async_stream_one_block_reaches_upstream_as_string(gateway: Gateway) -> None: + identity: Final = f"databricks-openai-async-{uuid.uuid4().hex}" + with wire_server(lambda _request: _shape_reply(identity, True)) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + async with openai.AsyncOpenAI( + base_url=f"{_proxy_root(gateway)}/v1", api_key=gateway.key, max_retries=0 + ) as client: + stream: Final = await client.chat.completions.create( + model=model, + messages=[{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}], + response_format={"type": "json_object"}, + stream=True, + extra_body={"cache": _NO_CACHE}, + ) + chunks: Final = [chunk async for chunk in stream] + received: Final = wire.drain() + assert {chunk.id for chunk in chunks} == {identity} + assert "".join(chunk.choices[0].delta.content or "" for chunk in chunks if chunk.choices) == "ok" + assert [_sent_messages(request) for request in received] == [[{"role": "user", "content": "Reply in JSON"}]] + + +async def test_databricks_anthropic_sdk_async_stream_one_block_system_and_user_reach_upstream_as_strings( + gateway: Gateway, +) -> None: + identity: Final = f"databricks-anthropic-async-{uuid.uuid4().hex}" + with wire_server(lambda _request: _shape_reply(identity, True)) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + async with anthropic.AsyncAnthropic( + base_url=_proxy_root(gateway), api_key=gateway.key, max_retries=0 + ) as client: + async with client.messages.stream( + model=model, + max_tokens=32, + system=[{"type": "text", "text": "Reply in JSON."}], + messages=[{"role": "user", "content": [{"type": "text", "text": "What is 2+2?"}]}], + ) as stream: + final: Final = await stream.get_final_message() + received: Final = wire.drain() + assert [block.text for block in final.content if block.type == "text"] == ["ok"] + assert [_sent_messages(request) for request in received] == [ + [{"role": "system", "content": "Reply in JSON."}, {"role": "user", "content": "What is 2+2?"}] + ] + + +def test_databricks_one_block_burst_through_an_upstream_outage_reaches_upstream_as_strings(gateway: Gateway) -> None: + plan: Final = tuple(_burst_request(index) for index in range(24)) + + def respond(request: Request) -> Reply: + if _OUTAGE.encode() in request.body: + error: Final = {"error_code": "TEMPORARILY_UNAVAILABLE", "message": _OUTAGE_MESSAGE} + return Reply(status=503, body=json.dumps(error).encode()) + body: Final = _JSON_OBJECT.validate_json(request.body) + return _upstream_reply(_JSON_SCHEMA_BACKEND, body.get("stream") is True) + + def one_block_body(endpoint: _Endpoint, model: str, stream: bool, prompt: str) -> dict[str, JsonValue]: + body: Final = _client_body(endpoint, model, stream, prompt) + match endpoint: + case "responses": + return {**body, "input": [{"role": "user", "content": [{"type": "input_text", "text": prompt}]}]} + case "chat" | "messages": + return {**body, "messages": [{"role": "user", "content": _one_block(prompt)}]} + + with wire_server(respond) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_JSON_SCHEMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + prompts: Final = tuple( + f"{_JSON_SCHEMA_PROMPT} {index} {_OUTAGE if down else ''}".strip() + for index, (_e, _s, down) in enumerate(plan) + ) + bodies: Final = tuple( + one_block_body(endpoint, model, stream, prompt) for (endpoint, stream, _down), prompt in zip(plan, prompts) + ) + with ThreadPoolExecutor(max_workers=12) as pool: + results: Final = tuple(pool.map(_call, itertools.repeat(gateway), (e for e, _s, _d in plan), bodies)) + received: Final = wire.drain() + assert sorted(json.dumps(_sent_messages(request)) for request in received) == sorted( + json.dumps([{"role": "user", "content": prompt}]) for prompt in prompts + ) + expected: Final = tuple( + (503, _OUTAGE_MESSAGE) if down else (200, _EXPECTED_JSON) for _endpoint, _stream, down in plan + ) + assert tuple(_outcome(*result) for result in results) == expected + + +def test_databricks_transform_request_shows_the_collapsed_string(gateway: Gateway, tmp_path: Path) -> None: + environment: Final = { + "DATABRICKS_API_BASE": "https://databricks.invalid/serving-endpoints", + "DATABRICKS_API_KEY": _API_KEY, + } + with owned_proxy_process(gateway, tmp_path, environment) as owned: + response: Final = owned.gateway.request( + "POST", + "/utils/transform_request", + { + "call_type": "completion", + "request_body": { + "model": f"databricks/{_LLAMA_BACKEND}", + "messages": [{"role": "user", "content": _one_block("Reply in JSON")}], + }, + }, + ) + assert response.status_code == 200, response.text + body: Final = _JSON_OBJECT.validate_json(response.content) + assert body["error"] is None, body + assert body["raw_request_api_base"] == "https://databricks.invalid/serving-endpoints/chat/completions" + sent: Final = body["raw_request_body"] + assert isinstance(sent, dict), body + assert sent["messages"] == [{"role": "user", "content": "Reply in JSON"}] + + +def test_databricks_non_string_text_block_is_rejected_before_reaching_upstream(gateway: Gateway) -> None: + with wire_server(_plain_reply) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"databricks/{_LLAMA_BACKEND}", api_base=wire.url, api_key=_API_KEY) + response: Final = gateway.request( + "POST", + "/v1/chat/completions", + { + "model": model, + "messages": [{"role": "user", "content": [{"type": "text", "text": 42}]}], + "cache": _NO_CACHE, + }, + ) + received: Final = wire.drain() + assert response.status_code == 400, response.text + assert "'int' object has no attribute 'strip'" in response.text + assert received == () diff --git a/tests/unit/llms/databricks/chat/test_databricks_chat_transformation.py b/tests/unit/llms/databricks/chat/test_databricks_chat_transformation.py index 9326ed6a49a..dfa8538c387 100644 --- a/tests/unit/llms/databricks/chat/test_databricks_chat_transformation.py +++ b/tests/unit/llms/databricks/chat/test_databricks_chat_transformation.py @@ -2,6 +2,7 @@ import copy import json import pytest +from pydantic import TypeAdapter from fastapi.testclient import TestClient from pydantic import BaseModel, ConfigDict @@ -18,6 +19,7 @@ from litellm.llms.databricks.chat.transformation import ( DatabricksConfig, _sanitize_empty_content, ) +from litellm.types.llms.openai import AllMessageValues from typing import Final import httpx import respx @@ -306,6 +308,119 @@ def test_transform_request_preserves_unity_model_service_name(): assert result["model"] == "system.ai.kimi-k3" +@pytest.mark.parametrize( + "model,messages,optional_params,expected_content", + [ + pytest.param( + "databricks-meta-llama-3-3-70b-instruct", + [{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}], + {"response_format": {"type": "json_object"}}, + "Reply in JSON", + id="user", + ), + pytest.param( + "databricks-meta-llama-3-3-70b-instruct", + [{"role": "system", "content": [{"type": "text", "text": "Reply in JSON"}]}], + {"response_format": {"type": "json_object"}}, + "Reply in JSON", + id="system", + ), + pytest.param( + "databricks-meta-llama-3-3-70b-instruct", + [{"role": "assistant", "content": [{"type": "text", "text": "Reply in JSON"}]}], + {"response_format": {"type": "json_object"}}, + "Reply in JSON", + id="assistant", + ), + pytest.param( + "databricks-meta-llama-3-3-70b-instruct", + [ + { + "role": "tool", + "tool_call_id": "call_1", + "content": [{"type": "text", "text": "Reply in JSON"}], + } + ], + {"response_format": {"type": "json_object"}}, + "Reply in JSON", + id="tool", + ), + pytest.param( + "databricks-meta-llama-3-3-70b-instruct", + [ + { + "role": "user", + "content": [{"type": "text", "text": "Reply in JSON", "cache_control": {"type": "ephemeral"}}], + } + ], + {"response_format": {"type": "json_object"}}, + [{"type": "text", "text": "Reply in JSON", "cache_control": {"type": "ephemeral"}}], + id="cache-control", + ), + pytest.param( + "databricks-meta-llama-3-3-70b-instruct", + [{"role": "user", "content": [{"type": "text", "text": "Reply"}, {"type": "text", "text": " in JSON"}]}], + {"response_format": {"type": "json_object"}}, + [{"type": "text", "text": "Reply"}, {"type": "text", "text": " in JSON"}], + id="multiple-text-blocks", + ), + pytest.param( + "databricks-meta-llama-3-3-70b-instruct", + [ + { + "role": "user", + "content": [ + {"type": "text", "text": "Reply in JSON"}, + {"type": "image_url", "image_url": {"url": "https://example.com/image.png"}}, + ], + } + ], + {"response_format": {"type": "json_object"}}, + [ + {"type": "text", "text": "Reply in JSON"}, + {"type": "image_url", "image_url": {"url": "https://example.com/image.png"}}, + ], + id="text-and-image", + ), + pytest.param( + "databricks-meta-llama-3-3-70b-instruct", + [{"role": "user", "content": "Reply in JSON"}], + {"response_format": {"type": "json_object"}}, + "Reply in JSON", + id="plain-string", + ), + pytest.param( + "databricks-claude-sonnet-5", + [{"role": "user", "content": [{"type": "text", "text": "Reply in JSON"}]}], + {"response_format": {"type": "json_object"}}, + [{"type": "text", "text": "Reply in JSON"}], + id="claude", + ), + ], +) +def test_transform_request_collapses_single_plain_text_block_for_non_claude_models( + model: str, + messages: list[AllMessageValues], + optional_params: dict[str, object], + expected_content: object, +) -> None: + config: Final[DatabricksConfig] = DatabricksConfig() + result: Final[dict[str, object]] = TypeAdapter(dict[str, object]).validate_python( + config.transform_request( # pyright: ignore[reportUnknownMemberType] # inherited hook is untyped + model=model, + messages=messages, + optional_params=optional_params, + litellm_params={}, + headers={}, + ) + ) + outgoing_messages: Final[list[dict[str, object]]] = TypeAdapter(list[dict[str, object]]).validate_python( + result["messages"] + ) + + assert outgoing_messages == [{**messages[0], "content": expected_content}] + + def test_transform_request_strips_thinking_blocks_and_reasoning_content(): """Regression for LIT-6762: replaying an assistant turn that litellm decorated with `thinking_blocks` / `reasoning_content` made Databricks 400 with @@ -914,6 +1029,7 @@ def test_completion_merges_system_messages_when_one_has_empty_content(respx_mock "databricks-meta-llama-3-3-70b-instruct", "databricks-qwen35-122b-a10b", "databricks-gpt-oss-120b", + "system.ai.deepseek-v4-1-flash", ), ) def test_databricks_non_claude_json_schema_preserves_refs(model: str) -> None: diff --git a/tests/unit/responses/test_responses_api_bridge_flag.py b/tests/unit/responses/test_responses_api_bridge_flag.py index 642495fab86..01bce88e372 100644 --- a/tests/unit/responses/test_responses_api_bridge_flag.py +++ b/tests/unit/responses/test_responses_api_bridge_flag.py @@ -355,11 +355,8 @@ class TestUseResponsesApiBridgeFlag: assert upstream.call_count == 1 request_body: Final = json.loads(upstream.calls[0].request.read()) assert request_body["messages"] == [ - { - "role": "system", - "content": [{"type": "text", "text": "You are terse."}, {"type": "text", "text": "Skills: none."}], - }, - {"role": "user", "content": [{"type": "text", "text": "Hello"}]}, + {"role": "system", "content": "You are terse.\n\nSkills: none."}, + {"role": "user", "content": "Hello"}, ] assert "client_metadata" not in request_body assert request_body["chat_template_kwargs"] == {"thinking": True} From 61c5d953ee526f1b9253b1c5e987a90bcf9a399c Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 20 Oct 2026 15:44:17 -0700 Subject: [PATCH 14/66] fix(anthropic): add the dangerous-tool-use beta when a /v1/messages request carries safeguards (#43955) Backport of #43955 to stable/1.104.x. Cherry-picked from eb5295b20c94ccb0ac7cd59df666280a404c24a7 (main). Adapted to the line: the transformation lives under anthropic/experimental_pass_through, the integration tests live under tests/integration/providers, and the CLI-beta wire assertion change is dropped since that test is not on the line. --- litellm/anthropic_beta_headers_manager.py | 45 +- .../messages/transformation.py | 11 +- litellm/llms/custom_httpx/llm_http_handler.py | 34 +- .../openai_like/messages/transformation.py | 2 + .../test_anthropic_safeguards_beta_chaos.py | 348 ++++++++ .../test_anthropic_safeguards_beta_wire.py | 809 ++++++++++++++++++ ...azure_anthropic_messages_transformation.py | 52 ++ .../custom_httpx/test_llm_http_handler.py | 42 + ..._like_anthropic_messages_transformation.py | 23 + 9 files changed, 1343 insertions(+), 23 deletions(-) create mode 100644 tests/integration/providers/test_anthropic_safeguards_beta_chaos.py create mode 100644 tests/integration/providers/test_anthropic_safeguards_beta_wire.py diff --git a/litellm/anthropic_beta_headers_manager.py b/litellm/anthropic_beta_headers_manager.py index 7e7099a53b0..35df2a09004 100644 --- a/litellm/anthropic_beta_headers_manager.py +++ b/litellm/anthropic_beta_headers_manager.py @@ -22,17 +22,28 @@ Environment Variables: - LITELLM_ANTHROPIC_BETA_HEADERS_URL: Custom URL for remote config (optional) """ +import asyncio import json import os +import threading +from collections.abc import Mapping +from concurrent.futures import ThreadPoolExecutor +from functools import cache from importlib.resources import files -from typing import Final +from typing import Final, TypeAlias import httpx +from pydantic import TypeAdapter from litellm.litellm_core_utils.litellm_logging import verbose_logger # Cache for the loaded configuration _BETA_HEADERS_CONFIG: dict | None = None +_BETA_HEADERS_CONFIG_LOCK: Final = threading.Lock() +_BETA_HEADERS_CONFIG_LOADER: Final = ThreadPoolExecutor(max_workers=1, thread_name_prefix="litellm-beta-headers-config") + +BetaHeadersConfig: TypeAlias = Mapping[str, str | Mapping[str, str | None]] +_BETA_HEADERS_CONFIG_ADAPTER: Final = TypeAdapter(BetaHeadersConfig) class GetAnthropicBetaHeadersConfig: @@ -174,13 +185,27 @@ def _load_beta_headers_config() -> dict: if _BETA_HEADERS_CONFIG is not None: return _BETA_HEADERS_CONFIG - # Get the URL from environment or use default - from litellm import anthropic_beta_headers_url + with _BETA_HEADERS_CONFIG_LOCK: + if _BETA_HEADERS_CONFIG is not None: + return _BETA_HEADERS_CONFIG - _BETA_HEADERS_CONFIG = get_beta_headers_config(url=anthropic_beta_headers_url) - verbose_logger.debug("Loaded and cached beta headers config") + # Get the URL from environment or use default + from litellm import anthropic_beta_headers_url - return _BETA_HEADERS_CONFIG + _BETA_HEADERS_CONFIG = get_beta_headers_config(url=anthropic_beta_headers_url) + verbose_logger.debug("Loaded and cached beta headers config") + + return _BETA_HEADERS_CONFIG + + +async def aload_beta_headers_config() -> None: + if _BETA_HEADERS_CONFIG is None: + await asyncio.get_running_loop().run_in_executor(_BETA_HEADERS_CONFIG_LOADER, _load_beta_headers_config) + + +@cache +def _bundled_beta_headers_config() -> BetaHeadersConfig: + return _BETA_HEADERS_CONFIG_ADAPTER.validate_python(GetAnthropicBetaHeadersConfig.load_local_beta_headers_config()) def reload_beta_headers_config() -> dict: @@ -288,6 +313,14 @@ def is_beta_header_supported( return beta_header in provider_mapping and provider_mapping[beta_header] is not None +def is_beta_header_supported_by_bundled_config(beta_header: str, provider: str) -> bool: + config: Final = _bundled_beta_headers_config() + aliases: Final = config.get("provider_aliases", {}) + canonical_provider: Final = (aliases.get(provider) if isinstance(aliases, Mapping) else None) or provider + provider_mapping: Final = config.get(canonical_provider, {}) + return isinstance(provider_mapping, Mapping) and provider_mapping.get(beta_header) is not None + + def get_provider_beta_header( anthropic_beta_header: str, provider: str, diff --git a/litellm/llms/anthropic/experimental_pass_through/messages/transformation.py b/litellm/llms/anthropic/experimental_pass_through/messages/transformation.py index a83e23d83d5..91e84027163 100644 --- a/litellm/llms/anthropic/experimental_pass_through/messages/transformation.py +++ b/litellm/llms/anthropic/experimental_pass_through/messages/transformation.py @@ -3,6 +3,7 @@ from typing import Any, Final import httpx +from litellm.anthropic_beta_headers_manager import is_beta_header_supported_by_bundled_config from litellm.exceptions import AuthenticationError from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj from litellm.litellm_core_utils.litellm_logging import verbose_logger @@ -611,6 +612,7 @@ class AnthropicMessagesConfig(BaseAnthropicMessagesConfig): optional_params: dict, custom_llm_provider: str = "anthropic", messages: Sequence[object] = (), + beta_map_provider: str | None = None, ) -> dict: """ Auto-inject anthropic-beta headers based on features used. @@ -627,8 +629,9 @@ class AnthropicMessagesConfig(BaseAnthropicMessagesConfig): optional_params: Optional parameters including tools, context_management, output_format, speed custom_llm_provider: Provider name for looking up correct tool search header messages: Request messages, scanned for per-message output_config + beta_map_provider: Provider whose beta map column gates safeguards, defaults to custom_llm_provider """ - beta_values: Final[set] = set() + beta_values: Final[set[str]] = set() existing_beta: Final = tuple( piece.strip() @@ -678,6 +681,12 @@ class AnthropicMessagesConfig(BaseAnthropicMessagesConfig): if optional_params.get("speed") == "fast": beta_values.add(ANTHROPIC_BETA_HEADER_VALUES.FAST_MODE_2026_02_01.value) + if optional_params.get("safeguards") is not None and is_beta_header_supported_by_bundled_config( + ANTHROPIC_BETA_HEADER_VALUES.DANGEROUS_TOOL_USE_2026_09_03.value, + beta_map_provider or custom_llm_provider, + ): + beta_values.add(ANTHROPIC_BETA_HEADER_VALUES.DANGEROUS_TOOL_USE_2026_09_03.value) + if _messages_carry_output_config(messages): beta_values.add(ANTHROPIC_BETA_HEADER_VALUES.PER_TURN_CONTROL_2026_07_01.value) diff --git a/litellm/llms/custom_httpx/llm_http_handler.py b/litellm/llms/custom_httpx/llm_http_handler.py index ef13483e2f8..49977269067 100644 --- a/litellm/llms/custom_httpx/llm_http_handler.py +++ b/litellm/llms/custom_httpx/llm_http_handler.py @@ -3,7 +3,7 @@ import json import ssl from collections.abc import AsyncGenerator, AsyncIterator, Coroutine, Iterator, Mapping, Sequence from contextlib import asynccontextmanager -from functools import lru_cache, partial +from functools import lru_cache, partial, reduce from types import MappingProxyType, ModuleType from typing import ( TYPE_CHECKING, @@ -32,7 +32,7 @@ import litellm.litellm_core_utils import litellm.types import litellm.types.utils from litellm._logging import _redact_string, verbose_logger -from litellm.anthropic_beta_headers_manager import update_headers_with_filtered_beta +from litellm.anthropic_beta_headers_manager import aload_beta_headers_config, update_headers_with_filtered_beta from litellm.constants import MAX_FILE_LIST_LIMIT, REALTIME_WEBSOCKET_MAX_MESSAGE_SIZE_BYTES from litellm.files.types import FileContentStreamingResult from litellm.litellm_core_utils.agentic_followup_kwargs import build_agentic_followup_kwargs @@ -46,6 +46,7 @@ from litellm.litellm_core_utils.audio_utils.subtitle_utils import ( synthesize_subtitle_document, ) from litellm.litellm_core_utils.core_helpers import set_provider_response_headers_in_hidden_params +from litellm.litellm_core_utils.dot_notation_indexing import delete_nested_value from litellm.litellm_core_utils.get_litellm_params import AWS_CREDENTIAL_KWARGS_KEYS from litellm.litellm_core_utils.llm_request_utils import serialize_multipart_form_fields from litellm.litellm_core_utils.realtime_errors import ( @@ -2116,6 +2117,16 @@ class BaseLLMHTTPHandler: merged_headers.update(extra_headers_from_kwargs) if provider_specific_headers: merged_headers.update(provider_specific_headers) + request_params: Final = reduce( + delete_nested_value, + litellm_params.get("additional_drop_params") or (), + anthropic_messages_optional_request_params, + ) + if ( + request_params.get("safeguards") is not None + and anthropic_messages_provider_config.should_filter_anthropic_beta_headers() + ): + await aload_beta_headers_config() ( headers, api_base, @@ -2123,7 +2134,7 @@ class BaseLLMHTTPHandler: headers=merged_headers or {}, model=model, messages=messages, - optional_params=anthropic_messages_optional_request_params, + optional_params=request_params, litellm_params=dict(litellm_params), api_key=api_key, api_base=api_base, @@ -2154,20 +2165,11 @@ class BaseLLMHTTPHandler: custom_llm_provider=custom_llm_provider, ) - additional_drop_params: Final[list[str]] = litellm_params.get("additional_drop_params") or [] - if additional_drop_params: - from litellm.litellm_core_utils.dot_notation_indexing import delete_nested_value - - for path in additional_drop_params: - anthropic_messages_optional_request_params = delete_nested_value( - anthropic_messages_optional_request_params, path - ) - # Prepare request body request_body: Final = anthropic_messages_provider_config.transform_anthropic_messages_request( model=model, messages=messages, - anthropic_messages_optional_request_params=anthropic_messages_optional_request_params, + anthropic_messages_optional_request_params=request_params, litellm_params=litellm_params, headers=headers, ) @@ -2273,7 +2275,7 @@ class BaseLLMHTTPHandler: held_back_tool_names: Final = self._server_fulfilled_tools_in_request( logging_obj=logging_obj, - tools=anthropic_messages_optional_request_params.get("tools"), + tools=request_params.get("tools"), ) initial_response = AgenticAnthropicStreamingIterator( completion_stream=completion_stream, @@ -2281,7 +2283,7 @@ class BaseLLMHTTPHandler: model=model, messages=messages, anthropic_messages_provider_config=anthropic_messages_provider_config, - anthropic_messages_optional_request_params=anthropic_messages_optional_request_params, + anthropic_messages_optional_request_params=request_params, logging_obj=logging_obj, custom_llm_provider=custom_llm_provider, kwargs=kwargs_for_agentic, @@ -2304,7 +2306,7 @@ class BaseLLMHTTPHandler: model=model, messages=messages, anthropic_messages_provider_config=anthropic_messages_provider_config, - anthropic_messages_optional_request_params=anthropic_messages_optional_request_params, + anthropic_messages_optional_request_params=request_params, logging_obj=logging_obj, custom_llm_provider=custom_llm_provider, kwargs=kwargs_for_agentic, diff --git a/litellm/llms/openai_like/messages/transformation.py b/litellm/llms/openai_like/messages/transformation.py index bae190c88c0..1426fcab3dd 100644 --- a/litellm/llms/openai_like/messages/transformation.py +++ b/litellm/llms/openai_like/messages/transformation.py @@ -8,6 +8,7 @@ from litellm.llms.anthropic.experimental_pass_through.messages.transformation im from litellm.llms.openai_like.json_loader import SimpleProviderConfig from litellm.secret_managers.main import get_secret_str from litellm.types.router import GenericLiteLLMParams +from litellm.types.utils import LlmProviders DEFAULT_ANTHROPIC_API_VERSION: Final = "2023-06-01" @@ -57,6 +58,7 @@ class OpenAILikeAnthropicMessagesConfig(AnthropicMessagesConfig): headers=normalized, optional_params=optional_params, messages=messages, + beta_map_provider=LlmProviders.OPENAI_LIKE.value, ) return merged, api_base diff --git a/tests/integration/providers/test_anthropic_safeguards_beta_chaos.py b/tests/integration/providers/test_anthropic_safeguards_beta_chaos.py new file mode 100644 index 00000000000..0266bdc190f --- /dev/null +++ b/tests/integration/providers/test_anthropic_safeguards_beta_chaos.py @@ -0,0 +1,348 @@ +import asyncio +import json +import re +import threading +import uuid +from dataclasses import dataclass +from pathlib import Path +from queue import SimpleQueue +from types import MappingProxyType +from typing import Final +from urllib.parse import urlsplit + +import httpx +import psutil +import pytest +import yaml +from integration._support.client import Gateway, eventually +from integration._support.database import read_rows +from integration._support.process import owned_proxy_process +from integration._support.wire import Reply, Request, Wire, wire_server +from integration.providers.test_anthropic_safeguards_beta_wire import ( + ANTHROPIC_KEY, + ANTHROPIC_MODEL, + BETA, + OMITTED, + anthropic_peer, + marker_of, + messages_body, + stream_frames, +) +from pydantic import JsonValue, TypeAdapter + +_CONFIG_MODEL: Final = "anthropic-safeguards-chaos" +_FOUNDRY_CONFIG_MODEL: Final = "azure-ai-safeguards-chaos" +_YAML_OBJECT: Final = TypeAdapter(dict[str, JsonValue]) +_MARKER: Final = re.compile(r"marker-([0-9a-f]{32})") +_STARTED_WORKER: Final = re.compile(r"Started server process \[(\d+)\]") +_MODEL_LIST: Final = json.dumps( + {"object": "list", "data": [{"id": ANTHROPIC_MODEL, "object": "model", "owned_by": "anthropic"}]} +).encode() + + +@dataclass(frozen=True, slots=True) +class _Call: + stream: bool + marker: str + safeguards: bool = True + + +@dataclass(frozen=True, slots=True) +class _Served: + call: _Call + status: int + text: str + + +def _calls(count: int, stream: bool, safeguards: bool = True) -> tuple[_Call, ...]: + return tuple(_Call(stream=stream, marker=uuid.uuid4().hex, safeguards=safeguards) for _ in range(count)) + + +def _streamed_reply(marker: str, abort_after: int | None = None, pause: float = 0) -> Reply: + return Reply( + content_type="text/event-stream", + chunks=stream_frames(marker), + abort_after=abort_after, + pause_between_chunks=pause, + ) + + +async def _send(client: httpx.AsyncClient, key: str, model: str, call: _Call) -> _Served: + async with client.stream( + "POST", + "/v1/messages", + json=( + messages_body(model, call.marker, stream=call.stream) + if call.safeguards + else messages_body(model, call.marker, stream=call.stream, safeguards=OMITTED) + ), + headers={"Authorization": f"Bearer {key}", "anthropic-version": "2023-06-01"}, + ) as response: + raw: Final = await response.aread() + return _Served(call=call, status=response.status_code, text=raw.decode()) + + +async def _burst( + base_url: str, key: str, model: str, calls: tuple[_Call, ...], *, tolerate_transport_errors: bool = False +) -> tuple[_Served, ...]: + async with httpx.AsyncClient(base_url=base_url, timeout=60, trust_env=False) as client: + results: Final = await asyncio.gather( + *(_send(client, key, model, call) for call in calls), return_exceptions=tolerate_transport_errors + ) + for result in results: + assert not isinstance(result, BaseException) or isinstance(result, httpx.TransportError), repr(result) + return tuple(result for result in results if isinstance(result, _Served)) + + +def _assert_answered_with_its_own_marker(served: _Served) -> None: + assert served.status == 200, served.text + assert set(_MARKER.findall(served.text)) == {served.call.marker}, served.text + assert f"msg_{served.call.marker}" in served.text, served.text + if served.call.stream: + assert "event: message_stop" in served.text, served.text + + +def _assert_every_request_carried_the_beta(received: tuple[Request, ...], markers: frozenset[str]) -> None: + assert sorted(marker_of(request) for request in received) == sorted(markers) + missing: Final = [ + frozenset(request.headers) for request in received if request.headers.get("anthropic-beta") != BETA + ] + assert missing == [], missing + + +def _spend_success_ids(model: str, expected: frozenset[str]) -> None: + rows: Final = eventually( + lambda: read_rows( + 'SELECT request_id FROM "LiteLLM_SpendLogs" WHERE model_group=%s AND status=%s', (model, "success") + ), + lambda found: expected <= {str(row["request_id"]) for row in found}, + seconds=70, + ) + identities: Final = [row["request_id"] for row in rows] + assert len(set(identities)) == len(identities), identities + + +async def test_burst_with_aborted_streams_keeps_the_beta_on_every_forwarded_request(gateway: Gateway) -> None: + calls: Final = tuple(_Call(stream=index % 2 == 0, marker=uuid.uuid4().hex) for index in range(30)) + aborted: Final = frozenset(call.marker for index, call in enumerate(calls) if call.stream and index % 3 == 0) + + def respond(request: Request) -> Reply: + marker: Final = marker_of(request) + if marker in aborted: + return _streamed_reply(marker, abort_after=0) + return anthropic_peer(request) + + with wire_server(respond) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY) + served: Final = await _burst(str(gateway.client.base_url), gateway.key, model, calls) + assert len(served) == 30 + for item in served: + if item.call.marker in aborted: + assert item.status == 500, item.text + assert '"type":"api_error"' in item.text and "marker-" not in item.text, item.text + else: + _assert_answered_with_its_own_marker(item) + recovery: Final = _Call(stream=True, marker=uuid.uuid4().hex) + (recovered,) = await _burst(str(gateway.client.base_url), gateway.key, model, (recovery,)) + _assert_answered_with_its_own_marker(recovered) + _assert_every_request_carried_the_beta(wire.drain(), frozenset(call.marker for call in (*calls, recovery))) + answered: Final = frozenset(f"msg_{call.marker}" for call in (*calls, recovery) if call.marker not in aborted) + _spend_success_ids(model, answered) + + +async def test_slow_streams_complete_with_the_beta_on_every_request(gateway: Gateway) -> None: + calls: Final = _calls(10, stream=True) + with ( + wire_server(lambda request: _streamed_reply(marker_of(request), pause=0.3)) as wire, + gateway.scenario() as scenario, + ): + model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY) + served: Final = await _burst(str(gateway.client.base_url), gateway.key, model, calls) + assert len(served) == 10 + for item in served: + _assert_answered_with_its_own_marker(item) + _assert_every_request_carried_the_beta(wire.drain(), frozenset(call.marker for call in calls)) + _spend_success_ids(model, frozenset(f"msg_{call.marker}" for call in calls)) + + +def _anthropic_deployment(wire: Wire) -> dict[str, JsonValue]: + return { + "model_name": _CONFIG_MODEL, + "litellm_params": {"model": f"anthropic/{ANTHROPIC_MODEL}", "api_base": wire.url, "api_key": ANTHROPIC_KEY}, + } + + +def _foundry_deployment(wire: Wire) -> dict[str, JsonValue]: + return { + "model_name": _FOUNDRY_CONFIG_MODEL, + "litellm_params": { + "model": "azure_ai/claude-sonnet-4-6", + "api_base": wire.url, + "api_key": "synthetic-foundry-key", + }, + } + + +def _chaos_config(tmp_path: Path, *deployments: dict[str, JsonValue]) -> Path: + base: Final = _YAML_OBJECT.validate_python(yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text())) + config: Final = {**base, "model_list": list(deployments)} + path: Final = tmp_path / "anthropic-safeguards-chaos.yaml" + path.write_text(yaml.safe_dump(config)) + return path + + +def _open_upstream_connections(pid: int, upstream: str) -> int: + port: Final = urlsplit(upstream).port + return sum( + 1 + for connection in psutil.Process(pid).net_connections(kind="tcp") + if connection.status == psutil.CONN_ESTABLISHED and connection.raddr and connection.raddr.port == port + ) + + +@pytest.mark.timeout(180) +async def test_worker_sigkill_mid_burst_leaves_the_sibling_sending_the_beta(gateway: Gateway, tmp_path: Path) -> None: + calls: Final = _calls(20, stream=False) + release: Final = threading.Event() + held_markers: Final[SimpleQueue[str]] = SimpleQueue() + + def held(request: Request) -> Reply: + if (request.method, request.target) == ("GET", "/v1/models"): + return Reply(body=_MODEL_LIST) + held_markers.put(marker_of(request)) + assert release.wait(timeout=60), "The burst was never released" + return anthropic_peer(request) + + with wire_server(held) as wire: + path: Final = _chaos_config(tmp_path, _anthropic_deployment(wire)) + with owned_proxy_process(gateway, tmp_path, {}, config=path, workers=2) as owned: + candidate: Final = owned.gateway + workers: Final = eventually( + lambda: tuple(int(found.group(1)) for found in _STARTED_WORKER.finditer(owned.log.read_text())), + lambda pids: len(pids) == 2, + seconds=30, + ) + burst: Final = asyncio.create_task( + _burst( + str(candidate.client.base_url), candidate.key, _CONFIG_MODEL, calls, tolerate_transport_errors=True + ) + ) + await asyncio.to_thread(eventually, held_markers.qsize, lambda size: size == 20, 60) + held_by: Final = MappingProxyType({pid: _open_upstream_connections(pid, wire.url) for pid in workers}) + assert sum(held_by.values()) == 20, held_by + victim_pid, survivor_pid = sorted(workers, key=held_by.__getitem__) + with owned.replacing_worker(victim_pid) as kill: + kill.freeze() + await asyncio.to_thread(kill) + release.set() + served: Final = await burst + assert held_by[survivor_pid] >= 10, held_by + assert len(served) == held_by[survivor_pid], (held_by, len(served)) + for item in served: + _assert_answered_with_its_own_marker(item) + follow_up: Final = _Call(stream=False, marker=uuid.uuid4().hex) + (answered,) = await _burst(str(candidate.client.base_url), candidate.key, _CONFIG_MODEL, (follow_up,)) + _assert_answered_with_its_own_marker(answered) + received: Final = wire.drain() + posts: Final = tuple(request for request in received if request.method == "POST") + probes: Final[list[tuple[str, str]]] = [ + (request.method, request.target) for request in received if request.method != "POST" + ] + assert set(probes) <= {("GET", "/v1/models")}, probes + _assert_every_request_carried_the_beta(posts, frozenset(call.marker for call in (*calls, follow_up))) + + +def _beta_map_gets(received: tuple[Request, ...]) -> int: + return sum(1 for request in received if (request.method, request.target) == ("GET", "/beta.json")) + + +async def _chat(base_url: str, key: str, marker: str) -> httpx.Response: + async with httpx.AsyncClient(base_url=base_url, timeout=60, trust_env=False) as client: + return await client.post( + "/v1/chat/completions", + json={ + "model": _CONFIG_MODEL, + "max_tokens": 16, + "messages": [{"role": "user", "content": f"Question marker-{marker}"}], + }, + headers={"Authorization": f"Bearer {key}"}, + ) + + +async def _answered_while_the_beta_map_is_held( + base_url: str, key: str, guarded: tuple[_Call, ...], chat_markers: tuple[str, ...] +) -> None: + served: Final = await _burst(base_url, key, _CONFIG_MODEL, guarded) + chats: Final = await asyncio.gather(*(_chat(base_url, key, marker) for marker in chat_markers)) + for item in served: + _assert_answered_with_its_own_marker(item) + for marker, chat in zip(chat_markers, chats, strict=True): + assert chat.status_code == 200, chat.text + assert f"marker-{marker}" in chat.text, chat.text + + +@pytest.mark.timeout(240) +async def test_cold_workers_fetch_the_beta_map_only_for_filtered_safeguards_requests_off_the_shared_threads( + gateway: Gateway, tmp_path: Path +) -> None: + beta_map: Final = Path("litellm/anthropic_beta_headers_config.json").read_bytes() + release: Final = threading.Event() + + def held_beta_map(_: Request) -> Reply: + assert release.wait(timeout=180), "The beta map was never released" + return Reply(body=beta_map) + + def upstream(request: Request) -> Reply: + if (request.method, request.target) == ("GET", "/v1/models"): + return Reply(body=_MODEL_LIST) + return anthropic_peer(request) + + plain: Final = _calls(8, stream=False, safeguards=False) + plain_foundry: Final = _calls(8, stream=False, safeguards=False) + direct: Final = _calls(8, stream=False) + foundry: Final = _calls(80, stream=False) + direct_while_held: Final = _calls(8, stream=False) + chat_markers: Final = tuple(uuid.uuid4().hex for _ in range(4)) + with wire_server(held_beta_map) as beta_map_wire, wire_server(upstream) as wire: + path: Final = _chaos_config(tmp_path, _anthropic_deployment(wire), _foundry_deployment(wire)) + with owned_proxy_process( + gateway, + tmp_path, + {"LITELLM_ANTHROPIC_BETA_HEADERS_URL": f"{beta_map_wire.url}/beta.json"}, + remove_environment=("LITELLM_LOCAL_ANTHROPIC_BETA_HEADERS",), + config=path, + workers=2, + ) as owned: + base_url: Final = str(owned.gateway.client.base_url) + key: Final = owned.gateway.key + cold: Final = ( + *await _burst(base_url, key, _CONFIG_MODEL, plain), + *await _burst(base_url, key, _FOUNDRY_CONFIG_MODEL, plain_foundry), + *await _burst(base_url, key, _CONFIG_MODEL, direct), + ) + for served_cold in cold: + _assert_answered_with_its_own_marker(served_cold) + assert beta_map_wire.received.qsize() == 0, "a request that never filters betas fetched the beta map" + + held: Final = asyncio.create_task(_burst(base_url, key, _FOUNDRY_CONFIG_MODEL, foundry)) + try: + await asyncio.to_thread(eventually, beta_map_wire.received.qsize, lambda size: size >= 1, 60) + await asyncio.wait_for( + _answered_while_the_beta_map_is_held(base_url, key, direct_while_held, chat_markers), timeout=45 + ) + assert not held.done(), "Foundry safeguards requests were answered before the beta map loaded" + finally: + release.set() + for served_foundry in await held: + _assert_answered_with_its_own_marker(served_foundry) + + received: Final = tuple(request for request in wire.drain() if request.method == "POST") + beta_by_marker: Final = MappingProxyType( + {marker_of(request): request.headers.get("anthropic-beta") for request in received} + ) + assert {beta_by_marker[call.marker] for call in (*direct, *direct_while_held, *foundry)} == {BETA}, ( + beta_by_marker + ) + assert {beta_by_marker[call.marker] for call in (*plain, *plain_foundry)} == {None}, beta_by_marker + fetches: Final = _beta_map_gets(beta_map_wire.drain()) + assert 1 <= fetches <= 2, fetches diff --git a/tests/integration/providers/test_anthropic_safeguards_beta_wire.py b/tests/integration/providers/test_anthropic_safeguards_beta_wire.py new file mode 100644 index 00000000000..0c41efffe73 --- /dev/null +++ b/tests/integration/providers/test_anthropic_safeguards_beta_wire.py @@ -0,0 +1,809 @@ +import itertools +import json +import re +import time +import uuid +from collections.abc import Callable, Mapping +from dataclasses import dataclass +from pathlib import Path +from types import MappingProxyType +from typing import Final + +import anthropic +import httpx +import openai +import pytest +from integration._support.client import Gateway, eventually +from integration._support.database import read_rows +from integration._support.process import owned_proxy +from integration._support.vertex import service_account_json +from integration._support.wire import Reply, Request, Wire, wire_server +from pydantic import JsonValue, TypeAdapter + +BETA: Final = "dangerous-tool-use-2026-09-03" +SAFEGUARDS: Final[list[JsonValue]] = [ + {"type": "dangerous_tool_use", "classifier_context": {"v": 1, "permission_mode": "auto"}} +] +ANTHROPIC_MODEL: Final = "claude-sonnet-4-5-20250929" +ANTHROPIC_KEY: Final = "synthetic-anthropic-key" +_CLAUDE_CODE_BETAS: Final = ( + "claude-code-20250219", + "interleaved-thinking-2025-05-14", + "fine-grained-tool-streaming-2025-05-14", + "context-management-2025-06-27", +) +_CLIENT_BETAS: Final = ",".join(_CLAUDE_CODE_BETAS) +_CLIENT_BETAS_WITH_DANGEROUS: Final = ",".join((*_CLAUDE_CODE_BETAS, BETA)) +_MERGED_BETAS: Final = ",".join(sorted((*_CLAUDE_CODE_BETAS, BETA))) +_FOUNDRY_MODEL: Final = "azure_ai/claude-sonnet-4-6" +_FOUNDRY_KEY: Final = "synthetic-foundry-key" +_FOUNDRY_TARGET: Final = "/anthropic/v1/messages" +_FOUNDRY_ARRAY_ERROR: Final = "safeguards: Input should be a valid array" +_FOUNDRY_EXTRA_INPUT_ERROR: Final = "safeguards: Extra inputs are not permitted" +_ANTHROPIC_VERSION: Final = MappingProxyType({"anthropic-version": "2023-06-01"}) +_MESSAGES_KEYS: Final = frozenset({"max_tokens", "messages", "model", "stream"}) +_RESPONSES_KEYS: Final = frozenset({"include", "input", "max_output_tokens", "model"}) +_SDK_EXTRA: Final[dict[str, JsonValue]] = {"safeguards": SAFEGUARDS, "cache": {"no-cache": True}, "num_retries": 0} +_MARKER: Final = re.compile(r"marker-([0-9a-f]{32})") +_JSON_OBJECT: Final = TypeAdapter(dict[str, JsonValue]) + + +@dataclass(frozen=True, slots=True) +class _Omitted: + pass + + +OMITTED: Final = _Omitted() + + +@dataclass(frozen=True, slots=True) +class _Observed: + method: str + target: str + marker: str + headers: Mapping[str, str] + body: Mapping[str, JsonValue] + + @property + def beta(self) -> str | None: + return self.headers.get("anthropic-beta") + + @property + def keys(self) -> frozenset[str]: + return frozenset(self.body) + + @property + def header_names(self) -> frozenset[str]: + return frozenset(self.headers) + + +def marker_of(request: Request) -> str: + found: Final = _MARKER.search(request.body.decode()) + assert found is not None, request.body + return found.group(1) + + +def _message(marker: str) -> dict[str, JsonValue]: + return { + "id": f"msg_{marker}", + "type": "message", + "role": "assistant", + "model": ANTHROPIC_MODEL, + "content": [{"type": "text", "text": f"answer marker-{marker}"}], + "stop_reason": "end_turn", + "stop_sequence": None, + "usage": {"input_tokens": 12, "output_tokens": 5}, + } + + +def stream_frames(marker: str) -> tuple[bytes, ...]: + opening: Final[dict[str, JsonValue]] = { + **_message(marker), + "content": [], + "stop_reason": None, + "usage": {"input_tokens": 12, "output_tokens": 0}, + } + events: Final[tuple[tuple[str, dict[str, JsonValue]], ...]] = ( + ("message_start", {"message": opening}), + ("content_block_start", {"index": 0, "content_block": {"type": "text", "text": ""}}), + ("content_block_delta", {"index": 0, "delta": {"type": "text_delta", "text": f"answer marker-{marker}"}}), + ("content_block_stop", {"index": 0}), + ("message_delta", {"delta": {"stop_reason": "end_turn", "stop_sequence": None}, "usage": {"output_tokens": 5}}), + ("message_stop", {}), + ) + return tuple( + f"event: {kind}\ndata: {json.dumps({'type': kind, **payload})}\n\n".encode() for kind, payload in events + ) + + +def anthropic_peer(request: Request) -> Reply: + marker: Final = marker_of(request) + if _JSON_OBJECT.validate_json(request.body).get("stream") is True: + return Reply(content_type="text/event-stream", chunks=stream_frames(marker)) + return Reply(body=json.dumps(_message(marker)).encode()) + + +def _responses_peer(request: Request) -> Reply: + marker: Final = marker_of(request) + return Reply( + body=json.dumps( + { + "id": f"resp_{marker}", + "object": "response", + "created_at": 1, + "status": "completed", + "model": "gpt-4o-mini", + "output": [ + { + "type": "message", + "id": f"msg_{marker}", + "status": "completed", + "role": "assistant", + "content": [{"type": "output_text", "text": f"answer marker-{marker}", "annotations": []}], + } + ], + "usage": {"input_tokens": 12, "output_tokens": 5, "total_tokens": 17}, + } + ).encode() + ) + + +def _error_peer(status: int, kind: str, message: str) -> Callable[[Request], Reply]: + body: Final = json.dumps({"type": "error", "error": {"type": kind, "message": message}}).encode() + return lambda request: Reply(status=status, body=body) + + +def messages_body( + model: str, + marker: str, + *, + safeguards: JsonValue | _Omitted = SAFEGUARDS, + stream: bool = False, + no_cache: bool = True, +) -> dict[str, JsonValue]: + base: Final[dict[str, JsonValue]] = { + "model": model, + "max_tokens": 16, + "messages": [{"role": "user", "content": f"Question marker-{marker}"}], + "num_retries": 0, + **({"stream": True} if stream else {}), + **({"cache": {"no-cache": True}} if no_cache else {}), + } + if isinstance(safeguards, _Omitted): + return base + return {**base, "safeguards": safeguards} + + +def _observe(request: Request) -> _Observed: + return _Observed( + request.method, request.target, marker_of(request), request.headers, _JSON_OBJECT.validate_json(request.body) + ) + + +def _only(wire: Wire) -> _Observed: + (request,) = wire.drain() + return _observe(request) + + +def _post(gateway: Gateway, body: Mapping[str, JsonValue], *, beta: str | None = None) -> httpx.Response: + headers: Final = {**_ANTHROPIC_VERSION, **({"anthropic-beta": beta} if beta else {})} + return gateway.request("POST", "/v1/messages", body, headers=headers) + + +def _assert_answered(response: httpx.Response, marker: str) -> None: + assert response.status_code == 200, response.text + assert response.json()["id"] == f"msg_{marker}", response.text + + +def _assert_streamed(response: httpx.Response, marker: str) -> None: + assert response.status_code == 200, response.text + assert f"msg_{marker}" in response.text and f"answer marker-{marker}" in response.text, response.text + assert "event: message_stop" in response.text, response.text + + +def _spend_row(identity: str) -> None: + rows: Final = eventually( + lambda: read_rows('SELECT request_id, status FROM "LiteLLM_SpendLogs" WHERE request_id=%s', (identity,)), + lambda found: len(found) == 1, + seconds=70, + ) + assert rows[0]["status"] == "success", rows + + +def _cache_hit_spend_row(identity: str) -> None: + rows: Final = eventually( + lambda: read_rows( + 'SELECT request_id, status, cache_hit FROM "LiteLLM_SpendLogs" WHERE request_id LIKE %s', + (f"{identity}\\_cache\\_hit%",), + ), + lambda found: len(found) == 1, + seconds=70, + ) + assert (rows[0]["status"], str(rows[0]["cache_hit"])) == ("success", "True"), rows + + +def _responses_spend_row(model: str) -> None: + rows: Final = eventually( + lambda: read_rows( + 'SELECT request_id, status FROM "LiteLLM_SpendLogs" WHERE model_group = %s AND call_type = %s', + (model, "aresponses"), + ), + lambda found: len(found) == 1, + seconds=70, + ) + assert rows[0]["status"] == "success", rows + + +def _expect_messages( + observed: _Observed, + *, + target: str, + auth: tuple[str, str] | None, + beta: str | None, + safeguards: JsonValue | _Omitted = SAFEGUARDS, + keys: frozenset[str] = _MESSAGES_KEYS, +) -> None: + assert (observed.method, observed.target) == ("POST", target) + if auth is not None: + credential_matches: Final = observed.headers.get(auth[0]) == auth[1] + assert credential_matches, f"{auth[0]} differs from the deployment credential; headers {observed.header_names}" + assert observed.beta == beta, observed.header_names + if isinstance(safeguards, _Omitted): + assert observed.keys == keys + return + assert observed.keys == keys | {"safeguards"} + assert observed.body["safeguards"] == safeguards + + +def _expect_anthropic_version(observed: _Observed) -> None: + assert observed.headers.get("anthropic-version") == "2023-06-01", observed.header_names + + +@dataclass(frozen=True, slots=True) +class _ShapeCase: + sent: JsonValue | _Omitted + forwarded: JsonValue | _Omitted + client_beta: str | None + expected_beta: str | None + stream: bool = False + + +_ANTHROPIC_SHAPES: Final = MappingProxyType( + { + "D1_safeguards_without_client_header": _ShapeCase(SAFEGUARDS, SAFEGUARDS, None, BETA), + "D2_safeguards_with_claude_code_header": _ShapeCase( + SAFEGUARDS, SAFEGUARDS, _CLIENT_BETAS_WITH_DANGEROUS, _MERGED_BETAS + ), + "D3_safeguards_with_claude_code_header_lacking_the_beta": _ShapeCase( + SAFEGUARDS, SAFEGUARDS, _CLIENT_BETAS, _MERGED_BETAS + ), + "D4_empty_safeguards": _ShapeCase([], [], None, BETA), + "D5_null_safeguards": _ShapeCase(None, OMITTED, None, None), + "D6_missing_safeguards": _ShapeCase(OMITTED, OMITTED, None, None), + } +) +_FOUNDRY_SHAPES: Final = MappingProxyType( + { + "D9_streamed_safeguards_with_claude_code_header": _ShapeCase( + SAFEGUARDS, SAFEGUARDS, _CLIENT_BETAS_WITH_DANGEROUS, BETA, stream=True + ), + "D11_empty_safeguards": _ShapeCase([], [], None, BETA), + "D12_null_safeguards": _ShapeCase(None, OMITTED, None, None), + "D13_missing_safeguards_with_claude_code_header_lacking_the_beta": _ShapeCase( + OMITTED, OMITTED, _CLIENT_BETAS, None + ), + } +) + + +@pytest.mark.parametrize("row", tuple(_ANTHROPIC_SHAPES)) +def test_anthropic_messages_derive_the_dangerous_tool_use_beta_from_safeguards(gateway: Gateway, row: str) -> None: + case: Final = _ANTHROPIC_SHAPES[row] + marker: Final = uuid.uuid4().hex + with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY) + response: Final = _post(gateway, messages_body(model, marker, safeguards=case.sent), beta=case.client_beta) + _assert_answered(response, marker) + observed: Final = _only(wire) + _expect_messages( + observed, + target="/v1/messages", + auth=("x-api-key", ANTHROPIC_KEY), + beta=case.expected_beta, + safeguards=case.forwarded, + ) + _expect_anthropic_version(observed) + _spend_row(f"msg_{marker}") + + +@dataclass(frozen=True, slots=True, kw_only=True) +class _DropCase: + deployment: Callable[[Gateway], Mapping[str, JsonValue]] + target: str + auth: tuple[str, str] | None + keys: frozenset[str] = _MESSAGES_KEYS + + +_VERTEX_PROJECT: Final = "scripted-project" +_VERTEX_LOCATION: Final = "us-east5" +_VERTEX_MODEL: Final = "claude-opus-5-5" + +_DROP_CASES: Final = MappingProxyType( + { + "anthropic": _DropCase( + deployment=lambda _: {"model": f"anthropic/{ANTHROPIC_MODEL}", "api_key": ANTHROPIC_KEY}, + target="/v1/messages", + auth=("x-api-key", ANTHROPIC_KEY), + ), + "azure_ai": _DropCase( + deployment=lambda _: {"model": _FOUNDRY_MODEL, "api_key": _FOUNDRY_KEY}, + target=_FOUNDRY_TARGET, + auth=("x-api-key", _FOUNDRY_KEY), + ), + "bedrock_claude_platform": _DropCase( + deployment=lambda _: { + "model": f"bedrock/claude_platform/{ANTHROPIC_MODEL}", + "api_key": "synthetic-platform-key", + "workspace_id": "ws-synthetic", + "aws_region_name": "us-east-1", + }, + target="/v1/messages", + auth=("x-api-key", "synthetic-platform-key"), + ), + "vertex_ai": _DropCase( + deployment=lambda gateway: { + "model": f"vertex_ai/{_VERTEX_MODEL}", + "api_key": None, + "vertex_project": _VERTEX_PROJECT, + "vertex_location": _VERTEX_LOCATION, + "vertex_credentials": service_account_json(_VERTEX_PROJECT, gateway.upstream_url.rstrip("/")), + }, + target=( + f"/v1/projects/{_VERTEX_PROJECT}/locations/{_VERTEX_LOCATION}" + f"/publishers/anthropic/models/{_VERTEX_MODEL}:rawPredict" + ), + auth=None, + keys=frozenset({"anthropic_version", "max_tokens", "messages", "stream"}), + ), + } +) + + +@pytest.mark.parametrize("row", tuple(_DROP_CASES)) +def test_a_deployment_dropping_safeguards_sends_neither_the_field_nor_the_beta(gateway: Gateway, row: str) -> None: + case: Final = _DROP_CASES[row] + marker: Final = uuid.uuid4().hex + with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model( + api_base=wire.url, additional_drop_params=["safeguards"], **case.deployment(gateway) + ) + response: Final = _post(gateway, messages_body(model, marker)) + _assert_answered(response, marker) + _expect_messages(_only(wire), target=case.target, auth=case.auth, beta=None, safeguards=OMITTED, keys=case.keys) + _spend_row(f"msg_{marker}") + + +def test_a_deployment_dropping_context_management_sends_neither_the_field_nor_its_beta(gateway: Gateway) -> None: + marker: Final = uuid.uuid4().hex + with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model( + model=f"anthropic/{ANTHROPIC_MODEL}", + api_base=wire.url, + api_key=ANTHROPIC_KEY, + additional_drop_params=["context_management"], + ) + body: Final = { + **messages_body(model, marker, safeguards=OMITTED), + "context_management": {"edits": [{"type": "clear_tool_uses_20250919"}]}, + } + response: Final = _post(gateway, body) + _assert_answered(response, marker) + _expect_messages( + _only(wire), target="/v1/messages", auth=("x-api-key", ANTHROPIC_KEY), beta=None, safeguards=OMITTED + ) + _spend_row(f"msg_{marker}") + + +@pytest.mark.parametrize("row", tuple(_FOUNDRY_SHAPES)) +def test_azure_ai_messages_derive_the_beta_instead_of_forwarding_the_client_header(gateway: Gateway, row: str) -> None: + case: Final = _FOUNDRY_SHAPES[row] + marker: Final = uuid.uuid4().hex + with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY) + response: Final = _post( + gateway, messages_body(model, marker, safeguards=case.sent, stream=case.stream), beta=case.client_beta + ) + if case.stream: + _assert_streamed(response, marker) + else: + _assert_answered(response, marker) + observed: Final = _only(wire) + _expect_messages( + observed, + target=_FOUNDRY_TARGET, + auth=("x-api-key", _FOUNDRY_KEY), + beta=case.expected_beta, + safeguards=case.forwarded, + ) + _expect_anthropic_version(observed) + _spend_row(f"msg_{marker}") + + +def test_anthropic_sdk_sync_safeguards_derive_the_beta(gateway: Gateway) -> None: + marker: Final = uuid.uuid4().hex + with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY) + client: Final = anthropic.Anthropic(base_url=str(gateway.client.base_url), api_key=gateway.key, max_retries=0) + reply: Final = client.messages.create( + model=model, + max_tokens=16, + messages=[{"role": "user", "content": f"Question marker-{marker}"}], + extra_body=_SDK_EXTRA, + ) + assert reply.id == f"msg_{marker}", reply + _expect_messages(_only(wire), target="/v1/messages", auth=("x-api-key", ANTHROPIC_KEY), beta=BETA) + _spend_row(f"msg_{marker}") + + +async def test_anthropic_sdk_async_stream_safeguards_derive_the_beta_and_log_spend(gateway: Gateway) -> None: + marker: Final = uuid.uuid4().hex + with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY) + client: Final = anthropic.AsyncAnthropic( + base_url=str(gateway.client.base_url), api_key=gateway.key, max_retries=0 + ) + async with client.messages.with_streaming_response.create( + model=model, + max_tokens=16, + messages=[{"role": "user", "content": f"Question marker-{marker}"}], + stream=True, + extra_body=_SDK_EXTRA, + ) as streamed: + pieces: Final = [ + event.delta.text + async for event in await streamed.parse() + if event.type == "content_block_delta" and event.delta.type == "text_delta" + ] + assert "".join(pieces) == f"answer marker-{marker}", pieces + _expect_messages(_only(wire), target="/v1/messages", auth=("x-api-key", ANTHROPIC_KEY), beta=BETA) + _spend_row(f"msg_{marker}") + + +def test_azure_ai_sdk_sync_safeguards_derive_the_beta(gateway: Gateway) -> None: + marker: Final = uuid.uuid4().hex + with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY) + client: Final = anthropic.Anthropic(base_url=str(gateway.client.base_url), api_key=gateway.key, max_retries=0) + reply: Final = client.messages.create( + model=model, + max_tokens=16, + messages=[{"role": "user", "content": f"Question marker-{marker}"}], + extra_body=_SDK_EXTRA, + ) + assert reply.id == f"msg_{marker}", reply + _expect_messages(_only(wire), target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=BETA) + _spend_row(f"msg_{marker}") + + +@dataclass(frozen=True, slots=True, kw_only=True) +class _ProviderCase: + parameters: Mapping[str, JsonValue] + auth: tuple[str, str] | None + expected_beta: str | None + target: str = "/v1/messages" + api_base_suffix: str = "" + model_info: Mapping[str, JsonValue] | None = None + client_beta: str | None = None + keys: frozenset[str] = _MESSAGES_KEYS + extra_headers: Mapping[str, str] = MappingProxyType({}) + body_beta: list[str] | None = None + + +_PROVIDERS: Final = MappingProxyType( + { + "D14_deepseek_with_claude_code_header": _ProviderCase( + parameters={"model": "deepseek/deepseek-chat", "api_key": "synthetic-deepseek-key"}, + client_beta=_CLIENT_BETAS_WITH_DANGEROUS, + target="/anthropic/v1/messages", + auth=("x-api-key", "synthetic-deepseek-key"), + expected_beta=None, + ), + "D15_tencent_with_claude_code_header": _ProviderCase( + parameters={"model": "tencent/deepseek-v4-flash", "api_key": "synthetic-tencent-key"}, + client_beta=_CLIENT_BETAS_WITH_DANGEROUS, + auth=("x-api-key", "synthetic-tencent-key"), + expected_beta=None, + ), + "D16_minimax_with_claude_code_header": _ProviderCase( + parameters={"model": "minimax/MiniMax-M2", "api_key": "synthetic-minimax-key"}, + client_beta=_CLIENT_BETAS_WITH_DANGEROUS, + auth=("x-api-key", "synthetic-minimax-key"), + expected_beta=None, + ), + "D17_openai_compatible_native_passthrough": _ProviderCase( + parameters={"model": "openai/claude-sonnet-4-5", "api_key": "synthetic-openai-like-key"}, + api_base_suffix="/v1", + model_info={"supported_endpoints": ["/v1/messages"]}, + auth=("authorization", "Bearer synthetic-openai-like-key"), + expected_beta=None, + ), + "D18_sail_with_claude_code_header": _ProviderCase( + parameters={"model": "sail/sail-claude", "api_key": "synthetic-sail-key"}, + client_beta=_CLIENT_BETAS_WITH_DANGEROUS, + auth=("authorization", "Bearer synthetic-sail-key"), + expected_beta=None, + ), + "D19_edenai": _ProviderCase( + parameters={"model": "edenai/claude-sonnet-4-5", "api_key": "synthetic-edenai-key"}, + auth=("authorization", "Bearer synthetic-edenai-key"), + expected_beta=None, + ), + "D21_bedrock_claude_platform": _ProviderCase( + parameters={ + "model": f"bedrock/claude_platform/{ANTHROPIC_MODEL}", + "api_key": "synthetic-platform-key", + "workspace_id": "ws-synthetic", + "aws_region_name": "us-east-1", + }, + auth=("x-api-key", "synthetic-platform-key"), + expected_beta=BETA, + extra_headers={"anthropic-workspace-id": "ws-synthetic"}, + ), + "D22_bedrock_claude_platform_with_claude_code_header": _ProviderCase( + parameters={ + "model": f"bedrock/claude_platform/{ANTHROPIC_MODEL}", + "api_key": "synthetic-platform-key", + "workspace_id": "ws-synthetic", + "aws_region_name": "us-east-1", + }, + client_beta=_CLIENT_BETAS_WITH_DANGEROUS, + auth=("x-api-key", "synthetic-platform-key"), + expected_beta=_MERGED_BETAS, + extra_headers={"anthropic-workspace-id": "ws-synthetic"}, + ), + "D23_bedrock_invoke": _ProviderCase( + parameters={ + "model": "bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0", + "api_key": "synthetic-bedrock-bearer", + "aws_region_name": "us-east-1", + }, + target="/model/anthropic.claude-sonnet-4-5-20250929-v1:0/invoke", + auth=("authorization", "Bearer synthetic-bedrock-bearer"), + expected_beta=None, + keys=frozenset({"anthropic_beta", "anthropic_version", "max_tokens", "messages"}), + body_beta=[BETA], + ), + "D24_bedrock_mantle": _ProviderCase( + parameters={ + "model": "bedrock_mantle/anthropic.claude-sonnet-5-v1:0", + "api_key": "synthetic-mantle-bearer", + "aws_region_name": "us-east-1", + }, + target="/anthropic/v1/messages", + auth=("authorization", "Bearer synthetic-mantle-bearer"), + expected_beta=BETA, + keys=frozenset({"max_tokens", "messages", "model"}), + ), + } +) + + +@pytest.mark.parametrize("row", tuple(_PROVIDERS)) +def test_anthropic_compatible_providers_receive_the_beta_only_where_the_proxy_derives_it( + gateway: Gateway, row: str +) -> None: + case: Final = _PROVIDERS[row] + marker: Final = uuid.uuid4().hex + with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model( + model_info=case.model_info, api_base=wire.url + case.api_base_suffix, **case.parameters + ) + response: Final = _post(gateway, messages_body(model, marker), beta=case.client_beta) + _assert_answered(response, marker) + observed: Final = _only(wire) + _expect_messages(observed, target=case.target, auth=case.auth, beta=case.expected_beta, keys=case.keys) + for name, value in case.extra_headers.items(): + assert observed.headers.get(name) == value, observed.header_names + assert observed.body.get("anthropic_beta") == case.body_beta, observed.body + _spend_row(f"msg_{marker}") + + +def test_github_copilot_messages_forward_safeguards_without_deriving_the_beta( + gateway: Gateway, tmp_path: Path +) -> None: + marker: Final = uuid.uuid4().hex + token_dir: Final = tmp_path / "copilot" + token_dir.mkdir() + with wire_server(anthropic_peer) as wire: + (token_dir / "api-key.json").write_text( + json.dumps({"token": "synthetic-copilot-token", "expires_at": 4102444800, "endpoints": {"api": wire.url}}) + ) + with ( + owned_proxy(gateway, tmp_path, {"GITHUB_COPILOT_TOKEN_DIR": str(token_dir)}) as owned, + owned.scenario() as scenario, + ): + model: Final = scenario.model(model="github_copilot/claude-sonnet-4-5", api_base=wire.url) + response: Final = _post(owned, messages_body(model, marker), beta=_CLIENT_BETAS_WITH_DANGEROUS) + _assert_answered(response, marker) + observed: Final = _only(wire) + _expect_messages( + observed, target="/v1/messages", auth=("authorization", "Bearer synthetic-copilot-token"), beta=None + ) + assert observed.headers.get("openai-intent") == "messages-proxy", observed.header_names + _spend_row(f"msg_{marker}") + + +def test_non_native_deployments_bridge_to_the_responses_api_without_safeguards_or_the_beta(gateway: Gateway) -> None: + marker: Final = uuid.uuid4().hex + with wire_server(_responses_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model( + model="openai/gpt-4o-mini", api_base=wire.url + "/v1", api_key="synthetic-openai-key" + ) + response: Final = _post(gateway, messages_body(model, marker), beta=_CLIENT_BETAS_WITH_DANGEROUS) + assert response.status_code == 200 and f"answer marker-{marker}" in response.text, response.text + observed: Final = _only(wire) + assert (observed.method, observed.target) == ("POST", "/v1/responses") + assert observed.headers.get("authorization") == "Bearer synthetic-openai-key", observed.header_names + assert observed.beta is None, observed.header_names + assert observed.keys == _RESPONSES_KEYS, observed.keys + _spend_row(str(_JSON_OBJECT.validate_json(response.content)["id"])) + + +def test_chat_completions_forward_safeguards_verbatim_without_deriving_the_beta(gateway: Gateway) -> None: + marker: Final = uuid.uuid4().hex + with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY) + client: Final = openai.OpenAI( + base_url=str(gateway.client.base_url).rstrip("/") + "/v1", api_key=gateway.key, max_retries=0 + ) + completion: Final = client.chat.completions.create( + model=model, messages=[{"role": "user", "content": f"Question marker-{marker}"}], extra_body=_SDK_EXTRA + ) + assert completion.choices[0].message.content == f"answer marker-{marker}", completion + _expect_messages( + _only(wire), + target="/v1/messages", + auth=("x-api-key", ANTHROPIC_KEY), + beta=None, + keys=frozenset({"max_tokens", "messages", "model"}), + ) + _spend_row(completion.id) + + +async def test_responses_stream_forwards_safeguards_verbatim_without_deriving_the_beta(gateway: Gateway) -> None: + marker: Final = uuid.uuid4().hex + with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=f"anthropic/{ANTHROPIC_MODEL}", api_base=wire.url, api_key=ANTHROPIC_KEY) + client: Final = openai.AsyncOpenAI( + base_url=str(gateway.client.base_url).rstrip("/") + "/v1", api_key=gateway.key, max_retries=0 + ) + async with client.responses.with_streaming_response.create( + model=model, input=f"Question marker-{marker}", stream=True, extra_body=_SDK_EXTRA + ) as streamed: + events: Final = [event async for event in await streamed.parse()] + deltas: Final = [event.delta for event in events if event.type == "response.output_text.delta"] + assert "".join(deltas) == f"answer marker-{marker}", events + assert any(event.type == "response.completed" for event in events), events + _expect_messages(_only(wire), target="/v1/messages", auth=("x-api-key", ANTHROPIC_KEY), beta=None) + _responses_spend_row(model) + + +_FOUNDRY_REJECTED_SHAPES: Final[Mapping[str, JsonValue]] = MappingProxyType( + {"S1_int": 1, "S2_empty_string": "", "S3_five_kb_string": "x" * 5000} +) + + +@pytest.mark.parametrize("row", tuple(_FOUNDRY_REJECTED_SHAPES)) +def test_foundry_rejecting_a_non_array_safeguards_value_reaches_the_caller_after_one_attempt( + gateway: Gateway, row: str +) -> None: + value: Final = _FOUNDRY_REJECTED_SHAPES[row] + marker: Final = uuid.uuid4().hex + with ( + wire_server(_error_peer(400, "invalid_request_error", _FOUNDRY_ARRAY_ERROR)) as wire, + gateway.scenario() as scenario, + ): + model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY) + response: Final = _post(gateway, messages_body(model, marker, safeguards=value)) + assert response.status_code == 400 and _FOUNDRY_ARRAY_ERROR in response.text, response.text + _expect_messages( + _only(wire), target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=BETA, safeguards=value + ) + + +def test_duplicate_safeguards_keys_resolve_to_the_last_value(gateway: Gateway) -> None: + marker: Final = uuid.uuid4().hex + with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY) + raw: Final = ( + f'{{"model": "{model}", "max_tokens": 16, "num_retries": 0, "cache": {{"no-cache": true}}, ' + f'"messages": [{{"role": "user", "content": "Question marker-{marker}"}}], ' + f'"safeguards": {json.dumps(SAFEGUARDS)}, "safeguards": null}}' + ) + response: Final = gateway.client.post( + "/v1/messages", + content=raw.encode(), + headers={ + "Authorization": f"Bearer {gateway.key}", + "content-type": "application/json", + **_ANTHROPIC_VERSION, + }, + ) + _assert_answered(response, marker) + _expect_messages( + _only(wire), target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=None, safeguards=OMITTED + ) + _spend_row(f"msg_{marker}") + + +def test_the_same_safeguards_sent_twice_are_two_upstream_calls_with_two_spend_rows(gateway: Gateway) -> None: + markers: Final = (uuid.uuid4().hex, uuid.uuid4().hex) + with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY) + responses: Final = tuple(_post(gateway, messages_body(model, marker)) for marker in markers) + for marker, response in zip(markers, responses, strict=True): + _assert_answered(response, marker) + received: Final = tuple(_observe(request) for request in wire.drain()) + assert len(received) == 2, received + for observed in received: + _expect_messages(observed, target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=BETA) + assert sorted(item.marker for item in received) == sorted(markers) + for marker in markers: + _spend_row(f"msg_{marker}") + + +_UPSTREAM_ERRORS: Final = MappingProxyType( + { + "S6_unauthorized_deployment": (401, "authentication_error", "invalid x-api-key"), + "S7_foundry_extra_inputs_rejection": (400, "invalid_request_error", _FOUNDRY_EXTRA_INPUT_ERROR), + } +) + + +@pytest.mark.parametrize("row", tuple(_UPSTREAM_ERRORS)) +def test_upstream_errors_reach_the_caller_with_the_beta_sent_once(gateway: Gateway, row: str) -> None: + status, kind, message = _UPSTREAM_ERRORS[row] + marker: Final = uuid.uuid4().hex + with wire_server(_error_peer(status, kind, message)) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY) + response: Final = _post(gateway, messages_body(model, marker)) + assert response.status_code == status and message in response.text, response.text + _expect_messages(_only(wire), target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=BETA) + + +def _post_noting_whether_upstream_was_called( + gateway: Gateway, body: Mapping[str, JsonValue], wire: Wire +) -> tuple[httpx.Response, bool]: + before: Final = wire.received.qsize() + response: Final = _post(gateway, body) + assert response.status_code == 200, response.text + return response, wire.received.qsize() > before + + +def _until_served_from_cache(gateway: Gateway, body: Mapping[str, JsonValue], wire: Wire) -> tuple[httpx.Response, int]: + deadline: Final = time.monotonic() + 20 + for attempt in itertools.count(1): + response, called_upstream = _post_noting_whether_upstream_was_called(gateway, body, wire) + if not called_upstream: + return response, attempt + assert time.monotonic() < deadline, "the response cache never served the repeated request" + raise AssertionError("unreachable") + + +def test_the_response_cache_serves_the_repeated_request_without_an_upstream_call(gateway: Gateway) -> None: + marker: Final = uuid.uuid4().hex + with wire_server(anthropic_peer) as wire, gateway.scenario() as scenario: + model: Final = scenario.model(model=_FOUNDRY_MODEL, api_base=wire.url, api_key=_FOUNDRY_KEY) + body: Final = messages_body(model, marker, no_cache=False) + first: Final = _post(gateway, body) + _assert_answered(first, marker) + _expect_messages(_only(wire), target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=BETA) + _spend_row(f"msg_{marker}") + hit, attempts = _until_served_from_cache(gateway, body, wire) + assert hit.json()["id"] == first.json()["id"], hit.text + assert hit.json()["content"] == first.json()["content"], hit.text + _cache_hit_spend_row(f"msg_{marker}") + misses: Final = tuple(_observe(request) for request in wire.drain()) + assert len(misses) == attempts - 1, (attempts, misses) + for observed in misses: + _expect_messages(observed, target=_FOUNDRY_TARGET, auth=("x-api-key", _FOUNDRY_KEY), beta=BETA) diff --git a/tests/unit/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py b/tests/unit/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py index b78b2d0d842..121a4000155 100644 --- a/tests/unit/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py +++ b/tests/unit/llms/azure_ai/claude/test_azure_anthropic_messages_transformation.py @@ -7,13 +7,17 @@ sys.path.insert( 0, os.path.abspath(os.path.join(os.path.dirname(__file__), "../../../../..")) ) +from typing import Final from unittest.mock import patch +import httpx import pytest +import litellm from litellm.llms.azure_ai.anthropic.messages_transformation import ( AzureAnthropicMessagesConfig, ) +from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler from litellm.types.router import GenericLiteLLMParams @@ -470,3 +474,51 @@ def test_azure_claude_4_8_plus_cost_map_entries_carry_mid_conversation_system_fl and info.get("supports_mid_conversation_system") is not True ] assert missing == [] + + +AUTO_MODE_SAFEGUARDS: Final = ({"type": "dangerous_tool_use", "classifier_context": {"v": 1, "permission_mode": "auto"}},) + + +@pytest.mark.usefixtures("local_beta_headers_config") +@pytest.mark.parametrize( + ("client_headers", "optional_params", "expected_beta"), + [ + ({}, {"safeguards": AUTO_MODE_SAFEGUARDS}, "dangerous-tool-use-2026-09-03"), + ( + {"anthropic-beta": "context-1m-2025-08-07"}, + {"safeguards": AUTO_MODE_SAFEGUARDS}, + "context-1m-2025-08-07,dangerous-tool-use-2026-09-03", + ), + ({"anthropic-beta": "context-1m-2025-08-07"}, {}, "context-1m-2025-08-07"), + ({}, {}, None), + ], +) +def test_safeguards_request_carries_the_dangerous_tool_use_beta_without_the_client_header( + client_headers: dict[str, str], optional_params: dict[str, object], expected_beta: str | None +) -> None: + headers, _ = AzureAnthropicMessagesConfig().validate_anthropic_messages_environment( + headers=client_headers, + model="claude-sonnet-4-6", + messages=[{"role": "user", "content": "Run ls -la with the Bash tool"}], + optional_params=optional_params, + litellm_params={"api_key": "test-api-key"}, + ) + assert headers.get("anthropic-beta") == expected_beta, headers + + +def _foundry_answer(request: httpx.Request) -> httpx.Response: + return httpx.Response( + status_code=200, + headers={"content-type": "application/json"}, + json={ + "id": "msg_safeguards", + "type": "message", + "role": "assistant", + "model": "claude-sonnet-4-6", + "content": [{"type": "text", "text": "hello from the gateway"}], + "stop_reason": "end_turn", + "stop_sequence": None, + "usage": {"input_tokens": 12, "output_tokens": 6}, + }, + request=request, + ) diff --git a/tests/unit/llms/custom_httpx/test_llm_http_handler.py b/tests/unit/llms/custom_httpx/test_llm_http_handler.py index 399e4dbf206..97bea84c7ea 100644 --- a/tests/unit/llms/custom_httpx/test_llm_http_handler.py +++ b/tests/unit/llms/custom_httpx/test_llm_http_handler.py @@ -4302,3 +4302,45 @@ async def test_async_text_to_speech_handler_records_upstream_response_headers(): assert response.content == b"audio-bytes" _assert_upstream_headers_recorded(response) + + +@pytest.mark.asyncio +@pytest.mark.usefixtures("local_beta_headers_config") +async def test_anthropic_messages_dropped_safeguards_send_neither_the_field_nor_its_beta() -> None: + received: Final[list[httpx.Request]] = [] + + def anthropic_answers(request: httpx.Request) -> httpx.Response: + received.append(request) + return httpx.Response( + status_code=200, + json={ + "id": "msg_dropped_safeguards", + "type": "message", + "role": "assistant", + "model": "claude-sonnet-4-6", + "content": [{"type": "text", "text": "hi"}], + "stop_reason": "end_turn", + "stop_sequence": None, + "usage": {"input_tokens": 5, "output_tokens": 1}, + }, + request=request, + ) + + upstream: Final = AsyncHTTPHandler(transport=httpx.MockTransport(anthropic_answers)) + try: + await litellm.anthropic.messages.acreate( + max_tokens=16, + messages=[{"role": "user", "content": "hi"}], + model="anthropic/claude-sonnet-4-6", + api_key="sk-ant-test", + safeguards=({"type": "dangerous_tool_use"},), + additional_drop_params=["safeguards"], + client=upstream, + ) + finally: + await upstream.close() + + assert len(received) == 1, received + sent: Final = received[0] + assert "safeguards" not in json.loads(sent.content) + assert "dangerous-tool-use-2026-09-03" not in sent.headers.get("anthropic-beta", ""), dict(sent.headers) diff --git a/tests/unit/llms/openai_like/messages/test_openai_like_anthropic_messages_transformation.py b/tests/unit/llms/openai_like/messages/test_openai_like_anthropic_messages_transformation.py index 07f06c9084c..a5b2e76f3f6 100644 --- a/tests/unit/llms/openai_like/messages/test_openai_like_anthropic_messages_transformation.py +++ b/tests/unit/llms/openai_like/messages/test_openai_like_anthropic_messages_transformation.py @@ -516,3 +516,26 @@ def test_request_strips_ttl_only_where_the_messages_api_defines_cache_control(co assert tool_result["content"][0]["cache_control"] == {"type": "ephemeral"} assert payload["messages"][1]["content"][1]["cache_control"] == {"type": "ephemeral"} assert payload["messages"][2] == {"role": "user", "content": "a plain string message"} + + +@pytest.mark.usefixtures("local_beta_headers_config") +@pytest.mark.parametrize( + ("client_headers", "expected_beta"), + [ + ({}, None), + ({"anthropic-beta": "dangerous-tool-use-2026-09-03"}, "dangerous-tool-use-2026-09-03"), + ], +) +def test_safeguards_reach_an_openai_like_host_with_only_the_client_betas( + config: OpenAILikeAnthropicMessagesConfig, client_headers: dict[str, str], expected_beta: str | None +) -> None: + headers, _ = config.validate_anthropic_messages_environment( + headers=client_headers, + model="some-model", + messages=[{"role": "user", "content": "hi"}], + optional_params={"safeguards": ({"type": "dangerous_tool_use"},)}, + litellm_params={}, + api_key="sk-test", + api_base="https://host/v1", + ) + assert headers.get("anthropic-beta") == expected_beta, headers From d3366b93b45d7f2e2561b76a2b2a0eb53682e017 Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Tue, 20 Oct 2026 15:45:32 -0700 Subject: [PATCH 15/66] feat(model_prices): add claude-haiku-5-5 model pricing (#45108) Backport of #45108 to stable/1.104.x. Cherry-picked from 5cd112687087b01f84e443386c3e27d1f16b62bc (main). Prerequisite for #45151: adds the claude-haiku-5-5 entries that fix corrects. Cost-map conflicts resolved by appending the new entries. --- ...odel_prices_and_context_window_backup.json | 643 ++++++++++++++++++ model_prices_and_context_window.json | 643 ++++++++++++++++++ model_prices_and_context_window.schema.json | 25 + tests/unit/test_utils.py | 5 + 4 files changed, 1316 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 9635cf3ce72..6c3c1154d85 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -77503,5 +77503,648 @@ "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://prices.azure.com/api/retail/prices?$filter=productName eq 'Microsoft Decision Models'" + }, + "claude-haiku-5-5": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/models/haiku-5-5/overview", + "supports_web_search": true, + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08 + }, + "bedrock_mantle/anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html" + }, + "bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_1hr": 2.4e-07, + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html" + }, + "anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "apac.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_creation_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.1e-07, + "output_cost_per_token": 5.5e-07, + "cache_read_input_token_cost": 1.1e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "au.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "azure_ai/claude-haiku-5-5": { + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_read_input_token_cost": 1e-08, + "deprecation_date": "2027-09-29", + "input_cost_per_token": 1e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" + }, + "bedrock/us-gov-east-1/anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_1hr": 2.4e-07, + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "bedrock/us-gov-west-1/anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_1hr": 2.4e-07, + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "eu.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "global.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "jp.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "perplexity/anthropic/claude-haiku-5-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_adaptive_thinking": true, + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "us-gov.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_1hr": 2.4e-07, + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "us.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "vertex_ai/claude-haiku-5-5": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-haiku-5-5@default": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 9635cf3ce72..6c3c1154d85 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -77503,5 +77503,648 @@ "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://prices.azure.com/api/retail/prices?$filter=productName eq 'Microsoft Decision Models'" + }, + "claude-haiku-5-5": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/models/haiku-5-5/overview", + "supports_web_search": true, + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08 + }, + "bedrock_mantle/anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html" + }, + "bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_1hr": 2.4e-07, + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html" + }, + "anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "apac.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_creation_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.1e-07, + "output_cost_per_token": 5.5e-07, + "cache_read_input_token_cost": 1.1e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "au.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "azure_ai/claude-haiku-5-5": { + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_read_input_token_cost": 1e-08, + "deprecation_date": "2027-09-29", + "input_cost_per_token": 1e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" + }, + "bedrock/us-gov-east-1/anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_1hr": 2.4e-07, + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "bedrock/us-gov-west-1/anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_1hr": 2.4e-07, + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "eu.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "global.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "jp.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "perplexity/anthropic/claude-haiku-5-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_adaptive_thinking": true, + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "us-gov.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 1.5e-07, + "cache_creation_input_token_cost_above_1hr": 2.4e-07, + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "us.anthropic.claude-haiku-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 1.375e-07, + "cache_creation_input_token_cost_above_1hr": 2.2e-07, + "cache_read_input_token_cost": 1.1e-08, + "input_cost_per_token": 1.1e-07, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "vertex_ai/claude-haiku-5-5": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-haiku-5-5@default": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "cache_creation_input_token_cost_batches": 6.25e-08, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_batches": 5e-09, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_batches": 2.5e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" } } diff --git a/model_prices_and_context_window.schema.json b/model_prices_and_context_window.schema.json index 5b2d52f11ee..7d6ff36e8f0 100644 --- a/model_prices_and_context_window.schema.json +++ b/model_prices_and_context_window.schema.json @@ -83,6 +83,11 @@ "minimum": 0, "description": "USD per token written to the provider's prompt cache." }, + "cache_creation_input_token_cost_above_100k_tokens": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "cache_creation_input_token_cost_above_128k_tokens": { "type": "number", "minimum": 0, @@ -93,6 +98,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": { "type": "number", "minimum": 0, @@ -160,6 +170,11 @@ "minimum": 0, "description": "USD per prompt token served from the provider's prompt cache." }, + "cache_read_input_token_cost_above_100k_tokens": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "cache_read_input_token_cost_above_128k_tokens": { "type": "number", "minimum": 0, @@ -341,6 +356,11 @@ "minimum": 0, "description": "USD per prompt token." }, + "input_cost_per_token_above_100k_tokens": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "input_cost_per_token_above_128k_tokens": { "type": "number", "minimum": 0, @@ -698,6 +718,11 @@ "minimum": 0, "description": "USD per generated token." }, + "output_cost_per_token_above_100k_tokens": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "output_cost_per_token_above_128k_tokens": { "type": "number", "minimum": 0, diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py index e80ca2a5820..55a160301bf 100644 --- a/tests/unit/test_utils.py +++ b/tests/unit/test_utils.py @@ -760,6 +760,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "cache_creation_input_token_cost": {"type": "number"}, "cache_creation_input_token_cost_above_1hr": {"type": "number"}, "cache_creation_input_token_cost_above_32k_tokens": {"type": "number"}, + "cache_creation_input_token_cost_above_100k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_128k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_200k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_256k_tokens": {"type": "number"}, @@ -773,6 +774,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "cache_creation_input_token_cost_priority": {"type": "number"}, "cache_read_input_token_cost": {"type": "number"}, "cache_read_input_token_cost_above_32k_tokens": {"type": "number"}, + "cache_read_input_token_cost_above_100k_tokens": {"type": "number"}, "cache_read_input_token_cost_above_128k_tokens": {"type": "number"}, "cache_read_input_token_cost_above_200k_tokens": {"type": "number"}, "cache_read_input_token_cost_above_256k_tokens": {"type": "number"}, @@ -781,6 +783,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "cache_read_input_token_cost_above_512k_tokens": {"type": "number"}, "cache_read_input_token_cost_batches": {"type": "number"}, "cache_read_input_token_cost_above_272k_tokens_batches": {"type": "number"}, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": {"type": "number"}, "cache_read_input_audio_token_cost": {"type": "number"}, "cache_read_input_image_token_cost": {"type": "number"}, @@ -797,6 +800,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "input_cost_per_image_above_128k_tokens": {"type": "number"}, "input_cost_per_video_token": {"type": "number"}, "input_cost_per_token_above_32k_tokens": {"type": "number"}, + "input_cost_per_token_above_100k_tokens": {"type": "number"}, "input_cost_per_token_above_200k_tokens": {"type": "number"}, "input_cost_per_token_above_256k_tokens": {"type": "number"}, "input_cost_per_token_above_272k_tokens": {"type": "number"}, @@ -896,6 +900,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "output_cost_per_second_4k": {"type": "number"}, "output_cost_per_token": {"type": "number"}, "output_cost_per_token_above_32k_tokens": {"type": "number"}, + "output_cost_per_token_above_100k_tokens": {"type": "number"}, "output_cost_per_token_above_128k_tokens": {"type": "number"}, "output_cost_per_token_above_200k_tokens": {"type": "number"}, "output_cost_per_token_above_256k_tokens": {"type": "number"}, From 2ac8b35a05150fff31422c5b18456296398bbacb Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 20 Oct 2026 15:46:08 -0700 Subject: [PATCH 16/66] fix(model_prices): consolidate claude-haiku-5-5 over-100k pricing and capability flags (#45151) Backport of #45151 to stable/1.104.x. Cherry-picked from 46d440ae9604f81b39d66152b1aceed87e0f9d30 (main). Conflicts resolved by keeping the line's fields and adding only the over-100k fields this PR introduces; cost-map entries replaced per model. --- .../crates/model-catalog/src/model_info.rs | 18 ++ .../tests/registry_validation.rs | 17 ++ ...odel_prices_and_context_window_backup.json | 197 ++++++++++++++---- litellm/types/utils.py | 20 +- model_prices_and_context_window.json | 197 ++++++++++++++---- model_prices_and_context_window.schema.json | 20 ++ .../llm_cost_calc/test_llm_cost_calc_utils.py | 135 ++++++++++++ tests/unit/test_claude_haiku_5_5_config.py | 128 ++++++++++++ tests/unit/test_utils.py | 4 + ui/litellm-dashboard/src/lib/http/schema.d.ts | 36 ++++ 10 files changed, 689 insertions(+), 83 deletions(-) create mode 100644 tests/unit/test_claude_haiku_5_5_config.py diff --git a/litellm-rust/crates/model-catalog/src/model_info.rs b/litellm-rust/crates/model-catalog/src/model_info.rs index 7b8ce15fbd6..de8390046ab 100644 --- a/litellm-rust/crates/model-catalog/src/model_info.rs +++ b/litellm-rust/crates/model-catalog/src/model_info.rs @@ -29,10 +29,16 @@ pub struct ModelInfo { #[serde(skip_serializing_if = "Option::is_none")] pub cache_creation_input_token_cost_above_32k_tokens: Option, #[serde(skip_serializing_if = "Option::is_none")] + pub cache_creation_input_token_cost_above_100k_tokens: Option, + #[serde(skip_serializing_if = "Option::is_none")] + pub cache_creation_input_token_cost_above_100k_tokens_batches: Option, + #[serde(skip_serializing_if = "Option::is_none")] pub cache_creation_input_token_cost_above_128k_tokens: Option, /// Rate applied once the prompt exceeds the token threshold in the field name. #[serde(skip_serializing_if = "Option::is_none")] pub cache_creation_input_token_cost_above_1hr: Option, + #[serde(skip_serializing_if = "Option::is_none")] + pub cache_creation_input_token_cost_above_1hr_above_100k_tokens: Option, /// Rate applied once the prompt exceeds the token threshold in the field name. #[serde(skip_serializing_if = "Option::is_none")] pub cache_creation_input_token_cost_above_1hr_above_200k_tokens: Option, @@ -76,6 +82,10 @@ pub struct ModelInfo { #[serde(skip_serializing_if = "Option::is_none")] pub cache_read_input_token_cost_above_32k_tokens: Option, #[serde(skip_serializing_if = "Option::is_none")] + pub cache_read_input_token_cost_above_100k_tokens: Option, + #[serde(skip_serializing_if = "Option::is_none")] + pub cache_read_input_token_cost_above_100k_tokens_batches: Option, + #[serde(skip_serializing_if = "Option::is_none")] pub cache_read_input_token_cost_above_128k_tokens: Option, /// Rate applied once the prompt exceeds the token threshold in the field name. #[serde(skip_serializing_if = "Option::is_none")] @@ -183,6 +193,10 @@ pub struct ModelInfo { #[serde(skip_serializing_if = "Option::is_none")] pub input_cost_per_token_above_32k_tokens: Option, #[serde(skip_serializing_if = "Option::is_none")] + pub input_cost_per_token_above_100k_tokens: Option, + #[serde(skip_serializing_if = "Option::is_none")] + pub input_cost_per_token_above_100k_tokens_batches: Option, + #[serde(skip_serializing_if = "Option::is_none")] pub input_cost_per_token_above_128k_tokens: Option, /// Rate applied once the prompt exceeds the token threshold in the field name. #[serde(skip_serializing_if = "Option::is_none")] @@ -329,6 +343,10 @@ pub struct ModelInfo { #[serde(skip_serializing_if = "Option::is_none")] pub output_cost_per_token_above_32k_tokens: Option, #[serde(skip_serializing_if = "Option::is_none")] + pub output_cost_per_token_above_100k_tokens: Option, + #[serde(skip_serializing_if = "Option::is_none")] + pub output_cost_per_token_above_100k_tokens_batches: Option, + #[serde(skip_serializing_if = "Option::is_none")] pub output_cost_per_token_above_128k_tokens: Option, /// Rate applied once the prompt exceeds the token threshold in the field name. #[serde(skip_serializing_if = "Option::is_none")] diff --git a/litellm-rust/crates/model-catalog/tests/registry_validation.rs b/litellm-rust/crates/model-catalog/tests/registry_validation.rs index 8f555e1f884..67589010aba 100644 --- a/litellm-rust/crates/model-catalog/tests/registry_validation.rs +++ b/litellm-rust/crates/model-catalog/tests/registry_validation.rs @@ -74,3 +74,20 @@ fn checked_in_catalog_and_backup_match() { "invalid registry aliases" ); } + +#[rstest] +#[case::input("input_cost_per_token_above_100k_tokens")] +#[case::input_batches("input_cost_per_token_above_100k_tokens_batches")] +#[case::output("output_cost_per_token_above_100k_tokens")] +#[case::output_batches("output_cost_per_token_above_100k_tokens_batches")] +#[case::cache_creation("cache_creation_input_token_cost_above_100k_tokens")] +#[case::cache_creation_batches("cache_creation_input_token_cost_above_100k_tokens_batches")] +#[case::cache_creation_1hr("cache_creation_input_token_cost_above_1hr_above_100k_tokens")] +#[case::cache_read("cache_read_input_token_cost_above_100k_tokens")] +#[case::cache_read_batches("cache_read_input_token_cost_above_100k_tokens_batches")] +fn registry_validation_keeps_above_100k_tier_rates(#[case] field: &str) { + let mut entry = Map::new(); + entry.insert("litellm_provider".into(), "anthropic".into()); + entry.insert(field.into(), 5e-7.into()); + validate_model_entry("test", &Value::Object(entry)).unwrap(); +} diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 6c3c1154d85..d9d544a4fa7 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -77505,6 +77505,10 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=productName eq 'Microsoft Decision Models'" }, "claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens_batches": 2.5e-07, + "output_cost_per_token_above_100k_tokens_batches": 1.25e-06, + "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07, + "cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-08, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, @@ -77544,8 +77548,8 @@ "us": 1.1 }, "supports_output_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/models/haiku-5-5/overview", "supports_web_search": true, @@ -77556,6 +77560,11 @@ "cache_read_input_token_cost_above_100k_tokens": 5e-08 }, "bedrock_mantle/anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, @@ -77591,12 +77600,17 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html" }, "bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 6e-07, + "output_cost_per_token_above_100k_tokens": 3e-06, + "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, + "cache_read_input_token_cost_above_100k_tokens": 6e-08, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.5e-07, @@ -77610,8 +77624,8 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, @@ -77633,6 +77647,11 @@ "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html" }, "anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, @@ -77668,12 +77687,17 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "apac.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "litellm_provider": "bedrock_converse", "supports_tool_search": true, @@ -77699,8 +77723,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, "cache_creation_input_token_cost_above_1hr": 2.2e-07, "cache_creation_input_token_cost": 1.375e-07, @@ -77710,6 +77734,11 @@ "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "au.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, @@ -77745,12 +77774,17 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "azure_ai/claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, @@ -77781,12 +77815,17 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" + "source": "https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide" }, "bedrock/us-gov-east-1/anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 6e-07, + "output_cost_per_token_above_100k_tokens": 3e-06, + "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, + "cache_read_input_token_cost_above_100k_tokens": 6e-08, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.5e-07, @@ -77800,9 +77839,10 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -77822,6 +77862,11 @@ "supports_xhigh_reasoning_effort": true }, "bedrock/us-gov-west-1/anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 6e-07, + "output_cost_per_token_above_100k_tokens": 3e-06, + "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, + "cache_read_input_token_cost_above_100k_tokens": 6e-08, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.5e-07, @@ -77835,9 +77880,10 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -77857,6 +77903,11 @@ "supports_xhigh_reasoning_effort": true }, "eu.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, @@ -77892,12 +77943,17 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, @@ -77933,12 +77989,17 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "jp.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, @@ -77974,10 +78035,10 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "perplexity/anthropic/claude-haiku-5-5": { "litellm_provider": "perplexity", @@ -77991,6 +78052,11 @@ "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "us-gov.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 6e-07, + "output_cost_per_token_above_100k_tokens": 3e-06, + "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, + "cache_read_input_token_cost_above_100k_tokens": 6e-08, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.5e-07, @@ -78004,10 +78070,10 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -78027,6 +78093,11 @@ "supports_xhigh_reasoning_effort": true }, "us.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, @@ -78062,12 +78133,17 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "vertex_ai/claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-07, @@ -78102,12 +78178,17 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/claude-haiku-5-5@default": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-07, @@ -78142,9 +78223,43 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "openrouter/anthropic/claude-haiku-5.5": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 512, + "supports_sampling_params": false } } diff --git a/litellm/types/utils.py b/litellm/types/utils.py index 2cce951ca60..97a51f42851 100644 --- a/litellm/types/utils.py +++ b/litellm/types/utils.py @@ -284,6 +284,8 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): input_cost_per_token_ultrafast: ReadOnly[float | None] # OpenAI ultrafast service tier pricing cache_creation_input_token_cost: float | None cache_creation_input_token_cost_above_200k_tokens: float | None + cache_creation_input_token_cost_above_100k_tokens: ReadOnly[float | None] + cache_creation_input_token_cost_above_1hr_above_100k_tokens: ReadOnly[float | None] cache_creation_input_token_cost_above_272k_tokens: float | None cache_creation_input_token_cost_above_272k_tokens_priority: float | None cache_creation_input_token_cost_above_272k_tokens_flex: float | None @@ -298,15 +300,18 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): cache_read_input_token_cost_priority: float | None # OpenAI priority service tier pricing cache_read_input_token_cost_ultrafast: ReadOnly[float | None] # OpenAI ultrafast service tier pricing cache_read_input_token_cost_above_200k_tokens: float | None + cache_read_input_token_cost_above_100k_tokens: ReadOnly[float | None] cache_read_input_token_cost_above_200k_tokens_priority: float | None cache_read_input_token_cost_above_272k_tokens: float | None cache_read_input_token_cost_above_272k_tokens_priority: float | None cache_read_input_token_cost_above_272k_tokens_flex: float | None cache_read_input_token_cost_above_512k_tokens: float | None cache_read_input_token_cost_batches: ReadOnly[float | None] + cache_read_input_token_cost_above_100k_tokens_batches: ReadOnly[float | None] cache_read_input_token_cost_above_272k_tokens_batches: ReadOnly[float | None] cache_creation_input_token_cost_batches: ReadOnly[float | None] cache_creation_input_token_cost_above_200k_tokens_batches: ReadOnly[float | None] + cache_creation_input_token_cost_above_100k_tokens_batches: ReadOnly[float | None] cache_creation_input_token_cost_above_272k_tokens_batches: ReadOnly[float | None] # Smallest prefix this model will actually cache, whatever caching mechanism its provider uses. # Absent means the provider-agnostic default applies; see MINIMUM_PROMPT_CACHE_TOKEN_COUNT. @@ -316,6 +321,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): input_cost_per_audio_token: float | None input_cost_per_token_above_128k_tokens: float | None # only for vertex ai models input_cost_per_token_above_200k_tokens: float | None # only for vertex ai gemini-2.5-pro models + input_cost_per_token_above_100k_tokens: ReadOnly[float | None] input_cost_per_token_above_200k_tokens_priority: float | None input_cost_per_token_above_272k_tokens: float | None # GPT-5.4/5.4-pro: prompts >272K priced at 2x input input_cost_per_token_above_272k_tokens_priority: float | None @@ -333,8 +339,10 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): input_cost_per_second: float | None # for OpenAI Speech models input_cost_per_token_batches: float | None input_cost_per_video_token_batches: ReadOnly[float | None] + input_cost_per_token_above_100k_tokens_batches: ReadOnly[float | None] input_cost_per_token_above_272k_tokens_batches: ReadOnly[float | None] output_cost_per_token_batches: float | None + output_cost_per_token_above_100k_tokens_batches: ReadOnly[float | None] output_cost_per_token_above_272k_tokens_batches: ReadOnly[float | None] output_cost_per_token: Required[float | None] output_cost_per_token_flex: float | None # OpenAI flex service tier pricing @@ -353,6 +361,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): output_cost_per_audio_token: float | None output_cost_per_token_above_128k_tokens: float | None # only for vertex ai models output_cost_per_token_above_200k_tokens: float | None # only for vertex ai gemini-2.5-pro models + output_cost_per_token_above_100k_tokens: ReadOnly[float | None] output_cost_per_token_above_200k_tokens_priority: float | None output_cost_per_token_above_272k_tokens: float | None # GPT-5.4/5.4-pro: prompts >272K priced at 1.5x output output_cost_per_token_above_272k_tokens_priority: float | None @@ -3731,6 +3740,8 @@ class CustomPricingLiteLLMParams(MirroredPricingParams): input_cost_per_token_priority: float | None = None input_cost_per_token_ultrafast: float | None = None cache_creation_input_token_cost_above_1hr: float | None = None + cache_creation_input_token_cost_above_100k_tokens: float | None = None + cache_creation_input_token_cost_above_1hr_above_100k_tokens: float | None = None cache_creation_input_token_cost_above_200k_tokens: float | None = None cache_creation_input_token_cost_above_272k_tokens: float | None = None cache_creation_input_token_cost_above_272k_tokens_priority: float | None = None @@ -3742,13 +3753,16 @@ class CustomPricingLiteLLMParams(MirroredPricingParams): cache_read_input_token_cost_flex: float | None = None cache_read_input_token_cost_priority: float | None = None cache_read_input_token_cost_ultrafast: float | None = None + cache_read_input_token_cost_above_100k_tokens: float | None = None cache_read_input_token_cost_above_200k_tokens: float | None = None cache_read_input_token_cost_above_200k_tokens_priority: float | None = None cache_read_input_token_cost_above_272k_tokens_priority: float | None = None cache_read_input_token_cost_above_272k_tokens_flex: float | None = None cache_read_input_token_cost_batches: float | None = None + cache_read_input_token_cost_above_100k_tokens_batches: float | None = None cache_read_input_token_cost_above_272k_tokens_batches: float | None = None cache_creation_input_token_cost_batches: float | None = None + cache_creation_input_token_cost_above_100k_tokens_batches: float | None = None cache_creation_input_token_cost_above_200k_tokens_batches: float | None = None cache_creation_input_token_cost_above_272k_tokens_batches: float | None = None cache_read_input_audio_token_cost: float | None = None @@ -3757,10 +3771,12 @@ class CustomPricingLiteLLMParams(MirroredPricingParams): input_cost_per_audio_token: float | None = None input_cost_per_token_cache_hit: float | None = None input_cost_per_token_above_128k_tokens: float | None = None + input_cost_per_token_above_100k_tokens: float | None = None input_cost_per_token_above_200k_tokens: float | None = None input_cost_per_token_above_200k_tokens_priority: float | None = None input_cost_per_token_above_272k_tokens_priority: float | None = None input_cost_per_token_above_272k_tokens_flex: float | None = None + input_cost_per_token_above_100k_tokens_batches: float | None = None input_cost_per_token_above_272k_tokens_batches: float | None = None input_cost_per_query: float | None = None input_cost_per_image: float | None = None @@ -3781,10 +3797,12 @@ class CustomPricingLiteLLMParams(MirroredPricingParams): output_cost_per_token_ultrafast: float | None = None output_cost_per_audio_token: float | None = None output_cost_per_token_above_128k_tokens: float | None = None + output_cost_per_token_above_100k_tokens: float | None = None output_cost_per_token_above_200k_tokens: float | None = None output_cost_per_token_above_200k_tokens_priority: float | None = None output_cost_per_token_above_272k_tokens_priority: float | None = None output_cost_per_token_above_272k_tokens_flex: float | None = None + output_cost_per_token_above_100k_tokens_batches: float | None = None output_cost_per_token_above_272k_tokens_batches: float | None = None output_cost_per_character_above_128k_tokens: float | None = None output_cost_per_image: float | None = None @@ -3851,7 +3869,7 @@ def shared_backend_model_info(model_info: dict[str, Any]) -> dict[str, Any]: return {k: v for k, v in model_info.items() if k in SHARED_BACKEND_MODEL_INFO_FIELDS} -ABOVE_THRESHOLD_COST_KEY_PATTERN: Final = re.compile(r"_above_\d+k?_tokens$") +ABOVE_THRESHOLD_COST_KEY_PATTERN: Final = re.compile(r"_above_\d+k?_tokens(?:_batches)?$") _PRICING_FIELD_EXEMPTIONS: Final[frozenset[str]] = frozenset({"output_vector_size"}) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 6c3c1154d85..d9d544a4fa7 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -77505,6 +77505,10 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=productName eq 'Microsoft Decision Models'" }, "claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens_batches": 2.5e-07, + "output_cost_per_token_above_100k_tokens_batches": 1.25e-06, + "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07, + "cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-08, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, @@ -77544,8 +77548,8 @@ "us": 1.1 }, "supports_output_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://platform.claude.com/docs/en/models/haiku-5-5/overview", "supports_web_search": true, @@ -77556,6 +77560,11 @@ "cache_read_input_token_cost_above_100k_tokens": 5e-08 }, "bedrock_mantle/anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, @@ -77591,12 +77600,17 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html" }, "bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 6e-07, + "output_cost_per_token_above_100k_tokens": 3e-06, + "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, + "cache_read_input_token_cost_above_100k_tokens": 6e-08, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.5e-07, @@ -77610,8 +77624,8 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, @@ -77633,6 +77647,11 @@ "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html" }, "anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, @@ -77668,12 +77687,17 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "apac.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "litellm_provider": "bedrock_converse", "supports_tool_search": true, @@ -77699,8 +77723,8 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, "cache_creation_input_token_cost_above_1hr": 2.2e-07, "cache_creation_input_token_cost": 1.375e-07, @@ -77710,6 +77734,11 @@ "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "au.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, @@ -77745,12 +77774,17 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "azure_ai/claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, @@ -77781,12 +77815,17 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" + "source": "https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide" }, "bedrock/us-gov-east-1/anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 6e-07, + "output_cost_per_token_above_100k_tokens": 3e-06, + "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, + "cache_read_input_token_cost_above_100k_tokens": 6e-08, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.5e-07, @@ -77800,9 +77839,10 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -77822,6 +77862,11 @@ "supports_xhigh_reasoning_effort": true }, "bedrock/us-gov-west-1/anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 6e-07, + "output_cost_per_token_above_100k_tokens": 3e-06, + "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, + "cache_read_input_token_cost_above_100k_tokens": 6e-08, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.5e-07, @@ -77835,9 +77880,10 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -77857,6 +77903,11 @@ "supports_xhigh_reasoning_effort": true }, "eu.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, @@ -77892,12 +77943,17 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.25e-07, "cache_creation_input_token_cost_above_1hr": 2e-07, @@ -77933,12 +77989,17 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "jp.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, @@ -77974,10 +78035,10 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "perplexity/anthropic/claude-haiku-5-5": { "litellm_provider": "perplexity", @@ -77991,6 +78052,11 @@ "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "us-gov.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 6e-07, + "output_cost_per_token_above_100k_tokens": 3e-06, + "cache_creation_input_token_cost_above_100k_tokens": 7.5e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06, + "cache_read_input_token_cost_above_100k_tokens": 6e-08, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.5e-07, @@ -78004,10 +78070,10 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, @@ -78027,6 +78093,11 @@ "supports_xhigh_reasoning_effort": true }, "us.anthropic.claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5.5e-07, + "output_cost_per_token_above_100k_tokens": 2.75e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5.5e-08, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost": 1.375e-07, "cache_creation_input_token_cost_above_1hr": 2.2e-07, @@ -78062,12 +78133,17 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "vertex_ai/claude-haiku-5-5": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-07, @@ -78102,12 +78178,17 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "vertex_ai/claude-haiku-5-5@default": { + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-07, @@ -78142,9 +78223,43 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "supports_forced_tool_use": false, - "thinking_always_on": true, + "supports_forced_tool_use": true, + "thinking_always_on": false, "prompt_cache_min_tokens": 512, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "openrouter/anthropic/claude-haiku-5.5": { + "input_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_1hr": 2e-07, + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://openrouter.ai/api/v1/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_web_search": true, + "supports_adaptive_thinking": true, + "prompt_cache_min_tokens": 512, + "supports_sampling_params": false } } diff --git a/model_prices_and_context_window.schema.json b/model_prices_and_context_window.schema.json index 7d6ff36e8f0..0060f821ba3 100644 --- a/model_prices_and_context_window.schema.json +++ b/model_prices_and_context_window.schema.json @@ -88,6 +88,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "cache_creation_input_token_cost_above_100k_tokens_batches": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "cache_creation_input_token_cost_above_128k_tokens": { "type": "number", "minimum": 0, @@ -175,6 +180,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "cache_read_input_token_cost_above_100k_tokens_batches": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "cache_read_input_token_cost_above_128k_tokens": { "type": "number", "minimum": 0, @@ -361,6 +371,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "input_cost_per_token_above_100k_tokens_batches": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "input_cost_per_token_above_128k_tokens": { "type": "number", "minimum": 0, @@ -723,6 +738,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "output_cost_per_token_above_100k_tokens_batches": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "output_cost_per_token_above_128k_tokens": { "type": "number", "minimum": 0, diff --git a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index 0afd989272e..e599a4b6353 100644 --- a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -3801,3 +3801,138 @@ def test_azure_gpt_5_6_alias_matches_sol_pricing(_local_model_cost_map, region_p assert shared_cost_fields for field in shared_cost_fields: assert alias[field] == sol[field], field + + +# Per-token rates read 2026-10-07 from https://platform.claude.com/docs/en/about-claude/pricing (direct and +# azure_ai, which Microsoft bills at Anthropic's rates per +# https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models-billing) and from the +# AmazonBedrockFoundationModels price list at +# https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json (Bedrock) +@pytest.mark.parametrize( + ("model", "custom_llm_provider", "prompt_tokens", "input_rate", "cache_read_rate", "output_rate"), + [ + ("claude-haiku-5-5", "anthropic", 100_000, 1e-07, 1e-08, 5e-07), + ("claude-haiku-5-5", "anthropic", 100_001, 5e-07, 5e-08, 2.5e-06), + ("azure_ai/claude-haiku-5-5", "azure_ai", 100_000, 1e-07, 1e-08, 5e-07), + ("azure_ai/claude-haiku-5-5", "azure_ai", 100_001, 5e-07, 5e-08, 2.5e-06), + ("global.anthropic.claude-haiku-5-5", "bedrock", 100_000, 1e-07, 1e-08, 5e-07), + ("global.anthropic.claude-haiku-5-5", "bedrock", 100_001, 5e-07, 5e-08, 2.5e-06), + ("us.anthropic.claude-haiku-5-5", "bedrock", 100_000, 1.1e-07, 1.1e-08, 5.5e-07), + ("us.anthropic.claude-haiku-5-5", "bedrock", 100_001, 5.5e-07, 5.5e-08, 2.75e-06), + ("us-gov.anthropic.claude-haiku-5-5", "bedrock", 100_000, 1.2e-07, 1.2e-08, 6e-07), + ("us-gov.anthropic.claude-haiku-5-5", "bedrock", 100_001, 6e-07, 6e-08, 3e-06), + ("bedrock_mantle/anthropic.claude-haiku-5-5", "bedrock_mantle", 100_001, 5.5e-07, 5.5e-08, 2.75e-06), + ("bedrock/us-gov-west-1/anthropic.claude-haiku-5-5", "bedrock", 100_001, 6e-07, 6e-08, 3e-06), + ("vertex_ai/claude-haiku-5-5", "vertex_ai", 100_000, 1e-07, 1e-08, 5e-07), + ("vertex_ai/claude-haiku-5-5", "vertex_ai", 100_001, 5e-07, 5e-08, 2.5e-06), + ], +) +def test_generic_cost_per_token_claude_haiku_5_5_prompt_length_tiers( + _local_model_cost_map: None, + model: str, + custom_llm_provider: str, + prompt_tokens: int, + input_rate: float, + cache_read_rate: float, + output_rate: float, +) -> None: + """Claude Haiku 5.5 bills every token at 5x the base rates once the prompt is over 100,000 tokens.""" + cached_tokens: Final = 10_000 + completion_tokens: Final = 1_000 + usage: Final = Usage( + prompt_tokens=prompt_tokens, + completion_tokens=completion_tokens, + total_tokens=prompt_tokens + completion_tokens, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=cached_tokens), + ) + + prompt_cost, completion_cost = generic_cost_per_token( + model=model, + usage=usage, + custom_llm_provider=custom_llm_provider, + ) + + assert prompt_cost == pytest.approx((prompt_tokens - cached_tokens) * input_rate + cached_tokens * cache_read_rate) + assert completion_cost == pytest.approx(completion_tokens * output_rate) + + +def test_vertex_regional_endpoint_uplift_scales_claude_haiku_5_5_over_100k_rates( + _local_model_cost_map: None, +) -> None: + """Vertex regional endpoints bill 1.1x the global rate on all token types + (https://cloud.google.com/vertex-ai/generative-ai/pricing, 2026-10-07: regional + over-100K input is $0.55/MTok), so the uplift scales the over-100k rates too.""" + cached_tokens: Final = 10_000 + prompt_tokens: Final = 100_001 + completion_tokens: Final = 1_000 + usage: Final = Usage( + prompt_tokens=prompt_tokens, + completion_tokens=completion_tokens, + total_tokens=prompt_tokens + completion_tokens, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=cached_tokens), + ) + + prompt_cost, completion_cost = generic_cost_per_token( + model="vertex_ai/claude-haiku-5-5", + usage=usage, + custom_llm_provider="vertex_ai", + vertex_location="us-east5", + ) + + assert prompt_cost == pytest.approx((prompt_tokens - cached_tokens) * 5.5e-07 + cached_tokens * 5.5e-08) + assert completion_cost == pytest.approx(completion_tokens * 2.75e-06) + + +# Batch rates read 2026-10-07 from the Batch processing table at +# https://platform.claude.com/docs/en/about-claude/pricing: $0.05 / $0.25 per MTok input and $0.25 / $1.25 output, +# up to and over 100,000 prompt tokens +@pytest.mark.parametrize( + ("prompt_tokens", "input_rate", "output_rate"), + [(100_000, 5e-08, 2.5e-07), (100_001, 2.5e-07, 1.25e-06)], +) +def test_batch_cost_calculator_claude_haiku_5_5_prompt_length_tiers( + _local_model_cost_map: None, + prompt_tokens: int, + input_rate: float, + output_rate: float, +) -> None: + from litellm.cost_calculator import batch_cost_calculator + + completion_tokens: Final = 1_000 + + prompt_cost, completion_cost = batch_cost_calculator( + usage=Usage( + prompt_tokens=prompt_tokens, + completion_tokens=completion_tokens, + total_tokens=prompt_tokens + completion_tokens, + ), + model="claude-haiku-5-5", + custom_llm_provider="anthropic", + ) + + assert prompt_cost == pytest.approx(prompt_tokens * input_rate) + assert completion_cost == pytest.approx(completion_tokens * output_rate) + + +@pytest.mark.parametrize( + ("prompt_tokens", "expected"), + [ + (100_000, (5e-08, 2.5e-07, 5e-09, 6.25e-08)), + (100_001, (2.5e-07, 1.25e-06, 2.5e-08, 3.125e-07)), + ], +) +def test_get_batch_cost_rates_claude_haiku_5_5_prompt_length_tiers( + _local_model_cost_map: None, + prompt_tokens: int, + expected: tuple[float, float, float, float], +) -> None: + """Cache write and cache read batch rates are 50% of the standard rates; Anthropic's batch table omits them.""" + from litellm.litellm_core_utils.llm_cost_calc.utils import get_batch_cost_rates + + rates: Final = get_batch_cost_rates( + litellm.get_model_info(model="claude-haiku-5-5", custom_llm_provider="anthropic"), + Usage(prompt_tokens=prompt_tokens, completion_tokens=1, total_tokens=prompt_tokens + 1), + "anthropic", + ) + + assert (rates.input, rates.output, rates.cache_read, rates.cache_creation) == expected diff --git a/tests/unit/test_claude_haiku_5_5_config.py b/tests/unit/test_claude_haiku_5_5_config.py new file mode 100644 index 00000000000..770014952e4 --- /dev/null +++ b/tests/unit/test_claude_haiku_5_5_config.py @@ -0,0 +1,128 @@ +""" +Validate Claude Haiku 5.5 model configuration entries. + +Haiku 5.5 ships with adaptive thinking on by default, but unlike Sonnet 5.5 / +Opus 5.5 thinking can still be turned off (``thinking: disabled`` at high +effort or below) and it accepts a forced ``tool_choice`` (``any`` or a named +tool). Its cost-map rows therefore carry ``thinking_always_on: false`` and +``supports_forced_tool_use: true``. +""" + +import json +import os +from collections.abc import Iterator +from typing import Final, cast + +import pytest + +import litellm +from litellm.litellm_core_utils.get_model_cost_map import GetModelCostMap +from litellm.llms.anthropic.common_utils import AnthropicModelInfo + +REPO_ROOT: Final = os.path.join(os.path.dirname(__file__), "../..") + +GET_WEATHER_TOOL: Final = { + "type": "function", + "function": { + "name": "get_weather", + "description": "Get the weather", + "parameters": { + "type": "object", + "properties": {"city": {"type": "string"}}, + }, + }, +} + + +@pytest.fixture(autouse=True) +def local_model_cost_map(monkeypatch: pytest.MonkeyPatch) -> Iterator[None]: + monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") + monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url="")) + monkeypatch.setattr(litellm, "disable_aiohttp_transport", True) + litellm.get_model_info.cache_clear() + yield + litellm.get_model_info.cache_clear() + + +def _load_root_cost_map() -> dict[str, dict[str, object]]: + json_path: Final = os.path.join(REPO_ROOT, "model_prices_and_context_window.json") + with open(json_path) as f: + return cast(dict[str, dict[str, object]], json.load(f)) + + +HAIKU_5_5_VARIANTS: Final = ( + "claude-haiku-5-5", + "anthropic.claude-haiku-5-5", + "apac.anthropic.claude-haiku-5-5", + "au.anthropic.claude-haiku-5-5", + "eu.anthropic.claude-haiku-5-5", + "global.anthropic.claude-haiku-5-5", + "jp.anthropic.claude-haiku-5-5", + "us.anthropic.claude-haiku-5-5", + "us-gov.anthropic.claude-haiku-5-5", + "bedrock/us-gov-east-1/anthropic.claude-haiku-5-5", + "bedrock/us-gov-west-1/anthropic.claude-haiku-5-5", + "bedrock_mantle/anthropic.claude-haiku-5-5", + "bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5", + "vertex_ai/claude-haiku-5-5", + "vertex_ai/claude-haiku-5-5@default", +) + + +@pytest.mark.parametrize("model_name", HAIKU_5_5_VARIANTS) +def test_haiku_5_5_rows_allow_disabling_thinking_and_forced_tools( + model_name: str, +) -> None: + root: Final = _load_root_cost_map() + backup: Final = GetModelCostMap.load_local_model_cost_map() + assert model_name in root + row: Final = root[model_name] + # https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5 (2026-10-07): + # thinking can be disabled, forced tool_choice accepted + assert row["thinking_always_on"] is False + assert row["supports_forced_tool_use"] is True + assert backup[model_name] == row + + +@pytest.mark.parametrize( + ("model", "provider"), + [ + ("claude-haiku-5-5", "anthropic"), + ("anthropic/claude-haiku-5-5", "anthropic"), + ("vertex_ai/claude-haiku-5-5", "vertex_ai"), + ], +) +def test_haiku_5_5_runtime_profile(local_model_cost_map: None, model: str, provider: str) -> None: + assert AnthropicModelInfo._is_adaptive_thinking_model(model, provider) is True + assert AnthropicModelInfo._is_always_on_thinking_model(model, provider) is False + assert AnthropicModelInfo.forced_tool_use_unsupported(model.removeprefix("anthropic/")) is False + + +def test_haiku_5_5_anthropic_tool_choice_required_maps_to_any( + local_model_cost_map: None, +) -> None: + optional_params: Final = litellm.AnthropicConfig().map_openai_params( + non_default_params={ + "tools": [dict(GET_WEATHER_TOOL)], + "tool_choice": "required", + }, + optional_params={}, + model="claude-haiku-5-5", + drop_params=False, + ) + assert optional_params["tool_choice"] == {"type": "any"} + + +def test_haiku_5_5_bedrock_tool_choice_required_maps_to_any( + local_model_cost_map: None, +) -> None: + optional_params: Final = litellm.AmazonConverseConfig().map_openai_params( + non_default_params={ + "tools": [dict(GET_WEATHER_TOOL)], + "tool_choice": "required", + }, + optional_params={}, + model="us.anthropic.claude-haiku-5-5", + drop_params=False, + ) + assert optional_params["tool_choice"] == {"any": {}} diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py index 55a160301bf..c40121e284f 100644 --- a/tests/unit/test_utils.py +++ b/tests/unit/test_utils.py @@ -761,6 +761,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "cache_creation_input_token_cost_above_1hr": {"type": "number"}, "cache_creation_input_token_cost_above_32k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_100k_tokens": {"type": "number"}, + "cache_creation_input_token_cost_above_100k_tokens_batches": {"type": "number"}, "cache_creation_input_token_cost_above_128k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_200k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_256k_tokens": {"type": "number"}, @@ -775,6 +776,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "cache_read_input_token_cost": {"type": "number"}, "cache_read_input_token_cost_above_32k_tokens": {"type": "number"}, "cache_read_input_token_cost_above_100k_tokens": {"type": "number"}, + "cache_read_input_token_cost_above_100k_tokens_batches": {"type": "number"}, "cache_read_input_token_cost_above_128k_tokens": {"type": "number"}, "cache_read_input_token_cost_above_200k_tokens": {"type": "number"}, "cache_read_input_token_cost_above_256k_tokens": {"type": "number"}, @@ -801,6 +803,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "input_cost_per_video_token": {"type": "number"}, "input_cost_per_token_above_32k_tokens": {"type": "number"}, "input_cost_per_token_above_100k_tokens": {"type": "number"}, + "input_cost_per_token_above_100k_tokens_batches": {"type": "number"}, "input_cost_per_token_above_200k_tokens": {"type": "number"}, "input_cost_per_token_above_256k_tokens": {"type": "number"}, "input_cost_per_token_above_272k_tokens": {"type": "number"}, @@ -901,6 +904,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "output_cost_per_token": {"type": "number"}, "output_cost_per_token_above_32k_tokens": {"type": "number"}, "output_cost_per_token_above_100k_tokens": {"type": "number"}, + "output_cost_per_token_above_100k_tokens_batches": {"type": "number"}, "output_cost_per_token_above_128k_tokens": {"type": "number"}, "output_cost_per_token_above_200k_tokens": {"type": "number"}, "output_cost_per_token_above_256k_tokens": {"type": "number"}, diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts index 42c306cc3b3..02e2a0dd073 100644 --- a/ui/litellm-dashboard/src/lib/http/schema.d.ts +++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts @@ -32623,8 +32623,14 @@ export interface components { cache_creation_input_audio_token_cost?: number | null; /** Cache Creation Input Token Cost */ cache_creation_input_token_cost?: number | null; + /** Cache Creation Input Token Cost Above 100K Tokens */ + cache_creation_input_token_cost_above_100k_tokens?: number | null; + /** Cache Creation Input Token Cost Above 100K Tokens Batches */ + cache_creation_input_token_cost_above_100k_tokens_batches?: number | null; /** Cache Creation Input Token Cost Above 1Hr */ cache_creation_input_token_cost_above_1hr?: number | null; + /** Cache Creation Input Token Cost Above 1Hr Above 100K Tokens */ + cache_creation_input_token_cost_above_1hr_above_100k_tokens?: number | null; /** Cache Creation Input Token Cost Above 200K Tokens */ cache_creation_input_token_cost_above_200k_tokens?: number | null; /** Cache Creation Input Token Cost Above 200K Tokens Batches */ @@ -32651,6 +32657,10 @@ export interface components { cache_read_input_image_token_cost?: number | null; /** Cache Read Input Token Cost */ cache_read_input_token_cost?: number | null; + /** Cache Read Input Token Cost Above 100K Tokens */ + cache_read_input_token_cost_above_100k_tokens?: number | null; + /** Cache Read Input Token Cost Above 100K Tokens Batches */ + cache_read_input_token_cost_above_100k_tokens_batches?: number | null; /** Cache Read Input Token Cost Above 200K Tokens */ cache_read_input_token_cost_above_200k_tokens?: number | null; /** Cache Read Input Token Cost Above 200K Tokens Priority */ @@ -32727,6 +32737,10 @@ export interface components { input_cost_per_second?: number | null; /** Input Cost Per Token */ input_cost_per_token?: number | null; + /** Input Cost Per Token Above 100K Tokens */ + input_cost_per_token_above_100k_tokens?: number | null; + /** Input Cost Per Token Above 100K Tokens Batches */ + input_cost_per_token_above_100k_tokens_batches?: number | null; /** Input Cost Per Token Above 128K Tokens */ input_cost_per_token_above_128k_tokens?: number | null; /** Input Cost Per Token Above 200K Tokens */ @@ -32850,6 +32864,10 @@ export interface components { output_cost_per_second_768p?: number | null; /** Output Cost Per Token */ output_cost_per_token?: number | null; + /** Output Cost Per Token Above 100K Tokens */ + output_cost_per_token_above_100k_tokens?: number | null; + /** Output Cost Per Token Above 100K Tokens Batches */ + output_cost_per_token_above_100k_tokens_batches?: number | null; /** Output Cost Per Token Above 128K Tokens */ output_cost_per_token_above_128k_tokens?: number | null; /** Output Cost Per Token Above 200K Tokens */ @@ -46221,8 +46239,14 @@ export interface components { cache_creation_input_audio_token_cost?: number | null; /** Cache Creation Input Token Cost */ cache_creation_input_token_cost?: number | null; + /** Cache Creation Input Token Cost Above 100K Tokens */ + cache_creation_input_token_cost_above_100k_tokens?: number | null; + /** Cache Creation Input Token Cost Above 100K Tokens Batches */ + cache_creation_input_token_cost_above_100k_tokens_batches?: number | null; /** Cache Creation Input Token Cost Above 1Hr */ cache_creation_input_token_cost_above_1hr?: number | null; + /** Cache Creation Input Token Cost Above 1Hr Above 100K Tokens */ + cache_creation_input_token_cost_above_1hr_above_100k_tokens?: number | null; /** Cache Creation Input Token Cost Above 200K Tokens */ cache_creation_input_token_cost_above_200k_tokens?: number | null; /** Cache Creation Input Token Cost Above 200K Tokens Batches */ @@ -46249,6 +46273,10 @@ export interface components { cache_read_input_image_token_cost?: number | null; /** Cache Read Input Token Cost */ cache_read_input_token_cost?: number | null; + /** Cache Read Input Token Cost Above 100K Tokens */ + cache_read_input_token_cost_above_100k_tokens?: number | null; + /** Cache Read Input Token Cost Above 100K Tokens Batches */ + cache_read_input_token_cost_above_100k_tokens_batches?: number | null; /** Cache Read Input Token Cost Above 200K Tokens */ cache_read_input_token_cost_above_200k_tokens?: number | null; /** Cache Read Input Token Cost Above 200K Tokens Priority */ @@ -46325,6 +46353,10 @@ export interface components { input_cost_per_second?: number | null; /** Input Cost Per Token */ input_cost_per_token?: number | null; + /** Input Cost Per Token Above 100K Tokens */ + input_cost_per_token_above_100k_tokens?: number | null; + /** Input Cost Per Token Above 100K Tokens Batches */ + input_cost_per_token_above_100k_tokens_batches?: number | null; /** Input Cost Per Token Above 128K Tokens */ input_cost_per_token_above_128k_tokens?: number | null; /** Input Cost Per Token Above 200K Tokens */ @@ -46448,6 +46480,10 @@ export interface components { output_cost_per_second_768p?: number | null; /** Output Cost Per Token */ output_cost_per_token?: number | null; + /** Output Cost Per Token Above 100K Tokens */ + output_cost_per_token_above_100k_tokens?: number | null; + /** Output Cost Per Token Above 100K Tokens Batches */ + output_cost_per_token_above_100k_tokens_batches?: number | null; /** Output Cost Per Token Above 128K Tokens */ output_cost_per_token_above_128k_tokens?: number | null; /** Output Cost Per Token Above 200K Tokens */ From 8dc91d9d0bdd01c3d170ec6a7464339190ddf667 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 20 Oct 2026 15:49:16 -0700 Subject: [PATCH 17/66] fix(rust): add the dangerous-tool-use beta when an anthropic /v1/messages request carries safeguards (#46102) Backport of #46102 to stable/1.104.x. Cherry-picked from 5b042c0db6c4f629e5daccfe9dbdeafbc90265cd (main). Ported to the line's Rust messages layer for the anthropic provider only: a non-null safeguards field adds dangerous-tool-use-2026-09-03. Azure AI keeps its current headers since its beta-map cell is null on this line, and the other Rust providers and integration tests in the source are not on this line. --- .../src/anthropic/messages/transformation.rs | 27 +++++++++++++++++-- .../anthropic/messages_transformation.rs | 6 +++-- 2 files changed, 29 insertions(+), 4 deletions(-) diff --git a/litellm-rust/crates/llms/src/anthropic/messages/transformation.rs b/litellm-rust/crates/llms/src/anthropic/messages/transformation.rs index 07c2eb46eaa..ceb03e158bc 100644 --- a/litellm-rust/crates/llms/src/anthropic/messages/transformation.rs +++ b/litellm-rust/crates/llms/src/anthropic/messages/transformation.rs @@ -140,11 +140,14 @@ impl BaseAnthropicMessagesConfig for AnthropicMessagesConfig { } fn request_headers(&self, headers: Headers, request: &AnthropicMessagesRequest) -> Headers { - update_headers_with_anthropic_beta(headers, request) + merge_beta_headers( + update_headers_with_anthropic_beta(headers, request), + safeguards_betas(&request.params), + ) } } -fn update_headers_with_anthropic_beta( +pub(crate) fn update_headers_with_anthropic_beta( headers: Headers, request: &AnthropicMessagesRequest, ) -> Headers { @@ -199,6 +202,20 @@ fn uses_structured_output(params: &AnthropicMessagesOptionalParams) -> bool { .is_some_and(|config| config.format.is_some()) } +fn safeguards_betas(params: &AnthropicMessagesOptionalParams) -> BetaSet { + carries_safeguards(params) + .then_some(AnthropicBeta::DangerousToolUse20260903) + .into_iter() + .collect() +} + +fn carries_safeguards(params: &AnthropicMessagesOptionalParams) -> bool { + params + .extra + .get("safeguards") + .is_some_and(|value| !value.is_null()) +} + fn messages_carry_output_config(messages: &[AnthropicMessage]) -> bool { messages .iter() @@ -1047,6 +1064,12 @@ mod tests { json!({"messages": [{"role": "user", "content": "hi", "output_config": {"effort": "low"}}]}), &[("anthropic-beta", "claude-code-20250219,context-management-2025-06-27,effort-2025-11-24,interleaved-thinking-2025-05-14,per-turn-control-2026-07-01")], )] + #[case::safeguards_add_the_dangerous_tool_use_beta( + &[("anthropic-beta", "claude-code-20250219")], + json!({"safeguards": [{"type": "dangerous_tool_use"}]}), + &[("anthropic-beta", "claude-code-20250219,dangerous-tool-use-2026-09-03")], + )] + #[case::null_safeguards_add_no_beta(&[("x-api-key", "k")], json!({"safeguards": null}), &[("x-api-key", "k")])] fn request_headers_merge_the_feature_betas( #[case] input: &[(&str, &str)], #[case] fields: Value, diff --git a/litellm-rust/crates/llms/src/azure_ai/anthropic/messages_transformation.rs b/litellm-rust/crates/llms/src/azure_ai/anthropic/messages_transformation.rs index 0c1434afb5d..4080af35fdf 100644 --- a/litellm-rust/crates/llms/src/azure_ai/anthropic/messages_transformation.rs +++ b/litellm-rust/crates/llms/src/azure_ai/anthropic/messages_transformation.rs @@ -12,7 +12,9 @@ use crate::{ Error, anthropic::{ common_utils::{API_KEY_PLACEMENT, MESSAGES_PATH_SUFFIX, non_empty}, - messages::transformation::{ANTHROPIC_MESSAGES_CONFIG, AnthropicMessagesConfig}, + messages::transformation::{ + ANTHROPIC_MESSAGES_CONFIG, AnthropicMessagesConfig, update_headers_with_anthropic_beta, + }, }, base_llm::{ anthropic_messages::transformation::{ @@ -103,7 +105,7 @@ impl BaseAnthropicMessagesConfig for AzureAnthropicMessagesConfig { } fn request_headers(&self, headers: Headers, request: &AnthropicMessagesRequest) -> Headers { - self.anthropic.request_headers(headers, request) + update_headers_with_anthropic_beta(headers, request) } } From bb1e40c3e5d4847d6ba5b6de95bfbe3de7973fcf Mon Sep 17 00:00:00 2001 From: joshua-berri Date: Tue, 20 Oct 2026 15:49:40 -0700 Subject: [PATCH 18/66] fix(batches): handle empty models when logging batch cost (#47155) Backport of #47155 to stable/1.104.x. Cherry-picked from 4143e0869eff3db190a5e8f73069bfe2c9428303 (main). --- .../proxy/common_utils/check_batch_cost.py | 3 +- .../common_utils/test_check_batch_cost.py | 119 +++++++++++++++++- 2 files changed, 120 insertions(+), 2 deletions(-) diff --git a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py index 35fc3510414..c53d7178e72 100644 --- a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py +++ b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py @@ -866,8 +866,9 @@ class CheckBatchCost: failed_requests=output_file_result.failed_requests + error_file_failed_requests, ) ) + logging_model: Final = batch_result.models[0] if batch_result.models else litellm_model_name or model_id logging_obj = LiteLLMLogging( - model=batch_result.models[0], + model=logging_model, messages=[{"role": "user", "content": ""}], stream=False, call_type="aretrieve_batch", diff --git a/tests/unit/proxy/common_utils/test_check_batch_cost.py b/tests/unit/proxy/common_utils/test_check_batch_cost.py index 4e7effad3bf..bb0c9a43a61 100644 --- a/tests/unit/proxy/common_utils/test_check_batch_cost.py +++ b/tests/unit/proxy/common_utils/test_check_batch_cost.py @@ -9,7 +9,8 @@ ARN unified_object_id) batches with no managed unified id. import asyncio import json from contextlib import contextmanager -from typing import TYPE_CHECKING +from hashlib import sha256 +from typing import TYPE_CHECKING, Final from unittest.mock import AsyncMock, MagicMock, patch import pytest @@ -3226,6 +3227,122 @@ class TestMultiPodBatchCostClaim: ): yield logging_obj + @pytest.mark.asyncio + @pytest.mark.parametrize( + ("deployment_model", "successes", "failures", "expected_model"), + ( + ("openai/", 0, 2, "openai/"), + ("", 0, 2, "model-123"), + ("openai/", 2, 1, "batch-test-model"), + ("openai/batch-test-model", 2, 1, "batch-test-model"), + ("openai/batch-test-model", 2, 0, "batch-test-model"), + ), + ) + async def test_batch_accounting_preserves_models_and_mixed_results( + self, deployment_model: str, successes: int, failures: int, expected_model: str + ) -> None: + import base64 + from datetime import datetime + + import httpx + import litellm + import respx + + from litellm.integrations.custom_logger import CustomLogger + from litellm.types.router import Deployment, LiteLLM_Params, ModelInfo + from litellm.types.utils import LiteLLMBatch, SpecialEnums + + input_rate: Final = 0.000002 + output_rate: Final = 0.000006 + litellm.register_model( + { + "batch-test-model": { + "litellm_provider": "openai", + "mode": "chat", + "input_cost_per_token_batches": input_rate, + "output_cost_per_token_batches": output_rate, + } + } + ) + success: Final = { + "response": { + "status_code": 200, + "body": { + "model": "batch-test-model", + "usage": {"prompt_tokens": 100, "completion_tokens": 20, "total_tokens": 120}, + }, + }, + "error": None, + } + failure: Final = {"response": None, "error": {"code": "batch_expired", "message": "expired"}} + rows: Final = (success,) * successes + (failure,) * failures + content: Final = b"\n".join(json.dumps(row).encode() for row in rows) + + class BatchSpendRecorder(CustomLogger): + def __init__(self) -> None: + super().__init__() + self.calls: tuple[dict[str, object], ...] = () + + async def async_log_success_event( + self, kwargs: dict[str, object], response_obj: object, start_time: datetime, end_time: datetime + ) -> None: + if kwargs["call_type"] == "aretrieve_batch": + self.calls += (kwargs,) + + callback: Final = BatchSpendRecorder() + litellm.logging_callback_manager.add_litellm_async_success_callback(callback) + row: Final = _FakeManagedObjectRow() + row.unified_object_id = ( + base64.urlsafe_b64encode( + SpecialEnums.LITELLM_MANAGED_BATCH_COMPLETE_STR.value.format("model-123", "batch-456").encode() + ) + .decode() + .rstrip("=") + ) + prisma: Final = self._prisma(row, []) + router: Final = self._router() + router.get_deployment.return_value = Deployment( + model_name="batch-alias", + litellm_params=LiteLLM_Params(model=deployment_model, custom_llm_provider="openai"), + model_info=ModelInfo(id="model-123"), + ) + router.aretrieve_batch.return_value = LiteLLMBatch( + id="batch-456", + completion_window="24h", + created_at=1, + endpoint="/v1/chat/completions", + input_file_id="file-input-1", + output_file_id=_CLAIM_OUTPUT_FILE_ID, + object="batch", + status="completed", + ) + router.get_deployment_credentials_with_provider.return_value = { + "api_key": "synthetic-key", + "custom_llm_provider": "openai", + } + with respx.mock: + respx.get(f"https://api.openai.com/v1/files/{_CLAIM_OUTPUT_FILE_ID}/content").mock( + return_value=httpx.Response(200, content=content) + ) + instance: Final = self._instance(prisma, router) + await instance.check_batch_cost() + await instance.check_batch_cost() + + assert row.batch_processed is True + assert row.status == "complete" + router.aretrieve_batch.assert_awaited_once() + assert len(callback.calls) == 1 + payload: Final = callback.calls[0]["standard_logging_object"] + assert payload["model"] == expected_model + assert payload["response_cost"] == pytest.approx(successes * (100 * input_rate + 20 * output_rate)) + assert payload["prompt_tokens"] == successes * 100 + assert payload["completion_tokens"] == successes * 20 + assert payload["hidden_params"]["batch_successful_requests"] == successes + assert payload["hidden_params"]["batch_failed_requests"] == failures + assert payload["hidden_params"]["batch_models"] == ( + ["batch-test-model"] if deployment_model == "openai/batch-test-model" else ["batch-test-model"] * successes + ) + @staticmethod def _claim_calls(prisma) -> list: return [ From f7b0b09e757a6e3a96abbfba30994c0a9606d7ed Mon Sep 17 00:00:00 2001 From: joshua-berri Date: Tue, 20 Oct 2026 15:56:21 -0700 Subject: [PATCH 19/66] fix(batches): preserve spend across malformed output and metadata failures (#47184) Backport of #47184 to stable/1.104.x. Cherry-picked from 3fb95c8fe385ebe422d82d8cb10c9e52fac266fb (main). Ported by hand onto the line's poller, whose surrounding code predates several main-only batch features: the claim now writes the terminal status and NUL-stripped file_object, a failed spend-log write restores both, and the managed-files postgres_storable_json sanitizer (from #45703 on main) is added to the line since this fix needs it. --- .../proxy/common_utils/check_batch_cost.py | 58 +++--- .../proxy/hooks/managed_files.py | 27 ++- litellm/batches/batch_utils.py | 18 +- tests/unit/batches/test_batch_utils.py | 28 +++ .../proxy/test_managed_files_access_check.py | 21 +- .../common_utils/test_check_batch_cost.py | 195 +++++++++++------- 6 files changed, 230 insertions(+), 117 deletions(-) diff --git a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py index c53d7178e72..6b839e7cece 100644 --- a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py +++ b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py @@ -2,6 +2,7 @@ Polls LiteLLM_ManagedObjectTable to check if the batch job is complete, and if the cost has been tracked. """ +import json from collections.abc import Sequence from dataclasses import replace as dataclasses_replace from datetime import datetime, timedelta, timezone @@ -336,7 +337,7 @@ class CheckBatchCost: "so it will no longer be polled" ) - async def _claim_job_for_costing(self, job: "_ManagedObjectRow") -> bool: + async def _claim_job_for_costing(self, job: "_ManagedObjectRow", response: "LiteLLMBatch") -> bool: """ Atomically flip batch_processed from false to true, returning whether this pod won the row. Every pod and uvicorn worker schedules its own poller against the shared @@ -350,10 +351,16 @@ class CheckBatchCost: """ if not self._has_batch_processed_column: return True + from litellm_enterprise.proxy.hooks.managed_files import postgres_storable_json + try: claimed: Final = await _managed_object_table(self.prisma_client).update_many( where={"id": job.id, "batch_processed": False}, - data={"batch_processed": True}, + data={ + "batch_processed": True, + "status": response.status if response.status != "completed" else "complete", + "file_object": postgres_storable_json(response), + }, ) except Exception as db_err: verbose_proxy_logger.error( @@ -362,7 +369,9 @@ class CheckBatchCost: return False return claimed > 0 - async def _release_job_claim(self, job: "_ManagedObjectRow") -> None: + async def _release_job_claim( + self, job: "_ManagedObjectRow", original_status: str | None, original_file_object: object + ) -> None: """Give a claimed row back once billing it failed, so a later poll cycle retries it. Safe to match on batch_processed=True: while this poller is active the retrieve @@ -374,7 +383,11 @@ class CheckBatchCost: try: await _managed_object_table(self.prisma_client).update_many( where={"id": job.id, "batch_processed": True}, - data={"batch_processed": False}, + data={ + "batch_processed": False, + "status": original_status, + "file_object": json.dumps(original_file_object), + }, ) except Exception as db_err: verbose_proxy_logger.error( @@ -671,8 +684,6 @@ class CheckBatchCost: @staticmethod def _get_input_file_id(job: "_ManagedObjectRow") -> Optional[str]: - import json - from litellm.types.utils import LiteLLMBatch file_object = job.file_object @@ -899,7 +910,9 @@ class CheckBatchCost: custom_llm_provider=str(llm_provider) if llm_provider else None, ) - if not await self._claim_job_for_costing(job): + original_status: Final = job.status + original_file_object: Final = job.file_object + if not await self._claim_job_for_costing(job, response.model_copy(update={"usage": batch_result.usage})): verbose_proxy_logger.info( f"CheckBatchCost: batch {batch_id} (job {job.id}) was claimed by another pod " "in this window, so its cost is already being tracked there" @@ -918,7 +931,7 @@ class CheckBatchCost: batch_completion_cost=batch_result.completion_cost, ) except Exception: - await self._release_job_claim(job) + await self._release_job_claim(job, original_status, original_file_object) raise # Record batch duration (completed_at - created_at) @@ -1061,22 +1074,19 @@ class CheckBatchCost: # Track this job for the final metrics summary processed_models.append(tracked) - # mark the job as complete - try: - update_data: dict = { - "status": response.status if response.status != "completed" else "complete", - "file_object": response.model_dump_json(), - } - if self._has_batch_processed_column: - update_data["batch_processed"] = True - await _managed_object_table(self.prisma_client).update( - where={"id": job.id}, - data=update_data, - ) - except Exception as db_err: - verbose_proxy_logger.error( - f"CheckBatchCost: failed to mark job {job.id} complete in DB: {db_err}" - ) + if not self._has_batch_processed_column: + try: + await _managed_object_table(self.prisma_client).update( + where={"id": job.id}, + data={ + "status": response.status if response.status != "completed" else "complete", + "file_object": response.model_dump_json(), + }, + ) + except Exception as db_err: + verbose_proxy_logger.error( + f"CheckBatchCost: failed to mark job {job.id} complete in DB: {db_err}" + ) elif response.status in PROVIDER_TERMINAL_BATCH_STATUSES: from litellm.proxy.openai_files_endpoints.common_utils import ( diff --git a/enterprise/litellm_enterprise/proxy/hooks/managed_files.py b/enterprise/litellm_enterprise/proxy/hooks/managed_files.py index 21bf7abdc2e..ce1988a0af0 100644 --- a/enterprise/litellm_enterprise/proxy/hooks/managed_files.py +++ b/enterprise/litellm_enterprise/proxy/hooks/managed_files.py @@ -22,7 +22,7 @@ from uuid import NAMESPACE_URL, uuid5 import httpx from fastapi import HTTPException -from pydantic import ValidationError +from pydantic import BaseModel, JsonValue, TypeAdapter, ValidationError import litellm from litellm import Router, verbose_logger @@ -205,6 +205,31 @@ def _managed_object_table(prisma_client: PrismaClient) -> _ManagedObjectTableAct return prisma_client.db.litellm_managedobjecttable +_JSON_VALUE_ADAPTER: Final[TypeAdapter[JsonValue]] = TypeAdapter(JsonValue) +_POSTGRES_UNSTORABLE_CHARACTER: Final = "\x00" + + +def _storable_text(text: str) -> str: + return text.replace(_POSTGRES_UNSTORABLE_CHARACTER, "") + + +def _storable_json_value(value: JsonValue) -> JsonValue: + if isinstance(value, str): + return _storable_text(value) + if isinstance(value, list): + return [_storable_json_value(item) for item in value] + if isinstance(value, dict): + return {_storable_text(key): _storable_json_value(item) for key, item in value.items()} + return value + + +def postgres_storable_json(file_object: BaseModel) -> str: + dumped: Final = file_object.model_dump_json() + if "\\u0000" not in dumped: + return dumped + return _JSON_VALUE_ADAPTER.dump_json(_storable_json_value(_JSON_VALUE_ADAPTER.validate_json(dumped))).decode() + + def _storage_metadata_of(file_object: OpenAIFileObject | None) -> Mapping[str, str]: hidden_params: Final = cast( # cast-ok: _hidden_params is an untyped attribute the upload path sets "Mapping[str, object]", getattr(file_object, "_hidden_params", None) or {} diff --git a/litellm/batches/batch_utils.py b/litellm/batches/batch_utils.py index 819a279a43c..6e16f5e81f2 100644 --- a/litellm/batches/batch_utils.py +++ b/litellm/batches/batch_utils.py @@ -3,7 +3,7 @@ from collections.abc import Iterable, Iterator, Mapping from dataclasses import dataclass from dataclasses import replace as dataclasses_replace from enum import Enum -from typing import Any, Final, Literal +from typing import Any, Final, Literal, cast import litellm from litellm._logging import verbose_logger @@ -744,9 +744,17 @@ def _batch_response_was_successful( message batch results lines report ``result.type == "succeeded"``; Bedrock batch output lines report ``modelOutput`` (and no ``error``). """ - if custom_llm_provider == "anthropic": - return _get_anthropic_result_from_batch_results_line(batch_job_output_file).get("type") == "succeeded" if custom_llm_provider == "bedrock": return batch_job_output_file.get("modelOutput") is not None and batch_job_output_file.get("error") is None - _response: Final[dict] = batch_job_output_file.get("response", None) or {} - return _response.get("status_code", None) == 200 + envelope_key: Final = "result" if custom_llm_provider == "anthropic" else "response" + envelope: Final = batch_job_output_file.get(envelope_key) + if not isinstance(envelope, Mapping): + if envelope is not None: + verbose_logger.warning("batch output %s must be an object, treating the line as unsuccessful", envelope_key) + return False + response: Final = cast(Mapping[object, object], envelope) # cast-ok: mapping shape validated above + return ( + response.get("type") == "succeeded" + if custom_llm_provider == "anthropic" + else response.get("status_code") == 200 + ) diff --git a/tests/unit/batches/test_batch_utils.py b/tests/unit/batches/test_batch_utils.py index dd95addac40..5b43392b3ed 100644 --- a/tests/unit/batches/test_batch_utils.py +++ b/tests/unit/batches/test_batch_utils.py @@ -17,6 +17,7 @@ deterministic stand-ins so the arithmetic under test is the only variable. import json import logging from types import MappingProxyType +from typing import Final, Literal import httpx import pytest @@ -2417,3 +2418,30 @@ async def test_flag_sends_every_vertex_row_down_the_native_path_when_a_model_is_ assert calls == [] assert (result.successful_requests, result.failed_requests) == (0, 1) + + +@pytest.mark.parametrize("provider", ("openai", "anthropic")) +@pytest.mark.parametrize("envelope", (1, "invalid", [1], None, {})) +@pytest.mark.parametrize("include_valid", (True, False)) +def test_invalid_batch_envelopes_preserve_recoverable_cost( + provider: Literal["openai", "anthropic"], envelope: object, include_valid: bool +) -> None: + invalid: Final[dict[str, object]] = {"response" if provider == "openai" else "result": envelope} + valid: Final[dict[str, object]] = ( + _success_row(model="batch-accounting-control", usage=_usage(100, 20)) + if provider == "openai" + else { + "result": { + "type": "succeeded", + "message": {"model": "batch-accounting-control", "usage": {"input_tokens": 100, "output_tokens": 20}}, + } + } + ) + entries: Final = (valid, invalid, valid) if include_valid else (invalid,) + result: Final = bu._aggregate_batch_cost_usage_models( + entries, provider, model_info={"input_cost_per_token_batches": 0.001, "output_cost_per_token_batches": 0.002} + ) + assert result.cost == pytest.approx(0.28 if include_valid else 0) + assert result.usage.prompt_tokens == (200 if include_valid else 0) + assert result.usage.completion_tokens == (40 if include_valid else 0) + assert (result.successful_requests, result.failed_requests) == (2 if include_valid else 0, 1) diff --git a/tests/unit/enterprise/proxy/test_managed_files_access_check.py b/tests/unit/enterprise/proxy/test_managed_files_access_check.py index ad46798b788..62f0d0797ef 100644 --- a/tests/unit/enterprise/proxy/test_managed_files_access_check.py +++ b/tests/unit/enterprise/proxy/test_managed_files_access_check.py @@ -9,6 +9,8 @@ with deployment credentials, bypassing the managed files access-control hooks. """ import base64 +import json +from typing import Final import pytest from types import SimpleNamespace from unittest.mock import AsyncMock, MagicMock, patch @@ -367,13 +369,14 @@ async def test_check_batch_cost_should_call_afile_content_directly_with_credenti # managed_files_obj.afile_content should NOT have been called mock_managed_files_hook.afile_content.assert_not_called() - # Verify the DB update writes batch_processed, status, and file_object - mock_prisma.db.litellm_managedobjecttable.update.assert_called_once() - update_call_kwargs = ( - mock_prisma.db.litellm_managedobjecttable.update.call_args.kwargs + claim_data: Final = next( + call.kwargs["data"] + for call in mock_prisma.db.litellm_managedobjecttable.update_many.call_args_list + if call.kwargs["where"].get("id") == mock_job.id ) - assert update_call_kwargs["data"]["batch_processed"] is True - assert update_call_kwargs["data"]["status"] == "complete" - assert ( - "file_object" in update_call_kwargs["data"] - ), "file_object must be written to DB so list_batches reads updated status" + assert claim_data["batch_processed"] is True + assert claim_data["status"] == "complete" + persisted_batch: Final = json.loads(claim_data["file_object"]) + assert persisted_batch["status"] == "completed" + assert persisted_batch["usage"]["prompt_tokens"] == 10 + assert persisted_batch["usage"]["completion_tokens"] == 5 diff --git a/tests/unit/proxy/common_utils/test_check_batch_cost.py b/tests/unit/proxy/common_utils/test_check_batch_cost.py index bb0c9a43a61..8a5b3402e4d 100644 --- a/tests/unit/proxy/common_utils/test_check_batch_cost.py +++ b/tests/unit/proxy/common_utils/test_check_batch_cost.py @@ -16,6 +16,8 @@ from unittest.mock import AsyncMock, MagicMock, patch import pytest from fastapi import HTTPException +from litellm.types.utils import LiteLLMBatch + if TYPE_CHECKING: from litellm.batches.batch_utils import BatchCostUsageResult @@ -697,11 +699,15 @@ class TestCheckBatchCost: return_value=[mock_job] ) - mock_response = MagicMock() - mock_response.status = "completed" - mock_response.output_file_id = "file-output-123" - mock_response.model_dump_json.return_value = ( - '{"id":"batch-1","status":"completed"}' + mock_response: Final = LiteLLMBatch( + id="batch-1", + status="completed", + output_file_id="file-output-123", + created_at=1, + completion_window="24h", + endpoint="/v1/chat/completions", + input_file_id="file-input-1", + object="batch", ) mock_llm_router.aretrieve_batch = AsyncMock(return_value=mock_response) @@ -765,15 +771,13 @@ class TestCheckBatchCost: await check_batch_cost_instance.check_batch_cost() - assert ( - mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1 - ), "Expected update() to be called exactly once for the completed job" - update_data = mock_prisma_client.db.litellm_managedobjecttable.update.call_args[ - 1 - ]["data"] - assert ( - update_data["batch_processed"] is True - ), "update() must include batch_processed=True when column is present" + assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count >= 3, ( + "Expected update() to be called exactly once for the completed job" + ) + update_data = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args[1]["data"] + assert update_data["batch_processed"] is True, ( + "update() must include batch_processed=True when column is present" + ) assert update_data["status"] == "complete" @pytest.mark.asyncio @@ -900,7 +904,7 @@ class TestCheckBatchCost: mock_update_database.assert_awaited_once() assert mock_update_database.call_args.kwargs["response_cost"] == 0.01 - assert mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1, ( + assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count >= 3, ( "the job must still be marked processed once cost tracking succeeds" ) @@ -1375,11 +1379,15 @@ class TestCheckBatchCost: return_value=[mock_job] ) - mock_response = MagicMock() - mock_response.status = terminal_status - mock_response.output_file_id = "file-output-123" - mock_response.model_dump_json.return_value = ( - f'{{"id":"batch-1","status":"{terminal_status}"}}' + mock_response: Final = LiteLLMBatch( + id="batch-1", + status=terminal_status, + output_file_id="file-output-123", + created_at=1, + completion_window="24h", + endpoint="/v1/chat/completions", + input_file_id="file-input-1", + object="batch", ) mock_llm_router.aretrieve_batch = AsyncMock(return_value=mock_response) @@ -1447,16 +1455,12 @@ class TestCheckBatchCost: mock_afile_content.await_count == 1 ), f"{terminal_status} batch with an output file must fetch results and be billed" mock_logging_obj.async_success_handler.assert_awaited_once() - assert ( - mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1 - ) - update_data = mock_prisma_client.db.litellm_managedobjecttable.update.call_args[ - 1 - ]["data"] + assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count >= 3 + update_data = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args[1]["data"] assert update_data["batch_processed"] is True - assert ( - update_data["status"] == terminal_status - ), f"billed {terminal_status} batch must keep its real terminal status in the DB" + assert update_data["status"] == terminal_status, ( + f"billed {terminal_status} batch must keep its real terminal status in the DB" + ) @pytest.mark.asyncio async def test_error_file_failures_add_to_failed_request_count( @@ -1971,14 +1975,15 @@ class TestUnmanagedVertexRouting: router.resolve_model_name_from_model_id.return_value = "gemini-2.5-flash" router.get_model_ids.return_value = ["deploy-1"] - mock_response = MagicMock() - mock_response.status = "completed" - mock_response.output_file_id = "gs://bucket/out/predictions.jsonl" - mock_response.error_file_id = None - mock_response.completed_at = None - mock_response.created_at = None - mock_response.model_dump_json.return_value = ( - '{"id":"8823717160934178816","status":"completed"}' + mock_response: Final = LiteLLMBatch( + id="8823717160934178816", + status="completed", + output_file_id="gs://bucket/out/predictions.jsonl", + created_at=1, + completion_window="24h", + endpoint="/v1/chat/completions", + input_file_id="file-input-1", + object="batch", ) router.aretrieve_batch = AsyncMock(return_value=mock_response) router.get_deployment_credentials_with_provider = MagicMock( @@ -2051,8 +2056,8 @@ class TestUnmanagedVertexRouting: mock_logging_obj.async_success_handler.assert_awaited_once() assert mock_logging_obj.async_success_handler.call_args[1]["batch_cost"] == 0.01 - assert prisma.db.litellm_managedobjecttable.update.call_count == 1 - update_data = prisma.db.litellm_managedobjecttable.update.call_args[1]["data"] + assert prisma.db.litellm_managedobjecttable.update_many.call_count >= 3 + update_data = prisma.db.litellm_managedobjecttable.update_many.call_args[1]["data"] assert update_data["batch_processed"] is True assert update_data["status"] == "complete" @@ -2203,14 +2208,15 @@ class TestUnmanagedBedrockRouting: router.resolve_model_name_from_model_id.return_value = "claude-sonnet-4" router.get_model_ids.return_value = ["deploy-1"] - mock_response = MagicMock() - mock_response.status = "completed" - mock_response.output_file_id = "s3://bucket/out/predictions.jsonl" - mock_response.error_file_id = None - mock_response.completed_at = None - mock_response.created_at = None - mock_response.model_dump_json.return_value = ( - f'{{"id":"{self._ARN}","status":"completed"}}' + mock_response: Final = LiteLLMBatch( + id=self._ARN, + status="completed", + output_file_id="s3://bucket/out/predictions.jsonl", + created_at=1, + completion_window="24h", + endpoint="/v1/chat/completions", + input_file_id="file-input-1", + object="batch", ) router.aretrieve_batch = AsyncMock(return_value=mock_response) router.get_deployment_credentials_with_provider = MagicMock( @@ -2281,8 +2287,8 @@ class TestUnmanagedBedrockRouting: mock_logging_obj.async_success_handler.assert_awaited_once() assert mock_logging_obj.async_success_handler.call_args[1]["batch_cost"] == 0.02 - assert prisma.db.litellm_managedobjecttable.update.call_count == 1 - update_data = prisma.db.litellm_managedobjecttable.update.call_args[1]["data"] + assert prisma.db.litellm_managedobjecttable.update_many.call_count >= 3 + update_data = prisma.db.litellm_managedobjecttable.update_many.call_args[1]["data"] assert update_data["batch_processed"] is True assert update_data["status"] == "complete" @@ -3150,13 +3156,20 @@ class TestMultiPodBatchCostClaim: @staticmethod def _router(): - response = MagicMock() - response.status = "completed" - response.output_file_id = _CLAIM_OUTPUT_FILE_ID - response.error_file_id = None - response.created_at = 1 - response.completed_at = 2 - response.model_dump_json.return_value = '{"id":"batch-456","status":"completed"}' + from litellm.types.utils import LiteLLMBatch + + response: Final = LiteLLMBatch( + id="batch-456", + status="completed", + output_file_id=_CLAIM_OUTPUT_FILE_ID, + error_file_id=None, + created_at=1, + completed_at=2, + completion_window="24h", + endpoint="/v1/chat/completions", + input_file_id="file-input-1", + object="batch", + ) deployment = MagicMock() deployment.litellm_params.custom_llm_provider = "openai" @@ -3238,8 +3251,9 @@ class TestMultiPodBatchCostClaim: ("openai/batch-test-model", 2, 0, "batch-test-model"), ), ) + @pytest.mark.parametrize("failure_envelope", (None, 1, "invalid", [1])) async def test_batch_accounting_preserves_models_and_mixed_results( - self, deployment_model: str, successes: int, failures: int, expected_model: str + self, deployment_model: str, successes: int, failures: int, expected_model: str, failure_envelope: object ) -> None: import base64 from datetime import datetime @@ -3274,7 +3288,7 @@ class TestMultiPodBatchCostClaim: }, "error": None, } - failure: Final = {"response": None, "error": {"code": "batch_expired", "message": "expired"}} + failure: Final = {"response": failure_envelope, "error": {"code": "batch_expired", "message": "expired"}} rows: Final = (success,) * successes + (failure,) * failures content: Final = b"\n".join(json.dumps(row).encode() for row in rows) @@ -3366,6 +3380,30 @@ class TestMultiPodBatchCostClaim: with patch("litellm.proxy.proxy_server.scheduler", scheduler): await guard._check_file_deletion_allowed(file_id) + @pytest.mark.asyncio + @pytest.mark.parametrize("status", ("completed", "failed", "expired", "cancelled")) + @pytest.mark.parametrize("metadata_text", ("before\x00after", r"\u0000")) + async def test_cost_claim_persists_terminal_metadata_without_a_later_write( + self, status: str, metadata_text: str + ) -> None: + row: Final = _FakeManagedObjectRow() + journal: Final = [] + prisma: Final = self._prisma(row, journal) + router: Final = self._router() + router.aretrieve_batch.return_value = router.aretrieve_batch.return_value.model_copy( + update={"status": status, "metadata": {"annotation": metadata_text}} + ) + prisma.db.litellm_managedobjecttable.update.side_effect = RuntimeError("final write unavailable") + worker: Final = self._instance(prisma, router) + with self._billing_patches(journal) as logging_obj: + await worker.check_batch_cost() + await worker.check_batch_cost() + assert row.batch_processed is True + assert row.status == ("complete" if status == "completed" else status) + assert json.loads(row.file_object)["status"] == status + assert json.loads(row.file_object)["metadata"] == {"annotation": metadata_text.replace("\x00", "")} + assert logging_obj.async_success_handler.await_count == 1 + @pytest.mark.asyncio async def test_winning_pod_claims_the_row_between_fetching_and_billing(self): """The claim flips batch_processed false -> true after the results are in hand and @@ -3377,13 +3415,9 @@ class TestMultiPodBatchCostClaim: with self._billing_patches(journal) as logging_obj: await self._instance(prisma, self._router()).check_batch_cost() - assert journal == ["fetch", "claim", "bill", "finalize"] - assert self._claim_calls(prisma) == [ - { - "where": {"id": "job-claim-1", "batch_processed": False}, - "data": {"batch_processed": True}, - } - ] + assert journal == ["fetch", "claim", "bill"] + assert row.status == "complete" + assert json.loads(row.file_object)["usage"] == {"prompt_tokens": 10, "completion_tokens": 5} logging_obj.async_success_handler.assert_awaited_once() assert row.batch_processed is True @@ -3403,18 +3437,17 @@ class TestMultiPodBatchCostClaim: assert journal == ["fetch"] logging_obj.async_success_handler.assert_not_awaited() - assert self._claim_calls(prisma) == [ - { - "where": {"id": "job-claim-1", "batch_processed": False}, - "data": {"batch_processed": True}, - } - ] + assert row.status == "in_progress" + assert json.loads(row.file_object)["status"] == "in_progress" @pytest.mark.asyncio - async def test_a_failed_spend_log_write_releases_the_claim(self): + @pytest.mark.parametrize("stored_as_json_string", (True, False)) + async def test_a_failed_spend_log_write_releases_the_claim(self, stored_as_json_string: bool) -> None: """A transient failure while billing a claimed batch must hand the row back, or its spend is silently lost instead of being retried on the next cycle.""" row = _FakeManagedObjectRow() + original_file_object: Final = row.file_object if stored_as_json_string else json.loads(row.file_object) + row.file_object = original_file_object journal = [] prisma = self._prisma(row, journal) @@ -3423,10 +3456,16 @@ class TestMultiPodBatchCostClaim: assert journal == ["fetch", "claim", "bill", "release"] assert row.batch_processed is False - assert self._claim_calls(prisma)[-1] == { - "where": {"id": "job-claim-1", "batch_processed": True}, - "data": {"batch_processed": False}, - } + assert row.status == "in_progress" + assert json.loads(row.file_object) == original_file_object + + with self._billing_patches(journal) as logging_obj: + await self._instance(prisma, self._router()).check_batch_cost() + await self._instance(prisma, self._router()).check_batch_cost() + + assert row.batch_processed is True + assert row.status == "complete" + logging_obj.async_success_handler.assert_awaited_once() @pytest.mark.asyncio async def test_a_worker_interrupted_mid_costing_leaves_the_batch_billable(self): @@ -3460,7 +3499,7 @@ class TestMultiPodBatchCostClaim: with self._billing_patches(survivor_journal) as survivor_logging: await self._instance(survivor_prisma, self._router()).check_batch_cost() - assert survivor_journal == ["fetch", "claim", "bill", "finalize"] + assert survivor_journal == ["fetch", "claim", "bill"] survivor_logging.async_success_handler.assert_awaited_once() assert row.batch_processed is True @@ -3493,7 +3532,7 @@ class TestMultiPodBatchCostClaim: finish_fetch.set() await asyncio.wait_for(costing, timeout=5) - assert journal == ["fetch", "claim", "bill", "finalize"] + assert journal == ["fetch", "claim", "bill"] assert row.batch_processed is True await self._run_deletion_guard(prisma, _CLAIM_OUTPUT_FILE_ID) From 3786195eb472506964272df86a0447c1eb342843 Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 20 Oct 2026 15:56:48 -0700 Subject: [PATCH 20/66] chore(cost-map): add openai gpt-6.1-sol from the pricing page (#43738) Backport of #43738 to stable/1.104.x. Cherry-picked from a3552c451bf2b21aab31e7dd11b2f1757b970d46 (main). Prerequisite for #43935: adds the gpt-6.1-sol cost-map row that fix gates on. Appended to the line's cost map. --- ...odel_prices_and_context_window_backup.json | 76 +++++++++++++++++++ model_prices_and_context_window.json | 76 +++++++++++++++++++ 2 files changed, 152 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index d9d544a4fa7..e4c2fb4112d 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -78261,5 +78261,81 @@ "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 512, "supports_sampling_params": false + }, + "gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_batches": 2e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 2e-05, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index d9d544a4fa7..e4c2fb4112d 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -78261,5 +78261,81 @@ "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 512, "supports_sampling_params": false + }, + "gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_batches": 2e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 2e-05, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true } } From 93faf0a1d5b1e3f74796ff2571d903ca5f5f8a51 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 20 Oct 2026 15:59:00 -0700 Subject: [PATCH 21/66] chore(cost-map): add azure and openrouter gpt-6.1-sol rows (#43744) Backport of #43744 to stable/1.104.x. Cherry-picked from bda2763f2c722d617171e71deb331d3de7d345e7 (main). Prerequisite for #43935: adds the azure and openrouter gpt-6.1-sol cost-map rows that fix gates on. Appended to the line's cost map. --- ...odel_prices_and_context_window_backup.json | 245 ++++++++++++++++++ model_prices_and_context_window.json | 245 ++++++++++++++++++ 2 files changed, 490 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index e4c2fb4112d..4ced9194464 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -78337,5 +78337,250 @@ "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true + }, + "azure_ai/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6.1-sol-2026-09-29": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "openrouter/openai/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6.1-sol-pro": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6.1-sol-pro:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6.1-sol:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e4c2fb4112d..4ced9194464 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -78337,5 +78337,250 @@ "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true + }, + "azure_ai/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6.1-sol-2026-09-29": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "openrouter/openai/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6.1-sol-pro": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6.1-sol-pro:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "openrouter/openai/gpt-6.1-sol:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, + "cache_read_input_token_cost": 5e-08, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true } } From 54f9259b403b2b334ad50a212a2dbb1e21a759b8 Mon Sep 17 00:00:00 2001 From: Paul El Khoury <82139421+pOpO1-9@users.noreply.github.com> Date: Tue, 20 Oct 2026 16:01:18 -0700 Subject: [PATCH 22/66] fix(openai): drop unsupported reasoning effort for gpt-6.1-sol (#43935) Backport of #43935 to stable/1.104.x. Cherry-picked from d7620c77a1ebaf30bb55f31030418b9da2f8cd21 (main). Adapted to the line: the bridge check lives in litellm/main.py rather than litellm/responses/bridge_check.py, the effort helpers keep the line's private names, and the azure gpt-6.1-sol rows get supports_none_reasoning_effort=false (from #46377 on main) since this fix and its tests key on it. Test files keep the line's content plus this PR's own hunks. --- .../llms/azure/chat/gpt_5_transformation.py | 60 ++------ .../llms/azure/responses/transformation.py | 8 + .../llms/azure_ai/responses/transformation.py | 13 ++ .../llms/openai/chat/gpt_5_transformation.py | 102 +++++++----- .../llms/openai/responses/transformation.py | 39 ++++- litellm/main.py | 23 ++- ...odel_prices_and_context_window_backup.json | 77 +++++++--- .../reasoning_effort_capability.py | 25 ++- model_prices_and_context_window.json | 77 +++++++--- ..._handler_reasoning_effort_normalization.py | 30 +++- .../chat/test_azure_gpt5_transformation.py | 145 ++++++++++++++++-- .../response/test_azure_transformation.py | 125 ++++++++++++++- .../chat/test_azure_ai_transformation.py | 17 +- .../test_azure_ai_responses_transformation.py | 74 +++++++++ .../test_openai_responses_transformation.py | 109 +++++++++++++ .../llms/openai/test_gpt5_transformation.py | 101 ++++++++++++ .../test_reasoning_effort_capability.py | 15 +- tests/unit/test_main.py | 49 +++++- 18 files changed, 910 insertions(+), 179 deletions(-) diff --git a/litellm/llms/azure/chat/gpt_5_transformation.py b/litellm/llms/azure/chat/gpt_5_transformation.py index 3189f5b57ac..a9b6c27a0df 100644 --- a/litellm/llms/azure/chat/gpt_5_transformation.py +++ b/litellm/llms/azure/chat/gpt_5_transformation.py @@ -1,12 +1,10 @@ """Support for Azure OpenAI gpt-5 model family.""" -from typing import Final +from typing import ClassVar, Final import litellm -from litellm.exceptions import UnsupportedParamsError from litellm.llms.openai.chat.gpt_5_transformation import ( OpenAIGPT5Config, - _get_effort_level, is_gpt_reasoning_series_name, ) from litellm.types.llms.openai import AllMessageValues @@ -15,9 +13,16 @@ from .gpt_transformation import AzureOpenAIConfig class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config): - """Azure specific handling for gpt-5 models.""" + """Azure specific handling for gpt-5 models. + + reasoning_effort none joins xhigh as opt-in here: Azure rejected it on every gpt-5 + deployment before gpt-5.1 (https://github.com/BerriAI/litellm/issues/16704), and a deployment + name the map never heard of must not forward it. See + https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning + """ GPT5_SERIES_ROUTE = "gpt5_series/" + OPT_IN_REASONING_EFFORTS: ClassVar[frozenset[str]] = frozenset(("xhigh", "none")) @classmethod def _model_map_lookup_name(cls, model: str) -> str: @@ -27,11 +32,18 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config): model_prices_and_context_window.json; ``azure/gpt-5.1`` is. Overriding the shared resolver rather than one lookup means the supports, explicitly-disabled and default-effort answers all read the same entry. + + An ``azure_ai/`` name reaches this config when ``get_llm_provider`` re-routes a Foundry + deployment on an OpenAI-v1 host to the azure provider with the prefix intact. It is the + same product the azure_ai config reads ``azure_ai/`` for, so that row answers when + the map carries it, and the azure/ twin when it does not. """ if model.startswith(cls.GPT5_SERIES_ROUTE): return "azure/" + model[len(cls.GPT5_SERIES_ROUTE) :] if model.startswith("azure/"): return model + if model.startswith("azure_ai/"): + return model if model in litellm.model_cost else "azure/" + model.removeprefix("azure_ai/") return "azure/" + model @classmethod @@ -75,34 +87,7 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config): drop_params: bool, api_version: str = "", ) -> dict: - reasoning_effort_value = non_default_params.get("reasoning_effort") or optional_params.get("reasoning_effort") - effective_effort: Final = _get_effort_level(reasoning_effort_value) - - # gpt-5.1/5.2/5.4 support reasoning_effort='none', but other gpt-5 models don't - # See: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning - supports_none: Final = self._supports_reasoning_effort_level(model, "none") - - if effective_effort == "none" and not supports_none: - if litellm.drop_params is True or (drop_params is not None and drop_params is True): - non_default_params = non_default_params.copy() - optional_params = optional_params.copy() - if _get_effort_level(non_default_params.get("reasoning_effort")) == "none": - non_default_params.pop("reasoning_effort") - if _get_effort_level(optional_params.get("reasoning_effort")) == "none": - optional_params.pop("reasoning_effort") - else: - raise UnsupportedParamsError( - status_code=400, - message=( - "Azure OpenAI does not support reasoning_effort='none' for this model. " - "Supported values are: 'low', 'medium', and 'high'. " - "To drop this parameter, set `litellm.drop_params=True` or for proxy:\n\n" - "`litellm_settings:\n drop_params: true`\n" - "Issue: https://github.com/BerriAI/litellm/issues/16704" - ), - ) - - result: Final = OpenAIGPT5Config.map_openai_params( + return OpenAIGPT5Config.map_openai_params( self, non_default_params=non_default_params, optional_params=optional_params, @@ -110,17 +95,6 @@ class AzureOpenAIGPT5Config(AzureOpenAIConfig, OpenAIGPT5Config): drop_params=drop_params, ) - # Only drop reasoning_effort='none' for models that don't support it - result_effort: Final = _get_effort_level(result.get("reasoning_effort")) - if result_effort == "none" and not supports_none: - result.pop("reasoning_effort") - - # Azure gpt-5.4+ with tools + reasoning_effort is now routed to the - # Responses API bridge (same as OpenAI), so we no longer need to drop - # reasoning_effort here. See: responses_api_bridge_check() in main.py. - - return result - def transform_request( self, model: str, diff --git a/litellm/llms/azure/responses/transformation.py b/litellm/llms/azure/responses/transformation.py index 2a82b42df7b..7ff983aa333 100644 --- a/litellm/llms/azure/responses/transformation.py +++ b/litellm/llms/azure/responses/transformation.py @@ -30,10 +30,18 @@ class AzureOpenAIResponsesAPIConfig(OpenAIResponsesAPIConfig): def custom_llm_provider(self) -> LlmProviders: return LlmProviders.AZURE + @staticmethod + def _is_gpt_5_model(model: str) -> bool: + return AzureOpenAIGPT5Config.is_model_gpt_5_model(model) + @staticmethod def _supports_reasoning_effort_none(model: str) -> bool: return AzureOpenAIGPT5Config._supports_reasoning_effort_level(model, "none") + @staticmethod + def _effort_level_is_disabled(model: str, level: str) -> bool: + return AzureOpenAIGPT5Config.row_disables_reasoning_effort_level(model, level) + @staticmethod def _effort_resolves_to_none(model: str, effort: str | None) -> bool: return AzureOpenAIGPT5Config.effort_resolves_to_none(model, effort) diff --git a/litellm/llms/azure_ai/responses/transformation.py b/litellm/llms/azure_ai/responses/transformation.py index 66a284c821d..07d0f777473 100644 --- a/litellm/llms/azure_ai/responses/transformation.py +++ b/litellm/llms/azure_ai/responses/transformation.py @@ -3,6 +3,7 @@ from typing import Final import httpx from litellm.llms.azure.responses.transformation import AzureOpenAIResponsesAPIConfig +from litellm.llms.azure_ai.chat.transformation import AzureAIGPT5Config from litellm.llms.azure_ai.common_utils import ( AzureFoundryModelInfo, api_key_header_for_base, @@ -27,6 +28,18 @@ class AzureAIResponsesAPIConfig(AzureOpenAIResponsesAPIConfig): def custom_llm_provider(self) -> LlmProviders: return LlmProviders.AZURE_AI + @staticmethod + def _supports_reasoning_effort_none(model: str) -> bool: + return AzureAIGPT5Config._supports_reasoning_effort_level(model, "none") + + @staticmethod + def _effort_level_is_disabled(model: str, level: str) -> bool: + return AzureAIGPT5Config.row_disables_reasoning_effort_level(model, level) + + @staticmethod + def _effort_resolves_to_none(model: str, effort: str | None) -> bool: + return AzureAIGPT5Config.effort_resolves_to_none(model, effort) + def validate_environment(self, headers: dict, model: str, litellm_params: GenericLiteLLMParams | None) -> dict: params: Final = litellm_params or GenericLiteLLMParams() auth_headers: Final = get_azure_ai_auth_headers( diff --git a/litellm/llms/openai/chat/gpt_5_transformation.py b/litellm/llms/openai/chat/gpt_5_transformation.py index d0e5ff01e71..05e40ec70bb 100644 --- a/litellm/llms/openai/chat/gpt_5_transformation.py +++ b/litellm/llms/openai/chat/gpt_5_transformation.py @@ -1,7 +1,7 @@ """Support for OpenAI gpt-5 model family.""" import re -from typing import Final +from typing import ClassVar, Final import litellm from litellm.utils import ( @@ -67,6 +67,10 @@ def _get_effort_level(value: str | dict | None) -> str | None: GPT_REASONING_SERIES_MARKERS: Final = ("gpt-5", "gpt-6") +def unsupported_reasoning_effort_message(param: str, level: str, model: str) -> str: + return f"{param}={level} is not supported for {model}. To drop unsupported params set `litellm.drop_params = True`" + + def is_gpt_reasoning_series_name(model: str) -> bool: normalized: Final = model.split("/")[-1] return any(marker in model for marker in GPT_REASONING_SERIES_MARKERS) and not normalized.startswith("gpt-5-chat") @@ -82,6 +86,9 @@ class OpenAIGPT5Config(OpenAIGPTConfig): - Support for GPT-5-Codex models optimized for code generation. """ + OPT_IN_REASONING_EFFORTS: ClassVar[frozenset[str]] = frozenset(("xhigh",)) + ROUTE_SPECIFIC_REASONING_EFFORTS: ClassVar[frozenset[str]] = frozenset(("max",)) + @classmethod def is_model_gpt_5_model(cls, model: str) -> bool: return is_gpt_reasoning_series_name(model) @@ -193,15 +200,10 @@ class OpenAIGPT5Config(OpenAIGPTConfig): return False @classmethod - def _is_reasoning_effort_level_explicitly_disabled(cls, model: str, level: str) -> bool: + def is_reasoning_effort_level_explicitly_disabled(cls, model: str, level: str) -> bool: """Return True only when the model map explicitly sets the capability to False. - Unlike ``_supports_reasoning_effort_level`` (which requires an explicit True), - this method returns True only when ``supports_{level}_reasoning_effort`` is - explicitly set to ``False`` in the model map. A missing key is treated as - supported (i.e. this method returns False = not disabled). - - Use this for opt-out checks where unknown models should be allowed through. + A missing key is not a disable. Unknown models pass through. """ return is_explicitly_disabled_factory( model=cls._model_map_lookup_name(model), @@ -209,6 +211,39 @@ class OpenAIGPT5Config(OpenAIGPTConfig): key=f"supports_{level}_reasoning_effort", ) + @classmethod + def _is_reasoning_effort_level_explicitly_disabled(cls, model: str, level: str) -> bool: + return cls.is_reasoning_effort_level_explicitly_disabled(model, level) + + @classmethod + def refuses_reasoning_effort_level(cls, model: str, level: str) -> bool: + """The chat gate for any requested effort level, read off the model's map row alone. + + An opt-in level (xhigh here; Azure adds none) is refused unless the row says true, since + the providers rejected it on most of the family when it arrived. Every other level is + refused only when the row says false: a model the map never heard of, or a row without the + flag, keeps forwarding what it was sent, and a level with no flag at all (medium, high) is + never refused. So a new model in the family needs its map row and no code change, the + row's supports__reasoning_effort flags being the whole contract. + + A route-specific level (max) is never refused by either gate: the same model honors it + on Responses and refuses it on Chat Completions, so one row flag cannot gate it on + either route. Chat forwards it for the Responses bridge and a plain chat call gets the + provider's own 400, exactly as before the gate read every level. + """ + if level in cls.ROUTE_SPECIFIC_REASONING_EFFORTS: + return False + if level in cls.OPT_IN_REASONING_EFFORTS: + return not cls._supports_reasoning_effort_level(model, level) + return cls.is_reasoning_effort_level_explicitly_disabled(model, level) + + @classmethod + def row_disables_reasoning_effort_level(cls, model: str, level: str) -> bool: + """The Responses gate: opt-out for every level except the route-specific ones.""" + if level in cls.ROUTE_SPECIFIC_REASONING_EFFORTS: + return False + return cls.is_reasoning_effort_level_explicitly_disabled(model, level) + def get_supported_openai_params(self, model: str) -> list: if self.is_model_gpt_5_search_model(model): return [ @@ -269,12 +304,12 @@ class OpenAIGPT5Config(OpenAIGPTConfig): drop_params=drop_params, ) - # Get raw reasoning_effort and effective effort level for all guards. - # Use effective_effort (extracted string) for xhigh validation, "none" checks, and - # tool/sampling guards — dict inputs like {"effort": "none", "summary": "detailed"} - # must be treated as effort="none" to avoid incorrect tool-drop or sampling errors. - raw_reasoning_effort = non_default_params.get("reasoning_effort") or optional_params.get("reasoning_effort") - effective_effort: Final = _get_effort_level(raw_reasoning_effort) + # Dict inputs like {"effort": "none", "summary": "detailed"} are judged by their effort + # string so the gate, the sampling guard, and the temperature guard all see one level. + raw_reasoning_effort: Final = non_default_params.get("reasoning_effort") or optional_params.get( + "reasoning_effort" + ) + requested_effort: Final = _get_effort_level(raw_reasoning_effort) # Normalize dict reasoning_effort to string for Chat Completions API. # Example: {"effort": "high", "summary": "detailed"} -> "high" @@ -286,31 +321,20 @@ class OpenAIGPT5Config(OpenAIGPTConfig): if "reasoning_effort" in optional_params: optional_params["reasoning_effort"] = normalized - if effective_effort == "xhigh": - # xhigh is an opt-in capability: only allow if model explicitly supports it. - if not self._supports_reasoning_effort_level(model, effective_effort): - if litellm.drop_params or drop_params: - non_default_params.pop("reasoning_effort", None) - optional_params.pop("reasoning_effort", None) - else: - raise litellm.utils.UnsupportedParamsError( - message=(f"reasoning_effort={effective_effort} is not supported for this model."), - status_code=400, - ) - elif effective_effort in ("minimal", "low"): - # minimal/low are opt-out: unknown models pass through; only block when - # the model map explicitly sets supports_{level}_reasoning_effort=false. - # Example: gpt-5.5-pro only accepts {medium, high, xhigh}, so it sets - # supports_low_reasoning_effort=false (and supports_minimal=false). - if self._is_reasoning_effort_level_explicitly_disabled(model, effective_effort): - if litellm.drop_params or drop_params: - non_default_params.pop("reasoning_effort", None) - optional_params.pop("reasoning_effort", None) - else: - raise litellm.utils.UnsupportedParamsError( - message=(f"reasoning_effort={effective_effort} is not supported for this model."), - status_code=400, - ) + if requested_effort is not None and self.refuses_reasoning_effort_level(model, requested_effort): + if litellm.drop_params or drop_params: + non_default_params.pop("reasoning_effort", None) + optional_params.pop("reasoning_effort", None) + else: + raise litellm.utils.UnsupportedParamsError( + message=unsupported_reasoning_effort_message("reasoning_effort", requested_effort, model), + status_code=400, + ) + + # The level the provider will see: None once dropped, so the guards below judge by the model's default effort + effective_effort: Final = _get_effort_level( + non_default_params.get("reasoning_effort") or optional_params.get("reasoning_effort") + ) ################################################################ # max_tokens is not supported for gpt-5 models on OpenAI API diff --git a/litellm/llms/openai/responses/transformation.py b/litellm/llms/openai/responses/transformation.py index 6c1d8698652..4ab02370d77 100644 --- a/litellm/llms/openai/responses/transformation.py +++ b/litellm/llms/openai/responses/transformation.py @@ -22,7 +22,10 @@ from litellm.litellm_core_utils.prompt_templates.common_utils import ( from litellm.litellm_core_utils.safe_json_loads import safe_json_loads from litellm.litellm_core_utils.url_utils import encode_url_path_segment from litellm.llms.base_llm.responses.transformation import BaseResponsesAPIConfig -from litellm.llms.openai.chat.gpt_5_transformation import is_gpt_reasoning_series_name +from litellm.llms.openai.chat.gpt_5_transformation import ( + is_gpt_reasoning_series_name, + unsupported_reasoning_effort_message, +) from litellm.responses.litellm_completion_transformation.custom_tools import TOOL_CALL_ITEM_ID_PREFIX_BY_TYPE from litellm.secret_managers.main import get_secret_str from litellm.types.llms.openai import * @@ -136,6 +139,20 @@ class OpenAIResponsesAPIConfig(BaseResponsesAPIConfig): return supports_none_reasoning_effort(model=model, custom_llm_provider=None) + @staticmethod + def _effort_level_is_disabled(model: str, level: str) -> bool: + """Whether the model's cost-map row turns this effort level off. + + The same row the chat gate reads, so a level the row refuses is refused on both wires + and a new model needs its row, not code. This surface stays opt-out for every level, + xhigh included, since it never refused a level the row omits; max is the exception, a + level the row cannot gate because the same model takes it here and refuses it on chat. + Azure overrides this so a bare deployment name reads the azure/ entry. + """ + from litellm.llms.openai.chat.gpt_5_transformation import OpenAIGPT5Config + + return OpenAIGPT5Config.row_disables_reasoning_effort_level(model, level) + @staticmethod def _effort_resolves_to_none(model: str, effort: str | None) -> bool: """Whether this request's reasoning effort ends up as "none", the one condition @@ -242,7 +259,25 @@ class OpenAIResponsesAPIConfig(BaseResponsesAPIConfig): lookup_name: Final = self._model_map_lookup_name(model) if self._is_gpt_5_model(model=lookup_name): reasoning: Final = params.get("reasoning") or {} - effort: Final = reasoning.get("effort") if isinstance(reasoning, dict) else None + requested_effort: Final = reasoning.get("effort") if isinstance(reasoning, dict) else None + if ( + isinstance(reasoning, dict) + and isinstance(requested_effort, str) + and self._effort_level_is_disabled(lookup_name, requested_effort) + ): + if not (drop_params or litellm.drop_params): + raise litellm.UnsupportedParamsError( + message=unsupported_reasoning_effort_message("reasoning.effort", requested_effort, model), + status_code=400, + ) + remaining: Final = reasoning.copy() + remaining.pop("effort", None) + if remaining: + params["reasoning"] = remaining + else: + params.pop("reasoning", None) + forwarded_reasoning: Final = params.get("reasoning") + effort: Final = forwarded_reasoning.get("effort") if isinstance(forwarded_reasoning, dict) else None supports_none: Final = self._supports_reasoning_effort_none(model=lookup_name) effort_is_none: Final = supports_none and self._effort_resolves_to_none(lookup_name, effort) diff --git a/litellm/main.py b/litellm/main.py index 12854db15d0..c3cf278633b 100644 --- a/litellm/main.py +++ b/litellm/main.py @@ -1057,6 +1057,18 @@ def _resolve_openai_api_base(api_base: str | None) -> str: ) +def _chat_gate_refuses_reasoning_effort_none(model: str, custom_llm_provider: str) -> bool: + from litellm.llms.azure_ai.chat.transformation import AzureAIGPT5Config + + match custom_llm_provider: + case "azure": + return litellm.AzureOpenAIGPT5Config.refuses_reasoning_effort_level(model, "none") + case "azure_ai": + return AzureAIGPT5Config.refuses_reasoning_effort_level(model, "none") + case _: + return OpenAIGPT5Config.refuses_reasoning_effort_level(model, "none") + + def responses_api_bridge_check( model: str, custom_llm_provider: str, @@ -1129,10 +1141,13 @@ def responses_api_bridge_check( ) for tool in (tools or ()) ) - if isinstance(reasoning_effort, dict): - reasoning_active = reasoning_effort.get("effort") != "none" or reasoning_effort.get("summary") is not None - else: - reasoning_active = reasoning_effort != "none" + requested_effort: Final = reasoning_effort.get("effort") if isinstance(reasoning_effort, dict) else reasoning_effort + requested_summary: Final = reasoning_effort.get("summary") if isinstance(reasoning_effort, dict) else None + reasoning_active: Final = ( + requested_effort != "none" + or requested_summary is not None + or _chat_gate_refuses_reasoning_effort_none(model, custom_llm_provider) + ) # The reasoning+tools constraint is enforced by the real OpenAI backend behind any api.openai.com # host (the default URL or a PrivateLink hostname such as .privatelink.api.openai.com) and # by Azure OpenAI through the azure provider. Resolve the effective OpenAI base arg>global>env>default diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 4ced9194464..617aabeeecf 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -3805,7 +3805,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, @@ -8251,7 +8251,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8300,7 +8300,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8841,7 +8841,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -30766,9 +30766,9 @@ "supports_response_schema": true, "supports_vision": true, "supports_reasoning": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.3-codex-spark": { "litellm_provider": "chatgpt", @@ -35018,11 +35018,13 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "deprecation_date": "2027-04-01" }, "gpt-5.3-chat-latest": { "cache_read_input_token_cost": 1.75e-07, @@ -69878,18 +69880,47 @@ }, "azure/eu/gpt-6-astra": { "deprecation_date": "2028-01-11", - "cache_creation_input_token_cost": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, - "cache_read_input_token_cost": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, - "input_cost_per_token": 1.1e-05, - "input_cost_per_token_above_272k_tokens": 2.2e-05, + "cache_creation_input_token_cost": 1.5e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3e-05, + "cache_read_input_token_cost": 1.2e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-06, + "input_cost_per_token": 1.2e-05, + "input_cost_per_token_above_272k_tokens": 2.4e-05, "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5.5e-05, - "output_cost_per_token_above_272k_tokens": 8.25e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_reasoning": true + "output_cost_per_token": 6e-05, + "output_cost_per_token_above_272k_tokens": 9e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, "azure/eu/gpt-6-luna": { "deprecation_date": "2028-03-11", @@ -78374,7 +78405,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, @@ -78423,7 +78454,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -78471,7 +78502,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, diff --git a/litellm/router_utils/reasoning_effort_capability.py b/litellm/router_utils/reasoning_effort_capability.py index 1d7656f253e..c24536cd6fa 100644 --- a/litellm/router_utils/reasoning_effort_capability.py +++ b/litellm/router_utils/reasoning_effort_capability.py @@ -1,20 +1,17 @@ """Resolve which reasoning_effort values a deployment, and by intersection a model group, accepts. -An entry that states its levels outright in reasoning_effort_levels is read first and wins -whole, for a model whose set the per-level flags cannot express: Kimi K3 takes low, high and max, -and no flag can drop medium because medium has none. Every other entry answers through the -supports_*_reasoning_effort flags below, whose polarity mirrors how a request path reads that same -flag. medium and high are unconditional for a reasoning model. minimal and low are opt-out: -openai/chat/gpt_5_transformation.py refuses them only when the map says false. xhigh and max are -opt-in. none is opt-out everywhere except the azure gpt-5 family, whose config raises -UnsupportedParamsError without an explicit true. +An entry that states its levels outright in reasoning_effort_levels wins whole, for a model whose set +the per-level flags cannot express (Kimi K3 takes low, high and max, and no flag can drop medium). +Every other entry answers through its supports_*_reasoning_effort flags, read with the polarity the +chat gate uses: medium and high are unconditional, minimal and low are opt-out (refused only on an +explicit false), xhigh is opt-in, and none is opt-out except on the azure gpt-5 family, whose chat +config refuses it without an explicit true. -xhigh is gated on the request path by the openai and azure gpt-5 configs. max is not gated there at -all: outside the gpt-6-astra rows every entry carrying supports_max_reasoning_effort is Claude-family, -and anthropic/chat/transformation.py gates max on the output_config path while its reasoning_effort -path maps any level to a thinking budget. Making max opt-in is a deliberate trade, then, since an -explicit flag is the only signal that the tier is a real one rather than litellm rounding the level -to a budget, and a missing flag costs advisory metadata rather than a rejected request. +The Responses gate reads none, minimal, low and xhigh as opt-out. Neither gate judges max, which +Chat Completions refuses and Responses honors on the gpt-6 family, so its flag is advisory and +advertised opt-in: outside the gpt-6 rows every entry carrying supports_max_reasoning_effort is +Claude-family, where anthropic/chat/transformation.py gates max on the output_config path, so an +explicit flag is the only signal that the tier is real. A deployment the map describes with no effort flags at all resolves to None rather than to the opt-out defaults. 689 of the map's 854 reasoning entries carry no flag, and the o-series, xai and diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 4ced9194464..617aabeeecf 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3805,7 +3805,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, @@ -8251,7 +8251,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8300,7 +8300,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -8841,7 +8841,7 @@ "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -30766,9 +30766,9 @@ "supports_response_schema": true, "supports_vision": true, "supports_reasoning": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.3-codex-spark": { "litellm_provider": "chatgpt", @@ -35018,11 +35018,13 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, - "supports_none_reasoning_effort": false, - "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "deprecation_date": "2027-04-01" }, "gpt-5.3-chat-latest": { "cache_read_input_token_cost": 1.75e-07, @@ -69878,18 +69880,47 @@ }, "azure/eu/gpt-6-astra": { "deprecation_date": "2028-01-11", - "cache_creation_input_token_cost": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, - "cache_read_input_token_cost": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, - "input_cost_per_token": 1.1e-05, - "input_cost_per_token_above_272k_tokens": 2.2e-05, + "cache_creation_input_token_cost": 1.5e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3e-05, + "cache_read_input_token_cost": 1.2e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-06, + "input_cost_per_token": 1.2e-05, + "input_cost_per_token_above_272k_tokens": 2.4e-05, "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5.5e-05, - "output_cost_per_token_above_272k_tokens": 8.25e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_reasoning": true + "output_cost_per_token": 6e-05, + "output_cost_per_token_above_272k_tokens": 9e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true }, "azure/eu/gpt-6-luna": { "deprecation_date": "2028-03-11", @@ -78374,7 +78405,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, @@ -78423,7 +78454,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -78471,7 +78502,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, - "supports_none_reasoning_effort": true, + "supports_none_reasoning_effort": false, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, diff --git a/tests/unit/llms/anthropic/experimental_pass_through/adapters/test_handler_reasoning_effort_normalization.py b/tests/unit/llms/anthropic/experimental_pass_through/adapters/test_handler_reasoning_effort_normalization.py index 895b3b57f7b..92c51f39345 100644 --- a/tests/unit/llms/anthropic/experimental_pass_through/adapters/test_handler_reasoning_effort_normalization.py +++ b/tests/unit/llms/anthropic/experimental_pass_through/adapters/test_handler_reasoning_effort_normalization.py @@ -205,6 +205,23 @@ class TestTheNormalizedTierIsTheTierSent: ): assert _reasoning_effort_sent(model, provider, effort) == expected + @pytest.mark.parametrize( + "model, provider", + [ + ("gpt-5.5", "azure_ai"), + ("azure_ai/gpt-5.5", "azure_ai"), + ("gpt-5.6", "azure"), + ("us/gpt-5.6", "azure"), + ], + ) + def test_an_azure_hosted_deployment_without_the_flag_drops_to_the_tier_it_accepts( + self, local_model_cost_map, model, provider + ): + """Chat Completions answers ``max`` on gpt-5.6 with a 400 naming ``none`` through ``xhigh`` + (OpenAI, 2026-10-01) and none of these Azure rows declares the level, so the adapter sends + the tier below instead of the rejected one.""" + assert _reasoning_effort_sent(model, provider, "max") == "xhigh" + @pytest.mark.parametrize( "model, provider", [ @@ -212,13 +229,16 @@ class TestTheNormalizedTierIsTheTierSent: ("azure_ai/gpt-6-astra", "azure_ai"), ("gpt-6-astra", "azure"), ("us/gpt-6-astra", "azure"), + ("eu/gpt-6-astra", "azure"), ], ) - def test_an_azure_hosted_astra_deployment_drops_to_the_tier_it_accepts( - self, local_model_cost_map, model, provider - ): - """The deployment answers ``max`` with a 400 naming ``none`` through ``xhigh``, so the rows - say so and the adapter sends the tier below instead of the rejected one.""" + def test_an_azure_hosted_astra_deployment_drops_to_the_tier_its_chat_route_accepts( + self, local_model_cost_map: None, model: str, provider: str + ) -> None: + """A Foundry gpt-6-astra answers a Chat Completions ``max`` with a 400 naming low through + xhigh while honoring the same level on the Responses route (2026-10-01). The row's flag is + route-blind, so it keeps max off and the adapter, which cannot know which route the call + takes, sends the tier below instead of the level chat rejects.""" assert _reasoning_effort_sent(model, provider, "max") == "xhigh" def test_the_openai_hosted_twin_still_sends_max(self, local_model_cost_map): diff --git a/tests/unit/llms/azure/chat/test_azure_gpt5_transformation.py b/tests/unit/llms/azure/chat/test_azure_gpt5_transformation.py index 3b3ef1a9cd4..a72417ce113 100644 --- a/tests/unit/llms/azure/chat/test_azure_gpt5_transformation.py +++ b/tests/unit/llms/azure/chat/test_azure_gpt5_transformation.py @@ -1,3 +1,6 @@ +from collections.abc import Mapping +from typing import Final + import pytest import litellm @@ -343,17 +346,22 @@ def test_azure_gpt_6_astra_takes_the_reasoning_series_request_shape(): model="gpt-6-astra", custom_llm_provider="azure", max_tokens=100, - reasoning_effort="max", + reasoning_effort="xhigh", ) assert params["max_completion_tokens"] == 100 assert "max_tokens" not in params - assert params["reasoning_effort"] == "max" + assert params["reasoning_effort"] == "xhigh" -@pytest.mark.parametrize("model", ["azure/gpt-6-astra", "azure/us/gpt-6-astra"]) -def test_azure_gpt6_astra_reasoning_effort_none_unlocks_temperature(config: AzureOpenAIGPT5Config, model: str): - """Foundry's gpt-6-astra accepts reasoning_effort='none' and, only then, a non-default - temperature (verified live against a Foundry deployment), unlike OpenAI's gpt-6-astra.""" +@pytest.mark.parametrize("model", ["azure/gpt-6-sol", "azure/us/gpt-6-sol"]) +def test_azure_reasoning_effort_none_unlocks_temperature_off_the_azure_row( + config: AzureOpenAIGPT5Config, monkeypatch: pytest.MonkeyPatch, model: str +): + """A deployment whose azure/ row takes none accepts a non-default temperature with it, read off + that row even when OpenAI's twin row says the model refuses none.""" + monkeypatch.setitem( + litellm.model_cost, "gpt-6-sol", {**litellm.model_cost["gpt-6-sol"], "supports_none_reasoning_effort": False} + ) params = config.map_openai_params( non_default_params={"temperature": 0.2, "reasoning_effort": "none"}, optional_params={}, @@ -365,14 +373,127 @@ def test_azure_gpt6_astra_reasoning_effort_none_unlocks_temperature(config: Azur assert params["reasoning_effort"] == "none" -@pytest.mark.parametrize("model", ["azure/gpt-6-astra", "azure/us/gpt-6-astra"]) -def test_azure_gpt6_astra_rejects_reasoning_effort_minimal(config: AzureOpenAIGPT5Config, model: str): - """Foundry's gpt-6-astra lists none, low, medium, high, xhigh and max but not minimal.""" - with pytest.raises(litellm.utils.UnsupportedParamsError): - config.map_openai_params( - non_default_params={"reasoning_effort": "minimal"}, +def _azure_chat_row_forwards(row: Mapping[str, object], level: str) -> bool: + """Azure chat polarity: max is never gated, xhigh and none need an explicit true, every other + level only has to not be false.""" + if level == "max": + return True + flag: Final = row.get(f"supports_{level}_reasoning_effort") + return flag is True if level in ("xhigh", "none") else flag is not False + + +@pytest.mark.parametrize("model", ["azure/gpt-6-astra", "azure/us/gpt-6-astra", "azure/eu/gpt-6-astra"]) +@pytest.mark.parametrize("level", ["none", "minimal", "low", "medium", "high", "xhigh", "max"]) +def test_azure_gpt6_astra_forwards_exactly_the_effort_levels_its_map_row_allows( + config: AzureOpenAIGPT5Config, model: str, level: str +): + """The azure/ row is the whole contract for a Foundry deployment. A live Foundry gpt-6-astra + (model gpt-6-astra-2026-09-03) answered reasoning_effort none with a 400 naming low, medium, + high and xhigh on 2026-10-01, so its row turns none and minimal off. The row keeps max off too, + since chat refuses it, but no gate reads that flag: the Responses route honors max, so chat + forwards it for the bridge and a plain chat call gets the provider's own 400.""" + forwarded: Final = _azure_chat_row_forwards(litellm.model_cost[model], level) + dropped: Final = config.map_openai_params( + non_default_params={"reasoning_effort": level}, + optional_params={}, + model=model, + drop_params=True, + api_version="2025-04-01-preview", + ) + assert ("reasoning_effort" in dropped) is forwarded + if forwarded: + kept: Final = config.map_openai_params( + non_default_params={"reasoning_effort": level}, optional_params={}, model=model, drop_params=False, api_version="2025-04-01-preview", ) + assert kept["reasoning_effort"] == level + else: + with pytest.raises(litellm.utils.UnsupportedParamsError): + config.map_openai_params( + non_default_params={"reasoning_effort": level}, + optional_params={}, + model=model, + drop_params=False, + api_version="2025-04-01-preview", + ) + + +@pytest.mark.parametrize("model", ["azure/gpt-6-astra", "azure/us/gpt-6-astra", "azure/eu/gpt-6-astra"]) +def test_azure_gpt6_astra_row_turns_none_and_minimal_off(model: str): + """Pinned on purpose so the row-derived test above cannot go vacuous: a Foundry gpt-6-astra + deployment refused none on chat and on Responses on 2026-10-01 (400 unsupported_value naming + low, medium, high, xhigh), and minimal the same way; max it refused on chat while honoring it + on Responses, so the route-blind flag stays off. When Azure adds a level, flip the row and + this assertion together.""" + row: Final = litellm.model_cost[model] + assert row["supports_none_reasoning_effort"] is False + assert row["supports_minimal_reasoning_effort"] is False + assert row["supports_max_reasoning_effort"] is False + + +def test_azure_chat_gate_reads_the_foundry_row_when_azure_ai_prefix_survives_provider_remap( + config: AzureOpenAIGPT5Config, monkeypatch: pytest.MonkeyPatch +): + """A Foundry deployment on an OpenAI-v1 host is re-routed to the azure provider with its + azure_ai/ prefix intact, and this config then gates it. The rows are made to disagree on low, + a level neither real row flags, so the prefixed name has to read azure_ai/gpt-6-sol while the + bare deployment name keeps reading azure/gpt-6-sol.""" + monkeypatch.setitem( + litellm.model_cost, + "azure_ai/gpt-6-sol", + {**litellm.model_cost["azure_ai/gpt-6-sol"], "supports_low_reasoning_effort": False}, + ) + monkeypatch.setitem( + litellm.model_cost, + "azure/gpt-6-sol", + {**litellm.model_cost["azure/gpt-6-sol"], "supports_low_reasoning_effort": True}, + ) + prefixed: Final = config.map_openai_params( + non_default_params={"reasoning_effort": "low"}, + optional_params={}, + model="azure_ai/gpt-6-sol", + drop_params=True, + api_version="2025-04-01-preview", + ) + assert "reasoning_effort" not in prefixed + bare: Final = config.map_openai_params( + non_default_params={"reasoning_effort": "low"}, + optional_params={}, + model="gpt-6-sol", + drop_params=True, + api_version="2025-04-01-preview", + ) + assert bare["reasoning_effort"] == "low" + + +def test_azure_chat_gate_falls_back_to_the_azure_row_for_an_azure_ai_name_the_map_lacks( + config: AzureOpenAIGPT5Config, monkeypatch: pytest.MonkeyPatch +): + monkeypatch.delitem(litellm.model_cost, "azure_ai/gpt-6-sol") + monkeypatch.setitem( + litellm.model_cost, + "azure/gpt-6-sol", + {**litellm.model_cost["azure/gpt-6-sol"], "supports_low_reasoning_effort": False}, + ) + dropped: Final = config.map_openai_params( + non_default_params={"reasoning_effort": "low"}, + optional_params={}, + model="azure_ai/gpt-6-sol", + drop_params=True, + api_version="2025-04-01-preview", + ) + assert "reasoning_effort" not in dropped + + +@pytest.mark.parametrize("key", ["azure/gpt-6.1-sol", "azure/gpt-6.1-sol-2026-09-29", "azure_ai/gpt-6.1-sol"]) +def test_azure_gpt61_sol_rows_turn_none_off(key: str): + """Pinned on purpose, as the astra row above: a Foundry gpt-6.1-sol deployment (model + gpt-6.1-sol-2026-09-29) refused none on chat and on Responses on 2026-10-02 (400 unsupported_value + naming low, medium, high, xhigh, and max on Responses), and minimal the same way, while these rows + still said none was on. When Azure adds a level, flip the row and this assertion together.""" + row: Final = litellm.model_cost[key] + assert row["supports_none_reasoning_effort"] is False + assert row["supports_minimal_reasoning_effort"] is False diff --git a/tests/unit/llms/azure/response/test_azure_transformation.py b/tests/unit/llms/azure/response/test_azure_transformation.py index 532c278e891..447efeee117 100644 --- a/tests/unit/llms/azure/response/test_azure_transformation.py +++ b/tests/unit/llms/azure/response/test_azure_transformation.py @@ -651,16 +651,21 @@ def local_model_cost_map(monkeypatch: pytest.MonkeyPatch) -> None: litellm.add_known_models(model_cost_map=litellm.model_cost) -def test_azure_responses_gpt6_astra_reasoning_effort_none_unlocks_temperature(local_model_cost_map: None): - """Foundry's gpt-6-astra accepts reasoning.effort='none' with a non-default temperature - while OpenAI's gpt-6-astra does not, so the gate must read the azure/ cost-map entry - for the bare deployment name rather than OpenAI's.""" +def test_azure_responses_reasoning_effort_none_unlocks_temperature_off_the_azure_row( + local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch +): + """The gate reads the azure/ cost-map entry for the bare deployment name rather than OpenAI's + twin: with OpenAI's gpt-6-sol row turned off for none, azure/gpt-6-sol's row still lets none + through and, only then, a non-default temperature.""" + monkeypatch.setitem( + litellm.model_cost, "gpt-6-sol", {**litellm.model_cost["gpt-6-sol"], "supports_none_reasoning_effort": False} + ) params = AzureOpenAIResponsesAPIConfig().map_openai_params( response_api_optional_params=ResponsesAPIOptionalRequestParams( temperature=0.2, reasoning={"effort": "none"}, ), - model="gpt-6-astra", + model="gpt-6-sol", drop_params=False, ) assert params["temperature"] == 0.2 @@ -679,6 +684,116 @@ def test_azure_responses_gpt6_astra_rejects_temperature_while_reasoning(local_mo ) +@pytest.mark.parametrize("model", ["gpt-6-astra", "gpt-6.1-sol"]) +@pytest.mark.parametrize("level", ["none", "minimal", "low", "medium", "high", "xhigh", "max"]) +def test_azure_responses_gpt6_effort_levels_follow_the_azure_row(local_model_cost_map: None, model: str, level: str): + """A bare deployment name reads the azure/ row, opt-out for every level but max, so the none + and minimal Foundry refuses on this route (live 400s on 2026-10-01 for gpt-6-astra and 2026-10-02 + for gpt-6.1-sol) are dropped or refused here while the max it honors goes through whatever the + route-blind flag says.""" + forwarded = ( + level == "max" or litellm.model_cost[f"azure/{model}"].get(f"supports_{level}_reasoning_effort") is not False + ) + dropped = AzureOpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params=ResponsesAPIOptionalRequestParams(reasoning={"effort": level}), + model=model, + drop_params=True, + ) + assert ("reasoning" in dropped) is forwarded + if forwarded: + kept = AzureOpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params=ResponsesAPIOptionalRequestParams(reasoning={"effort": level}), + model=model, + drop_params=False, + ) + assert kept["reasoning"] == {"effort": level} + else: + with pytest.raises(litellm.UnsupportedParamsError): + AzureOpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params=ResponsesAPIOptionalRequestParams(reasoning={"effort": level}), + model=model, + drop_params=False, + ) + + +def test_azure_gpt6_astra_keeps_max_on_this_route_whatever_its_row_says(local_model_cost_map: None): + """Pinned on purpose: the row-derived test above exempts max by hand, so this one has to fail + if the gate ever reads the flag. A Foundry gpt-6-astra deployment answered reasoning.effort max + through /v1/responses with 200, the effort echoed back and reasoning tokens billed, on + 2026-10-01, while chat refuses the same level, as OpenAI's chat does. The row keeps max off for + the adapter and the picker, and this gate still forwards it even under drop_params.""" + assert litellm.model_cost["azure/gpt-6-astra"]["supports_max_reasoning_effort"] is False + kept = AzureOpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params=ResponsesAPIOptionalRequestParams(reasoning={"effort": "max"}), + model="gpt-6-astra", + drop_params=True, + ) + assert kept["reasoning"] == {"effort": "max"} + + +@pytest.mark.parametrize("level", ["none", "minimal", "low", "medium", "high", "xhigh", "max"]) +def test_azure_responses_effort_gate_fires_when_azure_ai_prefix_survives_provider_remap( + local_model_cost_map: None, level: str +): + """litellm.responses(model="azure_ai/gpt-6.1-sol", api_base=) is re-routed to the + azure provider with the prefix intact, so this config sees the prefixed name. The gate used to + skip every prefixed name as another provider's pass-through, and a live Foundry gpt-6.1-sol + answered the forwarded none and minimal with 400 on 2026-10-02 even under drop_params. The + prefixed name reads the azure_ai/ row and drops or refuses exactly what that row turns off.""" + forwarded = ( + level == "max" + or litellm.model_cost["azure_ai/gpt-6.1-sol"].get(f"supports_{level}_reasoning_effort") is not False + ) + dropped = AzureOpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params=ResponsesAPIOptionalRequestParams( + max_output_tokens=60, reasoning={"effort": level} + ), + model="azure_ai/gpt-6.1-sol", + drop_params=True, + ) + assert ("reasoning" in dropped) is forwarded + if forwarded: + return + with pytest.raises(litellm.UnsupportedParamsError): + AzureOpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params=ResponsesAPIOptionalRequestParams( + max_output_tokens=60, reasoning={"effort": level} + ), + model="azure_ai/gpt-6.1-sol", + drop_params=False, + ) + + +def test_azure_responses_prefixed_name_reads_the_foundry_row_not_the_azure_twin( + local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch +): + """The rows are made to disagree on low, a level neither real row flags, so the prefixed name + proving it reads azure_ai/gpt-6-sol cannot pass by reading azure/gpt-6-sol, which the bare + deployment name keeps reading.""" + monkeypatch.setitem( + litellm.model_cost, + "azure_ai/gpt-6-sol", + {**litellm.model_cost["azure_ai/gpt-6-sol"], "supports_low_reasoning_effort": False}, + ) + monkeypatch.setitem( + litellm.model_cost, + "azure/gpt-6-sol", + {**litellm.model_cost["azure/gpt-6-sol"], "supports_low_reasoning_effort": True}, + ) + prefixed = AzureOpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params=ResponsesAPIOptionalRequestParams(reasoning={"effort": "low"}), + model="azure_ai/gpt-6-sol", + drop_params=True, + ) + assert "reasoning" not in prefixed + bare = AzureOpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params=ResponsesAPIOptionalRequestParams(reasoning={"effort": "low"}), + model="gpt-6-sol", + drop_params=True, + ) + assert bare["reasoning"] == {"effort": "low"} + + def test_azure_responses_sends_the_deployment_name_when_azure_ai_prefix_survives_provider_remap(): request = AzureOpenAIResponsesAPIConfig().transform_responses_api_request( model="azure_ai/gpt-5.4-nano", diff --git a/tests/unit/llms/azure_ai/chat/test_azure_ai_transformation.py b/tests/unit/llms/azure_ai/chat/test_azure_ai_transformation.py index 47609261a25..b229fb857d7 100644 --- a/tests/unit/llms/azure_ai/chat/test_azure_ai_transformation.py +++ b/tests/unit/llms/azure_ai/chat/test_azure_ai_transformation.py @@ -146,17 +146,30 @@ def _local_model_cost_map(monkeypatch: pytest.MonkeyPatch) -> None: monkeypatch.setattr(litellm, "model_cost", get_model_cost_map(url=litellm.model_cost_map_url)) -def test_foundry_gpt_6_astra_keeps_sampling_params_when_reasoning_effort_is_none(_local_model_cost_map): +def test_foundry_gpt_6_sol_keeps_sampling_params_when_reasoning_effort_is_none(_local_model_cost_map): + """gpt-6-sol's Foundry row still says none, so the sampling params that ride on it stay. gpt-6-astra + used to be the model here until its row turned none off (a live Foundry deployment answered none + with a 400 naming low through xhigh on 2026-10-01); the test below pins that flip.""" optional_params = AzureAIStudioConfig().map_openai_params( non_default_params={"reasoning_effort": "none", "temperature": 0.2, "top_p": 0.9}, optional_params={}, - model="gpt-6-astra", + model="gpt-6-sol", drop_params=False, ) assert optional_params == {"reasoning_effort": "none", "temperature": 0.2, "top_p": 0.9} +def test_foundry_gpt_6_astra_refuses_reasoning_effort_none_before_the_call(_local_model_cost_map): + with pytest.raises(litellm.utils.UnsupportedParamsError): + AzureAIStudioConfig().map_openai_params( + non_default_params={"reasoning_effort": "none"}, + optional_params={}, + model="gpt-6-astra", + drop_params=False, + ) + + def test_azure_ai_grok_stop_parameter_handling(): diff --git a/tests/unit/llms/azure_ai/responses/test_azure_ai_responses_transformation.py b/tests/unit/llms/azure_ai/responses/test_azure_ai_responses_transformation.py index bae956eb061..26076f8bb34 100644 --- a/tests/unit/llms/azure_ai/responses/test_azure_ai_responses_transformation.py +++ b/tests/unit/llms/azure_ai/responses/test_azure_ai_responses_transformation.py @@ -1,12 +1,15 @@ import json +from typing import Final import httpx import pytest import respx import litellm +from litellm.llms.azure.responses.transformation import AzureOpenAIResponsesAPIConfig from litellm.llms.azure_ai.responses.transformation import AzureAIResponsesAPIConfig from litellm.responses.main import _will_bridge_to_chat_completions +from litellm.types.llms.openai import ResponsesAPIOptionalRequestParams from litellm.types.router import GenericLiteLLMParams from litellm.utils import ProviderConfigManager @@ -309,3 +312,74 @@ async def test_aresponses_serverless_host_stays_on_chat_bridge(): assert chat_route.called assert not responses_route.called assert chat_route.calls.last.request.headers["Authorization"] == "Bearer fake-key" + + +def _responses_params(**fields: object) -> ResponsesAPIOptionalRequestParams: + return ResponsesAPIOptionalRequestParams(**fields) # pyright: ignore[reportArgumentType] # TypedDict kwargs from a test helper + + +def test_foundry_responses_effort_gate_reads_the_azure_ai_row( + local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch +): + """A Foundry deployment and its Azure OpenAI namesake are different products, so the Foundry + Responses route answers from the azure_ai/ row the Foundry chat route already reads, never from + the azure/ twin. The rows are made to disagree on low, a level neither real row flags, so a + leak from the wrong row cannot hide behind rows that happen to agree.""" + monkeypatch.setitem( + litellm.model_cost, + "azure_ai/gpt-6-sol", + {**litellm.model_cost["azure_ai/gpt-6-sol"], "supports_low_reasoning_effort": False}, + ) + monkeypatch.setitem( + litellm.model_cost, + "azure/gpt-6-sol", + {**litellm.model_cost["azure/gpt-6-sol"], "supports_low_reasoning_effort": True}, + ) + + dropped: Final = AzureAIResponsesAPIConfig().map_openai_params( + response_api_optional_params=_responses_params(reasoning={"effort": "low"}), + model="gpt-6-sol", + drop_params=True, + ) + assert "reasoning" not in dropped + + with pytest.raises(litellm.UnsupportedParamsError): + AzureAIResponsesAPIConfig().map_openai_params( + response_api_optional_params=_responses_params(reasoning={"effort": "low"}), + model="gpt-6-sol", + drop_params=False, + ) + + kept_by_azure_openai: Final = AzureOpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params=_responses_params(reasoning={"effort": "low"}), + model="gpt-6-sol", + drop_params=True, + ) + assert kept_by_azure_openai["reasoning"] == {"effort": "low"} + + +def test_foundry_responses_none_unlocks_temperature_off_the_azure_ai_row( + local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch +): + """The sampling-param unlock that rides on none reads the same azure_ai/ row as the effort gate: + with the azure/ twin turned off for none, the Foundry row still lets none through and, only + then, a non-default temperature.""" + monkeypatch.setitem( + litellm.model_cost, + "azure_ai/gpt-6-sol", + {**litellm.model_cost["azure_ai/gpt-6-sol"], "supports_none_reasoning_effort": True}, + ) + monkeypatch.setitem( + litellm.model_cost, + "azure/gpt-6-sol", + {**litellm.model_cost["azure/gpt-6-sol"], "supports_none_reasoning_effort": False}, + ) + + params: Final = AzureAIResponsesAPIConfig().map_openai_params( + response_api_optional_params=_responses_params(temperature=0.2, reasoning={"effort": "none"}), + model="gpt-6-sol", + drop_params=False, + ) + + assert params["temperature"] == 0.2 + assert params["reasoning"] == {"effort": "none"} diff --git a/tests/unit/llms/openai/responses/test_openai_responses_transformation.py b/tests/unit/llms/openai/responses/test_openai_responses_transformation.py index 0ef45501d91..3bc3d12db2b 100644 --- a/tests/unit/llms/openai/responses/test_openai_responses_transformation.py +++ b/tests/unit/llms/openai/responses/test_openai_responses_transformation.py @@ -1858,6 +1858,115 @@ class TestResponsesSurfaceSharesTheEffortRule: ) assert ("top_p" in mapped) is top_p_survives + @pytest.mark.parametrize("level", ["none", "minimal", "low", "medium", "high", "xhigh", "max"]) + def test_effort_levels_the_map_row_turns_off_are_dropped_or_refused(self, local_model_cost_map, level): + """Same row as the chat gate, read opt-out for every level but max. gpt-6.1-sol's row turns + none and minimal off: OpenAI lists low, medium, high, xhigh and max for it + (https://developers.openai.com/api/docs/models/gpt-6.1-sol, via #43910), and a local proxy + got OpenAI's 400 for none and minimal through /v1/responses on 2026-09-30.""" + forwarded = ( + level == "max" or litellm.model_cost["gpt-6.1-sol"].get(f"supports_{level}_reasoning_effort") is not False + ) + dropped = OpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params={"reasoning": {"effort": level}}, + model="gpt-6.1-sol", + drop_params=True, + ) + assert ("reasoning" in dropped) is forwarded + if forwarded: + kept = OpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params={"reasoning": {"effort": level}}, + model="gpt-6.1-sol", + drop_params=False, + ) + assert kept["reasoning"] == {"effort": level} + else: + with pytest.raises(litellm.UnsupportedParamsError): + OpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params={"reasoning": {"effort": level}}, + model="gpt-6.1-sol", + drop_params=False, + ) + + @pytest.mark.parametrize( + ("flags", "level", "forwarded"), + [ + ({}, "none", True), + ({"supports_none_reasoning_effort": False}, "none", False), + ({"supports_none_reasoning_effort": True}, "none", True), + ({"supports_minimal_reasoning_effort": False}, "minimal", False), + ({"supports_max_reasoning_effort": False}, "max", True), + ({}, "xhigh", True), + ({"supports_xhigh_reasoning_effort": False}, "xhigh", False), + ({"supports_none_reasoning_effort": False}, "medium", True), + ], + ) + def test_the_row_flags_alone_decide_whether_a_level_is_forwarded( + self, local_model_cost_map, monkeypatch, flags, level, forwarded + ): + """Same model name, rewritten row: this surface reads every level opt-out, xhigh included, + so the gate flips with the flags alone. max is the one level no flag can turn off here, + since the same model honors it on this route and refuses it on chat. The chat test module + pins the real row's facts.""" + real_row = litellm.model_cost["gpt-6.1-sol"] + without_flags = { + field: value + for field, value in real_row.items() + if not (field.startswith("supports_") and field.endswith("_reasoning_effort")) + } + monkeypatch.setitem(litellm.model_cost, "gpt-6.1-sol", {**without_flags, **flags}) + dropped = OpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params={"reasoning": {"effort": level}}, + model="gpt-6.1-sol", + drop_params=True, + ) + assert ("reasoning" in dropped) is forwarded + if not forwarded: + with pytest.raises(litellm.UnsupportedParamsError): + OpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params={"reasoning": {"effort": level}}, + model="gpt-6.1-sol", + drop_params=False, + ) + + def test_dropping_a_refused_effort_keeps_the_rest_of_the_reasoning_object(self, local_model_cost_map): + refused = next( + level + for level in ("none", "minimal", "low") + if litellm.model_cost["gpt-6.1-sol"].get(f"supports_{level}_reasoning_effort") is False + ) + mapped = OpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params={"reasoning": {"effort": refused, "summary": "auto"}}, + model="gpt-6.1-sol", + drop_params=True, + ) + assert mapped["reasoning"] == {"summary": "auto"} + + @pytest.mark.parametrize("level", ["none", "minimal", "low", "medium", "high", "xhigh", "max"]) + def test_gpt5_3_codex_forwards_exactly_the_effort_levels_its_map_row_allows(self, local_model_cost_map, level): + """The gate turns a stale false into a local refusal, so the Responses-only codex row has to + say what the route does. On 2026-10-01 /v1/responses answered gpt-5.3-codex none and xhigh + with 200 (effort echoed back) and minimal and max with 400 unsupported_value naming none, + low, medium, high and xhigh, so the row takes none and xhigh and turns minimal off.""" + forwarded = ( + level == "max" or litellm.model_cost["gpt-5.3-codex"].get(f"supports_{level}_reasoning_effort") is not False + ) + mapped = OpenAIResponsesAPIConfig().map_openai_params( + response_api_optional_params={"reasoning": {"effort": level}}, + model="gpt-5.3-codex", + drop_params=True, + ) + assert ("reasoning" in mapped) is forwarded + + def test_gpt5_3_codex_row_takes_none_and_xhigh(self, local_model_cost_map): + """Pinned on purpose so the row-derived test above cannot go vacuous: the live answers of + 2026-10-01 listed above. When OpenAI changes the set, flip the row and this assertion + together.""" + row = litellm.model_cost["gpt-5.3-codex"] + assert row["supports_none_reasoning_effort"] is True + assert row["supports_xhigh_reasoning_effort"] is True + assert row["supports_minimal_reasoning_effort"] is False + def test_top_p_raises_without_drop_params(self, local_model_cost_map): with pytest.raises(litellm.UnsupportedParamsError): OpenAIResponsesAPIConfig().map_openai_params( diff --git a/tests/unit/llms/openai/test_gpt5_transformation.py b/tests/unit/llms/openai/test_gpt5_transformation.py index 41f5816600f..7b10411ba20 100644 --- a/tests/unit/llms/openai/test_gpt5_transformation.py +++ b/tests/unit/llms/openai/test_gpt5_transformation.py @@ -1,4 +1,6 @@ import re +from collections.abc import Mapping +from typing import Final import pytest @@ -431,6 +433,105 @@ def test_gpt5_drops_reasoning_effort_minimal_when_requested(config: OpenAIConfig assert "reasoning_effort" not in params +def _chat_row_forwards(row: Mapping[str, object], level: str) -> bool: + """Chat polarity: max is never gated, xhigh needs an explicit true, every other level only has + to not be false.""" + if level == "max": + return True + flag: Final = row.get(f"supports_{level}_reasoning_effort") + return flag is True if level == "xhigh" else flag is not False + + +@pytest.mark.parametrize("level", ["none", "minimal", "low", "medium", "high", "xhigh", "max"]) +def test_gpt6_1_sol_forwards_exactly_the_effort_levels_its_map_row_allows(config: OpenAIConfig, level: str): + """The map row is the whole contract, so a new GPT-6 model is gated by its row with no code + change. gpt-6.1-sol's row turns none and minimal off: OpenAI lists low, medium, high, xhigh + and max for it (https://developers.openai.com/api/docs/models/gpt-6.1-sol, via #43910), and a + local proxy got OpenAI's 400 for none and minimal on both endpoints on 2026-09-30.""" + forwarded: Final = _chat_row_forwards(litellm.model_cost["gpt-6.1-sol"], level) + dropped: Final = config.map_openai_params( + non_default_params={"reasoning_effort": level}, + optional_params={}, + model="gpt-6.1-sol", + drop_params=True, + ) + assert ("reasoning_effort" in dropped) is forwarded + if forwarded: + kept: Final = config.map_openai_params( + non_default_params={"reasoning_effort": level}, + optional_params={}, + model="gpt-6.1-sol", + drop_params=False, + ) + assert kept["reasoning_effort"] == level + else: + with pytest.raises(litellm.utils.UnsupportedParamsError): + config.map_openai_params( + non_default_params={"reasoning_effort": level}, + optional_params={}, + model="gpt-6.1-sol", + drop_params=False, + ) + + +def test_gpt6_1_sol_row_turns_none_and_minimal_off(): + """Pinned on purpose so the row-derived test above cannot go vacuous: OpenAI lists low, medium, + high, xhigh and max for gpt-6.1-sol and neither none nor minimal + (https://developers.openai.com/api/docs/models/gpt-6.1-sol, read 2026-09-30 via #43910), and a + local proxy got OpenAI's 400 for both on 2026-09-30. When OpenAI adds a level, flip the row and + this assertion together.""" + row: Final = litellm.model_cost["gpt-6.1-sol"] + assert row["supports_none_reasoning_effort"] is False + assert row["supports_minimal_reasoning_effort"] is False + + +def _row_without_effort_flags(row: Mapping[str, object]) -> dict[str, object]: + return { + field: value + for field, value in row.items() + if not (field.startswith("supports_") and field.endswith("_reasoning_effort")) + } + + +@pytest.mark.parametrize( + ("flags", "level", "forwarded"), + [ + ({}, "none", True), + ({"supports_none_reasoning_effort": False}, "none", False), + ({"supports_none_reasoning_effort": True}, "none", True), + ({"supports_minimal_reasoning_effort": False}, "minimal", False), + ({"supports_max_reasoning_effort": False}, "max", True), + ({}, "max", True), + ({}, "xhigh", False), + ({"supports_xhigh_reasoning_effort": True}, "xhigh", True), + ({"supports_none_reasoning_effort": False}, "medium", True), + ], +) +def test_the_row_flags_alone_decide_whether_a_chat_level_is_forwarded( + config: OpenAIConfig, monkeypatch: pytest.MonkeyPatch, flags: dict[str, bool], level: str, forwarded: bool +): + """Same model name, rewritten row: the gate flips with the flags and nothing else, so breaking the + gate fails here while the pinned test above catches the real row losing a flag.""" + monkeypatch.setitem( + litellm.model_cost, "gpt-6.1-sol", {**_row_without_effort_flags(litellm.model_cost["gpt-6.1-sol"]), **flags} + ) + dropped: Final = config.map_openai_params( + non_default_params={"reasoning_effort": level}, + optional_params={}, + model="gpt-6.1-sol", + drop_params=True, + ) + assert ("reasoning_effort" in dropped) is forwarded + if not forwarded: + with pytest.raises(litellm.utils.UnsupportedParamsError): + config.map_openai_params( + non_default_params={"reasoning_effort": level}, + optional_params={}, + model="gpt-6.1-sol", + drop_params=False, + ) + + def test_gpt5_minimal_dict_triggers_validation(config: OpenAIConfig): """Dict with effort='minimal' triggers minimal model-support validation.""" with pytest.raises(litellm.utils.UnsupportedParamsError): diff --git a/tests/unit/router_utils/test_reasoning_effort_capability.py b/tests/unit/router_utils/test_reasoning_effort_capability.py index 2f23320a8ad..787444c96c1 100644 --- a/tests/unit/router_utils/test_reasoning_effort_capability.py +++ b/tests/unit/router_utils/test_reasoning_effort_capability.py @@ -395,22 +395,25 @@ class TestGpt6AstraAdvertisesItsDocumentedLevels: [ ("azure/gpt-6-astra", "azure"), ("azure/us/gpt-6-astra", "azure"), + ("azure/eu/gpt-6-astra", "azure"), ("azure_ai/gpt-6-astra", "azure_ai"), ], ) - def test_an_azure_hosted_deployment_advertises_none_but_not_max( + def test_an_azure_hosted_deployment_advertises_the_levels_both_its_routes_accept( self, local_model_cost_map, model, custom_llm_provider ): - """Microsoft hosts the same model with a different level set than OpenAI does. Verified live - on both Azure routes: none returns 200 with zero reasoning tokens and unlocks temperature, - which OpenAI's API rejects, while max returns 400 unsupported_value naming none through - xhigh as the levels it does take.""" + """Verified live on 2026-10-01 against a Foundry gpt-6-astra deployment (model + gpt-6-astra-2026-09-03): none returns 400 unsupported_value on chat and on Responses, naming + low, medium, high and xhigh as the levels it takes; Responses also honors max with reasoning + tokens billed while chat refuses it, as OpenAI's chat does. The flag is route-blind, so the + row keeps max off and the advertised set stops at the level every route accepts. + Earlier evidence (2026-09-05, commit e79f3ec5205) had none accepted on chat; the deployment + no longer behaves that way.""" from litellm.utils import _get_model_info_helper model_info = dict(_get_model_info_helper(model=model, custom_llm_provider=custom_llm_provider)) assert resolve_supported_reasoning_efforts(model_info, deployment_is_mapped=True) == ( - "none", "low", "medium", "high", diff --git a/tests/unit/test_main.py b/tests/unit/test_main.py index c7e9301c02b..2c99228013e 100644 --- a/tests/unit/test_main.py +++ b/tests/unit/test_main.py @@ -986,6 +986,50 @@ def test_responses_api_bridge_check_gpt_5_4_tools_with_reasoning_none_stays_chat assert model_info.get("mode") != "responses" +@pytest.mark.parametrize( + "model, custom_llm_provider, reasoning_effort", + [ + ("gpt-6.1-sol", "openai", "none"), + ("gpt-6.1-sol", "openai", {"effort": "none"}), + ("gpt-6-astra", "azure", "none"), + ], +) +def test_responses_api_bridge_check_tools_with_a_none_the_row_refuses_routes_to_responses( + local_model_cost_map: None, model: str, custom_llm_provider: str, reasoning_effort: object +) -> None: + """The ``none`` escape hatch only holds when the chat gate forwards it. These rows refuse + ``none``, so the gate drops it (or refuses the call) and the provider runs its default effort, + under which Chat Completions rejects function tools; the bridge has to fire the way it does + for an unset effort. Row-derived: the test follows the flag, never the vendor's answer.""" + from litellm.main import responses_api_bridge_check + + row_key: Final = model if custom_llm_provider == "openai" else f"{custom_llm_provider}/{model}" + assert litellm.model_cost[row_key]["supports_none_reasoning_effort"] is False + + model_info, _ = responses_api_bridge_check( + model=model, + custom_llm_provider=custom_llm_provider, + tools=[{"type": "function", "function": {"name": "get_capital"}}], + reasoning_effort=reasoning_effort, + ) + + assert model_info.get("mode") == "responses" + + +def test_responses_api_bridge_check_a_none_the_row_refuses_stays_chat_without_tools( + local_model_cost_map: None, +) -> None: + """Without function tools nothing forces the Responses route: the dropped ``none`` leaves a + plain chat call at the default effort, as for any other dropped level.""" + from litellm.main import responses_api_bridge_check + + model_info, _ = responses_api_bridge_check( + model="gpt-6.1-sol", custom_llm_provider="openai", reasoning_effort="none" + ) + + assert model_info.get("mode") != "responses" + + def test_responses_api_bridge_check_reasoning_none_with_summary_still_routes_to_responses(): """A reasoning summary is Responses-only regardless of effort value.""" from litellm.main import responses_api_bridge_check @@ -1362,11 +1406,15 @@ _FOUNDRY_FUNCTION_TOOL: Final = ({"type": "function", "function": {"name": "get_ pytest.param("gpt-6-astra", "https://myresource.openai.azure.com", None, id="gpt-6-azure-openai-host"), pytest.param("gpt-5.6-sol", _FOUNDRY_API_BASE, "low", id="gpt-5.6-explicit-effort"), pytest.param("gpt-5.6-sol", _FOUNDRY_API_BASE, {"effort": "high"}, id="gpt-5.6-explicit-effort-dict"), + pytest.param("gpt-6-astra", _FOUNDRY_API_BASE, "none", id="gpt-6-row-refused-none"), ], ) def test_responses_api_bridge_check_azure_ai_foundry_rejected_tools_route_to_responses( model_name, api_base, reasoning_effort ): + """The explicit ``none`` only keeps a Foundry gpt-6 request on chat while the deployment takes + it; the ``azure_ai/gpt-6-astra`` row says it does not, so the gate drops it and the call runs at + the default effort, under which Foundry rejects function tools from gpt-6 on.""" from litellm.main import responses_api_bridge_check model_info, model = responses_api_bridge_check( @@ -1384,7 +1432,6 @@ def test_responses_api_bridge_check_azure_ai_foundry_rejected_tools_route_to_res @pytest.mark.parametrize( "model_name, api_base, reasoning_effort", [ - pytest.param("gpt-6-astra", _FOUNDRY_API_BASE, "none", id="explicit-none-stays-chat"), pytest.param("gpt-5.6-sol", _FOUNDRY_API_BASE, None, id="gpt-5.6-unset-effort-stays-chat"), pytest.param("gpt-5.6-sol", _FOUNDRY_API_BASE, "none", id="gpt-5.6-explicit-none-stays-chat"), pytest.param("gpt-5.5", _FOUNDRY_API_BASE, "high", id="gpt-5.5-explicit-effort-stays-chat"), From 5684267b1237348c06e78957eafa2c67db8589db Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 16:04:07 -0700 Subject: [PATCH 23/66] fix(logging): report the cost-map entry billing used in model_map_information (#47182) Backport of #47182 to stable/1.104.x. Cherry-picked from 1212260ab15fe2c9ff28f0c465ad2d0833da8143 (main). Adapted to the line's private helper names (_select_model_name_for_cost_calc, _response_cost_calculator); the new test is appended to the line's test file. --- litellm/litellm_core_utils/litellm_logging.py | 15 +++- .../test_litellm_logging.py | 84 +++++++++++++++++++ 2 files changed, 98 insertions(+), 1 deletion(-) diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py index f601503824d..e03bc59b838 100644 --- a/litellm/litellm_core_utils/litellm_logging.py +++ b/litellm/litellm_core_utils/litellm_logging.py @@ -5863,6 +5863,7 @@ class StandardLoggingPayloadSetup: custom_llm_provider: str | None, init_response_obj: object, api_base: str | None = None, + router_model_id: str | None = None, ) -> StandardLoggingModelInformation: model_cost_name: Final = _select_model_name_for_cost_calc( model=base_model if custom_pricing else None, @@ -5870,12 +5871,23 @@ class StandardLoggingPayloadSetup: base_model=base_model, custom_pricing=custom_pricing, ) + pricing_model_name: Final = ( + _select_model_name_for_cost_calc( + model=base_model if custom_pricing else None, + completion_response=init_response_obj, + base_model=base_model, + custom_pricing=custom_pricing, + router_model_id=router_model_id, + ) + if router_model_id is not None + else model_cost_name + ) if model_cost_name is None: model_cost_information = StandardLoggingModelInformation(model_map_key="", model_map_value=None) else: try: _model_cost_information: Final = litellm.get_model_info( - model=model_cost_name, + model=pricing_model_name or model_cost_name, custom_llm_provider=custom_llm_provider, api_base=api_base, ) @@ -6537,6 +6549,7 @@ def get_standard_logging_object_payload( custom_llm_provider=kwargs.get("custom_llm_provider"), init_response_obj=init_response_obj, api_base=litellm_params.get("api_base"), + router_model_id=logging_obj.get_router_model_id(), ) error_information, error_str = StandardLoggingPayloadSetup.get_error_information_for_logging_payload( diff --git a/tests/unit/litellm_core_utils/test_litellm_logging.py b/tests/unit/litellm_core_utils/test_litellm_logging.py index d5aa0159b8d..2a524f46731 100644 --- a/tests/unit/litellm_core_utils/test_litellm_logging.py +++ b/tests/unit/litellm_core_utils/test_litellm_logging.py @@ -26,6 +26,7 @@ from litellm.integrations.custom_logger import CustomLogger from litellm.litellm_core_utils.litellm_logging import Logging as LitellmLogging from litellm.litellm_core_utils.litellm_logging import ( _extract_response_obj_and_hidden_params, + get_standard_logging_object_payload, _get_status_fields, set_callbacks, ) @@ -8841,3 +8842,86 @@ async def test_prompt_management_with_unchanged_variables_replays_a_byte_identic assert json.dumps(messages_n_plus_one[: len(messages_n)], sort_keys=True) == json.dumps(messages_n, sort_keys=True) assert messages_n[0] == {"role": "system", "content": "You are a pirate. Answer in one sentence."} assert len(messages_n_plus_one) == len(messages_n) + 2 +@pytest.mark.parametrize( + ("input_cost_per_token", "output_cost_per_token"), + [(1e-06, 2e-06), (0.0, 0.0)], + ids=["custom_price", "explicit_zero_price"], +) +def test_standard_logging_payload_reports_the_deployment_entry_the_request_was_billed_from( + input_cost_per_token: float, output_cost_per_token: float +): + """A deployment with its own price keeps the catalog model as model_map_key but is logged at its own rates.""" + deployment_id: Final = "lit9660-priced-deployment" + deployment_model_info: Final = { + "id": deployment_id, + "input_cost_per_token": input_cost_per_token, + "output_cost_per_token": output_cost_per_token, + } + litellm.register_model( + model_cost={ + deployment_id: { + "litellm_provider": "openai", + "mode": "chat", + "input_cost_per_token": input_cost_per_token, + "output_cost_per_token": output_cost_per_token, + } + }, + persist_across_reloads=False, + ) + try: + logging_obj: Final = LitellmLogging( + model="gpt-5.4-nano", + messages=[{"role": "user", "content": "Hi"}], + stream=False, + call_type="completion", + start_time=time.time(), + litellm_call_id="lit9660", + function_id="fn", + ) + litellm_params: Final = { + "metadata": { + "model_group": "lit9660-group", + "deployment": "openai/gpt-5.4-nano", + "model_info": deployment_model_info, + } + } + logging_obj.update_environment_variables( + model="gpt-5.4-nano", user="", optional_params={}, litellm_params=litellm_params, custom_llm_provider="openai" + ) + response: Final = ModelResponse( + model="gpt-5.4-nano", + choices=[litellm.Choices(message=litellm.Message(role="assistant", content="hi"))], + usage=litellm.Usage(prompt_tokens=10, completion_tokens=6, total_tokens=16), + ) + + response_cost: Final = logging_obj._response_cost_calculator(result=response) + payload: Final = get_standard_logging_object_payload( + kwargs={ + "model": "gpt-5.4-nano", + "custom_llm_provider": "openai", + "litellm_params": litellm_params, + "response_cost": response_cost, + }, + init_response_obj=response, + start_time=datetime.datetime.now(), + end_time=datetime.datetime.now(), + logging_obj=logging_obj, + status="success", + ) + + assert response_cost == 10 * input_cost_per_token + 6 * output_cost_per_token + assert payload is not None + assert payload["model_map_information"] == { + "model_map_key": "openai/gpt-5.4-nano", + "model_map_value": litellm.get_model_info(model=f"openai/{deployment_id}", custom_llm_provider="openai"), + } + model_map_value: Final = payload["model_map_information"]["model_map_value"] + assert model_map_value is not None + assert (model_map_value["input_cost_per_token"], model_map_value["output_cost_per_token"]) == ( + input_cost_per_token, + output_cost_per_token, + ) + finally: + litellm.model_cost.pop(deployment_id, None) + + From 826f40473505b8a5ada4aae977732ad33078e520 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Mon, 19 Oct 2026 14:19:14 -0700 Subject: [PATCH 24/66] fix(decisions): log every request field the caller sent on /v1/systemone and /v1/decisions (#47183) * fix(decisions): log every request field the caller sent on /v1/systemone and /v1/decisions * fix(decisions): serialize the logged request with model_dump_json so no mutable dict is built * refactor(decisions): drop the state-only messages pick in function_setup, prepare_call logs the request * fix(decisions): return the single logged message so no mutable list type is annotated * fix(decisions): log the caller's raw request fields before validation so a rejected request is still recorded * fix(decisions): serialize the raw request fields with pydantic_core so question objects and mapping proxies log as JSON * fix(decisions): log the caller request at the SDK entry so requests rejected before prepare_call are recorded too * test(decisions): assert the exact BadRequestError for the rejected-questions case --------- Backport of #47183 to stable/1.104.x Cherry-picked from 53821f665417c0d02be0c4495e188ea9c0c3584e (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/decisions/call.py | 27 ++++++++ litellm/decisions/main.py | 9 +++ litellm/systemone/main.py | 5 +- litellm/utils.py | 7 -- tests/unit/decisions/test_call.py | 102 ++++++++++++++++++++++++++++++ 5 files changed, 142 insertions(+), 8 deletions(-) create mode 100644 tests/unit/decisions/test_call.py diff --git a/litellm/decisions/call.py b/litellm/decisions/call.py index 1ad2f006736..1d75d6942f0 100644 --- a/litellm/decisions/call.py +++ b/litellm/decisions/call.py @@ -1,9 +1,11 @@ +import json from collections.abc import Mapping, Sequence from dataclasses import dataclass, field, replace from typing import Final, TypeAlias import httpx from pydantic import ConfigDict, TypeAdapter, ValidationError +from pydantic_core import to_jsonable_python from typing_extensions import assert_never import litellm @@ -30,6 +32,7 @@ from litellm.types.decisions import ( OpenAIDecisionResponse, UnsupportedDecisionsRequest, ) +from litellm.types.llms.openai import ChatCompletionUserMessage from litellm.types.utils import LlmProviders from litellm.utils import ProviderConfigManager @@ -148,6 +151,30 @@ def _provider_ir_request( return _UnsupportedSafetyIdentifier() +_LOGGED_FIELDS_ADAPTER: Final[TypeAdapter[Mapping[str, object]]] = TypeAdapter(Mapping[str, object]) + + +def _jsonable_fallback(value: object) -> object: + return dict(_LOGGED_FIELDS_ADAPTER.validate_python(value)) if isinstance(value, Mapping) else str(value) + + +def _logged_request_message(caller_request: object) -> ChatCompletionUserMessage: + caller_fields: Final = _LOGGED_FIELDS_ADAPTER.validate_python( + to_jsonable_python(caller_request, fallback=_jsonable_fallback) + ) + sent_fields: Final = json.dumps( + dict((name, value) for name, value in caller_fields.items() if value not in (None, [], {})) + ) + return ChatCompletionUserMessage(role="user", content=sent_fields) + + +def log_caller_request(kwargs: Mapping[str, object], caller_request: object) -> None: + """Record every request field the caller sent as the logged `messages`, before any validation.""" + logging_obj: Final = kwargs.get("litellm_logging_obj") + if isinstance(logging_obj, LiteLLMLoggingObj): + logging_obj.update_messages([_logged_request_message(caller_request)]) + + def prepare_call( *, model: str, diff --git a/litellm/decisions/main.py b/litellm/decisions/main.py index 8b13d04770a..a31e385dac4 100644 --- a/litellm/decisions/main.py +++ b/litellm/decisions/main.py @@ -13,6 +13,7 @@ from litellm.decisions.call import ( SystemOneQuestions, SystemOneRequestFields, asend, + log_caller_request, prepare_call, send, ) @@ -59,6 +60,14 @@ def _prepare_decisions_call( extra_headers: Mapping[str, str] | None, kwargs: Mapping[str, object], ) -> DecisionsCall: + log_caller_request( + kwargs, + { + "input": decision_input, + "questions": questions, + **({"state": kwargs["state"]} if "state" in kwargs else {}), + }, + ) return prepare_call( model=model, fields=_request_fields(decision_input, questions, kwargs), diff --git a/litellm/systemone/main.py b/litellm/systemone/main.py index 754b69142f9..b784082b00f 100644 --- a/litellm/systemone/main.py +++ b/litellm/systemone/main.py @@ -8,6 +8,7 @@ from litellm.decisions.call import ( SystemOneQuestions, SystemOneRequestFields, asend, + log_caller_request, prepare_call, reject_other_format, send, @@ -29,10 +30,12 @@ def _prepare_systemone_call( extra_headers: Mapping[str, str] | None, kwargs: Mapping[str, object], ) -> DecisionsCall: + fields: Final = SystemOneRequestFields(state=state, questions=questions) + log_caller_request(kwargs, fields) reject_other_format(model=model, kwargs=kwargs, field_name="input", other_function="decisions") return prepare_call( model=model, - fields=SystemOneRequestFields(state=state, questions=questions), + fields=fields, safety_identifier=safety_identifier, api_key=api_key, api_base=api_base, diff --git a/litellm/utils.py b/litellm/utils.py index 64ecfcac98c..f6d775d1248 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -954,10 +954,6 @@ def _ocr_document_summary(document: object) -> str: # Runs once per call to check if the user wants to send their data anywhere - PostHog/Sentry/Slack/etc. -_DECISION_CALL_TYPES: Final[frozenset[str]] = frozenset( - (CallTypes.decisions.value, CallTypes.adecisions.value, CallTypes.systemone.value, CallTypes.asystemone.value) -) - def function_setup( original_function: str, @@ -1207,9 +1203,6 @@ def function_setup( if isinstance(search_query, list) else search_query ) - elif call_type in _DECISION_CALL_TYPES: - decisions_state: Final = args[1] if len(args) > 1 else kwargs.get("state") or kwargs.get("input") or "" - messages = decisions_state if isinstance(decisions_state, str) else json.dumps(decisions_state, default=str) elif call_type in (CallTypes.image_edit.value, CallTypes.aimage_edit.value): messages = args[1] if len(args) > 1 else kwargs.get("prompt") elif call_type in (CallTypes.ocr.value, CallTypes.aocr.value): diff --git a/tests/unit/decisions/test_call.py b/tests/unit/decisions/test_call.py new file mode 100644 index 00000000000..0aec79ceb09 --- /dev/null +++ b/tests/unit/decisions/test_call.py @@ -0,0 +1,102 @@ +import json +from collections.abc import Mapping +from datetime import datetime, timezone +from typing import Final + +import pytest + +import litellm +from litellm.decisions.main import _prepare_decisions_call +from litellm.litellm_core_utils.litellm_logging import Logging +from litellm.systemone.main import _prepare_systemone_call + +QUESTION_TEXT: Final = "Is this about a billing problem?" +CONNECTION: Final = { + "model": "hosted_vllm/jev-fake", + "safety_identifier": None, + "api_key": "fake-provider-key", + "api_base": "http://127.0.0.1:4010", + "timeout": None, + "custom_llm_provider": None, + "extra_headers": None, +} + + +def _logging_obj(call_type: str) -> Logging: + return Logging( + model="hosted_vllm/jev-fake", + messages="placeholder", + stream=False, + call_type=call_type, + start_time=datetime.now(timezone.utc), + litellm_call_id="lit-9659", + function_id="lit-9659", + ) + + +def _logged_request(logging_obj: Logging) -> Mapping[str, object]: + messages: Final = logging_obj.model_call_details["messages"] + assert len(messages) == 1 and messages[0]["role"] == "user" + return json.loads(messages[0]["content"]) + + +def test_systemone_logs_every_request_field_the_caller_sent(): + logging_obj: Final = _logging_obj("asystemone") + + _prepare_systemone_call( + **CONNECTION, + state={"message": "My card was charged twice."}, + questions={"billing": {"type": "noul", "instructions": QUESTION_TEXT}}, + kwargs={"litellm_logging_obj": logging_obj}, + ) + + logged: Final = _logged_request(logging_obj) + assert logged["state"] == {"message": "My card was charged twice."} + assert logged["questions"]["billing"]["instructions"] == QUESTION_TEXT + assert set(logged) == {"state", "questions"} + + +def test_decisions_logs_every_request_field_the_caller_sent(): + logging_obj: Final = _logging_obj("adecisions") + + _prepare_decisions_call( + **CONNECTION, + decision_input="My card was charged twice.", + questions=[{"type": "predicate", "instructions": QUESTION_TEXT}], + kwargs={"litellm_logging_obj": logging_obj}, + ) + + logged: Final = _logged_request(logging_obj) + assert logged["input"] == "My card was charged twice." + assert logged["questions"][0]["instructions"] == QUESTION_TEXT + assert set(logged) == {"input", "questions"} + + +def test_request_is_logged_even_when_it_is_rejected_before_the_provider_call(): + logging_obj: Final = _logging_obj("asystemone") + + with pytest.raises(litellm.BadRequestError): + _prepare_systemone_call( + **CONNECTION, + state={"message": "My card was charged twice."}, + questions={"billing": {"type": "noul", "instructions": QUESTION_TEXT}}, + kwargs={"litellm_logging_obj": logging_obj, "input": "sent to the wrong function"}, + ) + + logged: Final = _logged_request(logging_obj) + assert logged["questions"]["billing"]["instructions"] == QUESTION_TEXT + + +def test_decisions_request_is_logged_even_when_its_questions_fail_validation(): + logging_obj: Final = _logging_obj("adecisions") + + with pytest.raises(litellm.BadRequestError): + _prepare_decisions_call( + **CONNECTION, + decision_input="My card was charged twice.", + questions=[{"type": "not-a-question-type", "instructions": QUESTION_TEXT}], + kwargs={"litellm_logging_obj": logging_obj}, + ) + + logged: Final = _logged_request(logging_obj) + assert logged["questions"][0]["instructions"] == QUESTION_TEXT From d64ac3998c00a7069ada1257fae2fe446f94f7aa Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Mon, 19 Oct 2026 14:27:29 -0700 Subject: [PATCH 25/66] feat(router): let a deployment set a timeout per service_tier (#47406) * feat(router): let a deployment set a timeout per service_tier Adds timeout_by_service_tier and stream_timeout_by_service_tier to a deployment's litellm_params. A request whose service_tier matches a key uses that value in place of the deployment's timeout or stream_timeout. A timeout the client sends still wins and requests without a matching tier are unchanged Co-authored-by: adc77 * style(router): sort the request_timeout_resolver import * fix(router): read the service tier maps without the untyped params get * fix(router): look the service tier timeout up through a typed get --------- Backport of #47406 to stable/1.104.x Cherry-picked from 62ce515d15fd61f15985d54120265f5976fbce4d (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: adc77 --- .../request_timeout_resolver.py | 23 ++++++- litellm/passthrough/timeout_utils.py | 19 ++++-- litellm/router.py | 3 + litellm/types/litellm_params.py | 2 + litellm/types/router.py | 5 ++ .../test_pass_through_endpoints.py | 26 ++++++++ tests/unit/test_router/test_router_timeout.py | 61 +++++++++++++++++++ tests/unit/types/test_litellm_params.py | 2 + ui/litellm-dashboard/src/lib/http/schema.d.ts | 16 +++++ 9 files changed, 151 insertions(+), 6 deletions(-) create mode 100644 tests/unit/test_router/test_router_timeout.py diff --git a/litellm/litellm_core_utils/request_timeout_resolver.py b/litellm/litellm_core_utils/request_timeout_resolver.py index a32651fedee..0e011dc06a0 100644 --- a/litellm/litellm_core_utils/request_timeout_resolver.py +++ b/litellm/litellm_core_utils/request_timeout_resolver.py @@ -12,10 +12,15 @@ tell "user asked for this" from "nobody set it". This resolver answers that: from __future__ import annotations -from typing import Final +from collections.abc import Mapping +from typing import Final, Literal, Protocol + +from pydantic import TypeAdapter from litellm.constants import DEFAULT_REQUEST_TIMEOUT_SECONDS +_TIMEOUTS_BY_SERVICE_TIER: Final[TypeAdapter[Mapping[str, float] | None]] = TypeAdapter(Mapping[str, float] | None) + def get_configured_request_timeout() -> float | None: """Return the explicitly-configured ``litellm.request_timeout``, else ``None``.""" @@ -27,3 +32,19 @@ def get_configured_request_timeout() -> float | None: if timeout != float(DEFAULT_REQUEST_TIMEOUT_SECONDS): return timeout return None + + +class _DeploymentParams(Protocol): + def get(self, key: str, /) -> object: ... + + +def get_service_tier_timeout( + service_tier: object, + litellm_params: _DeploymentParams, + key: Literal["timeout_by_service_tier", "stream_timeout_by_service_tier"], +) -> float | None: + """Return the deployment's ``key`` timeout for the request's ``service_tier``, else ``None``.""" + if not isinstance(service_tier, str): + return None + timeouts: Final = _TIMEOUTS_BY_SERVICE_TIER.validate_python(litellm_params.get(key)) + return None if timeouts is None else timeouts.get(service_tier) diff --git a/litellm/passthrough/timeout_utils.py b/litellm/passthrough/timeout_utils.py index fc67aa8c553..a54689a8f4d 100644 --- a/litellm/passthrough/timeout_utils.py +++ b/litellm/passthrough/timeout_utils.py @@ -5,6 +5,8 @@ from typing import Final from pydantic import TypeAdapter +from litellm.litellm_core_utils.request_timeout_resolver import get_service_tier_timeout + DEFAULT_PASS_THROUGH_REQUEST_TIMEOUT_SECONDS: Final = 600.0 _SECONDS: Final = TypeAdapter(float) @@ -48,21 +50,27 @@ def resolve_llm_passthrough_timeout( Anthropic /v1/messages). Non-streaming precedence: kwargs timeout/request_timeout -> litellm_params - timeout/request_timeout -> router_timeout -> general_settings.pass_through_request_timeout - -> 600s default. + timeout_by_service_tier[kwargs service_tier] -> litellm_params timeout/request_timeout -> router_timeout + -> general_settings.pass_through_request_timeout -> 600s default. Streaming (``kwargs["stream"]`` truthy) resolves ``stream_timeout`` at every level before any generic timeout, matching ``Router._get_stream_timeout`` on the completion route: - kwargs stream_timeout -> litellm_params stream_timeout -> router_stream_timeout, then the - non-streaming chain above. + kwargs stream_timeout -> litellm_params stream_timeout_by_service_tier[kwargs service_tier] -> + litellm_params stream_timeout -> router_stream_timeout, then the non-streaming chain above. Only the first set value is validated as seconds, so a value in a lower-precedence field never fails the call. """ request: Final = kwargs if kwargs is not None else _NO_PARAMS deployment: Final = litellm_params if litellm_params is not None else _NO_PARAMS + service_tier: Final = request.get("service_tier") stream_candidates: Final = ( - (request.get("stream_timeout"), deployment.get("stream_timeout"), router_stream_timeout) + ( + request.get("stream_timeout"), + get_service_tier_timeout(service_tier, deployment, "stream_timeout_by_service_tier"), + deployment.get("stream_timeout"), + router_stream_timeout, + ) if request.get("stream") else () ) @@ -70,6 +78,7 @@ def resolve_llm_passthrough_timeout( *stream_candidates, request.get("timeout"), request.get("request_timeout"), + get_service_tier_timeout(service_tier, deployment, "timeout_by_service_tier"), deployment.get("timeout"), deployment.get("request_timeout"), router_timeout, diff --git a/litellm/router.py b/litellm/router.py index d794311453c..1bf6c85c61b 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -97,6 +97,7 @@ from litellm.litellm_core_utils.ptu_pricing import ( ) from litellm.litellm_core_utils.request_timeout_resolver import ( get_configured_request_timeout, + get_service_tier_timeout, ) from litellm.litellm_core_utils.secret_redaction import redact_string from litellm.litellm_core_utils.sensitive_data_masker import ( @@ -4044,6 +4045,7 @@ class Router: """Helper to get stream timeout from kwargs or deployment params""" return ( kwargs.get("stream_timeout", None) # the params dynamically set by user + or get_service_tier_timeout(kwargs.get("service_tier"), data, "stream_timeout_by_service_tier") or data.get("stream_timeout", None) # timeout set on litellm_params for this deployment or self.stream_timeout # timeout set on router or self.request_timeout # litellm_settings.request_timeout (per-attempt) @@ -4055,6 +4057,7 @@ class Router: timeout: Final = ( kwargs.get("timeout", None) # the params dynamically set by user or kwargs.get("request_timeout", None) # the params dynamically set by user + or get_service_tier_timeout(kwargs.get("service_tier"), data, "timeout_by_service_tier") or data.get("timeout", None) # timeout set on litellm_params for this deployment or data.get("request_timeout", None) # timeout set on litellm_params for this deployment or self.request_timeout # litellm_settings.request_timeout (per-attempt) diff --git a/litellm/types/litellm_params.py b/litellm/types/litellm_params.py index 83a42c235f9..3ebe7c7cd16 100644 --- a/litellm/types/litellm_params.py +++ b/litellm/types/litellm_params.py @@ -72,6 +72,8 @@ class ProviderConnection: request_timeout: float | None = None force_timeout: float | None = None stream_timeout: float | str | None = None + timeout_by_service_tier: Mapping[str, float] | None = None + stream_timeout_by_service_tier: Mapping[str, float] | None = None max_retries: int | None = None tenant_id: str | None = None client_id: str | None = None diff --git a/litellm/types/router.py b/litellm/types/router.py index b72809f625f..b2464d83944 100644 --- a/litellm/types/router.py +++ b/litellm/types/router.py @@ -389,6 +389,9 @@ class GenericLiteLLMParams(CredentialLiteLLMParams, CustomPricingLiteLLMParams): otpm: int | None = None timeout: float | str | httpx.Timeout | None = None # if str, pass in as os.environ/ stream_timeout: float | str | None = None # timeout when making stream=True calls, if str, pass in as os.environ/ + # per service_tier overrides of timeout / stream_timeout, used when the request's service_tier matches a key + timeout_by_service_tier: Mapping[str, float] | None = None + stream_timeout_by_service_tier: Mapping[str, float] | None = None max_retries: int | None = None drop_params: bool | str | None = None organization: str | None = None # for openai orgs @@ -573,6 +576,8 @@ class LiteLLMParamsTypedDict(TypedDict, total=False): api_version: str | None timeout: float | str | httpx.Timeout | None stream_timeout: float | str | None + timeout_by_service_tier: ReadOnly[Mapping[str, float] | None] + stream_timeout_by_service_tier: ReadOnly[Mapping[str, float] | None] max_retries: int | None organization: list | str | None # for openai orgs provider_affinity_header: ReadOnly[str | None] diff --git a/tests/test_litellm/proxy/pass_through_endpoints/test_pass_through_endpoints.py b/tests/test_litellm/proxy/pass_through_endpoints/test_pass_through_endpoints.py index aa269a10867..14f32183d64 100644 --- a/tests/test_litellm/proxy/pass_through_endpoints/test_pass_through_endpoints.py +++ b/tests/test_litellm/proxy/pass_through_endpoints/test_pass_through_endpoints.py @@ -1249,6 +1249,32 @@ def test_resolve_llm_passthrough_timeout_validates_only_the_winning_value( assert resolve_llm_passthrough_timeout(kwargs=kwargs, litellm_params=litellm_params) == expected +def test_resolve_llm_passthrough_timeout_uses_the_deployment_timeout_for_the_requests_service_tier(): + litellm_params = { + "timeout": 610, + "stream_timeout": 30, + "timeout_by_service_tier": {"flex": 900}, + "stream_timeout_by_service_tier": {"flex": 950}, + } + assert resolve_llm_passthrough_timeout(kwargs={"service_tier": "flex"}, litellm_params=litellm_params) == 900.0 + assert resolve_llm_passthrough_timeout(kwargs={"service_tier": "default"}, litellm_params=litellm_params) == 610.0 + assert ( + resolve_llm_passthrough_timeout(kwargs={"service_tier": "flex", "timeout": 20}, litellm_params=litellm_params) + == 20.0 + ) + assert ( + resolve_llm_passthrough_timeout(kwargs={"service_tier": "flex", "stream": True}, litellm_params=litellm_params) + == 950.0 + ) + assert ( + resolve_llm_passthrough_timeout( + kwargs={"service_tier": "flex", "stream": True}, + litellm_params={"timeout": 610, "stream_timeout": 30, "timeout_by_service_tier": {"flex": 900}}, + ) + == 30.0 + ) + + def test_resolve_llm_passthrough_timeout_rejects_a_non_numeric_winner(): with pytest.raises(ValidationError): resolve_llm_passthrough_timeout(kwargs={"timeout": httpx.Timeout(30.0)}) diff --git a/tests/unit/test_router/test_router_timeout.py b/tests/unit/test_router/test_router_timeout.py new file mode 100644 index 00000000000..9520bf57a4c --- /dev/null +++ b/tests/unit/test_router/test_router_timeout.py @@ -0,0 +1,61 @@ +from typing import Final + +import pytest + +from litellm import Router + + +@pytest.mark.parametrize( + "request_kwargs, expected_timeout", + [ + ({"service_tier": "flex"}, 900.0), + ({"service_tier": "default"}, 610.0), + ({}, 610.0), + ({"service_tier": "flex", "timeout": 20}, 20), + ({"service_tier": "flex", "stream": True}, 950.0), + ({"service_tier": "default", "stream": True}, 610.0), + ({"service_tier": "flex", "stream": True, "stream_timeout": 30}, 30), + ], +) +def test_the_deployment_timeout_for_the_requests_service_tier_wins_over_its_general_timeout( + request_kwargs: dict[str, object], expected_timeout: float +) -> None: + router: Final = Router( + model_list=[ + { + "model_name": "openai-gpt-5.1", + "litellm_params": { + "model": "openai/gpt-5.1", + "api_key": "sk-test", + "timeout": 610, + "stream_timeout": 610, + "timeout_by_service_tier": {"flex": 900}, + "stream_timeout_by_service_tier": {"flex": 950}, + }, + } + ] + ) + deployment_params: Final = router.model_list[0]["litellm_params"] + + assert router._get_timeout(kwargs=request_kwargs, data=deployment_params) == expected_timeout + + +def test_a_stream_keeps_the_deployment_stream_timeout_when_only_the_request_timeout_map_names_its_tier() -> None: + router: Final = Router( + model_list=[ + { + "model_name": "openai-gpt-5.1", + "litellm_params": { + "model": "openai/gpt-5.1", + "api_key": "sk-test", + "timeout": 610, + "stream_timeout": 30, + "timeout_by_service_tier": {"flex": 900}, + }, + } + ] + ) + deployment_params: Final = router.model_list[0]["litellm_params"] + + assert router._get_timeout(kwargs={"service_tier": "flex", "stream": True}, data=deployment_params) == 30.0 + assert router._get_timeout(kwargs={"service_tier": "flex"}, data=deployment_params) == 900.0 diff --git a/tests/unit/types/test_litellm_params.py b/tests/unit/types/test_litellm_params.py index e421321aaaa..d88fcce4936 100644 --- a/tests/unit/types/test_litellm_params.py +++ b/tests/unit/types/test_litellm_params.py @@ -74,6 +74,8 @@ CONNECTION_NAMES: Final = ( "request_timeout", "force_timeout", "stream_timeout", + "timeout_by_service_tier", + "stream_timeout_by_service_tier", "max_retries", "tenant_id", "client_id", diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts index 42c306cc3b3..a91ec268faa 100644 --- a/ui/litellm-dashboard/src/lib/http/schema.d.ts +++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts @@ -32920,6 +32920,10 @@ export interface components { } | null; /** Stream Timeout */ stream_timeout?: number | string | null; + /** Stream Timeout By Service Tier */ + stream_timeout_by_service_tier?: { + [key: string]: number; + } | null; /** Tag Regex */ tag_regex?: string[] | null; /** Tags */ @@ -32932,6 +32936,10 @@ export interface components { }[] | null; /** Timeout */ timeout?: number | string | null; + /** Timeout By Service Tier */ + timeout_by_service_tier?: { + [key: string]: number; + } | null; /** Tpm */ tpm?: number | null; /** Use Chat Completions Api */ @@ -46518,6 +46526,10 @@ export interface components { } | null; /** Stream Timeout */ stream_timeout?: number | string | null; + /** Stream Timeout By Service Tier */ + stream_timeout_by_service_tier?: { + [key: string]: number; + } | null; /** Tag Regex */ tag_regex?: string[] | null; /** Tags */ @@ -46530,6 +46542,10 @@ export interface components { }[] | null; /** Timeout */ timeout?: number | string | null; + /** Timeout By Service Tier */ + timeout_by_service_tier?: { + [key: string]: number; + } | null; /** Tpm */ tpm?: number | null; /** Use Chat Completions Api */ From f0fb99913169ce9c8276832a9dffa1230cdc09e1 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Mon, 19 Oct 2026 15:14:46 -0700 Subject: [PATCH 26/66] fix(cost): bill Gemini audio/image/video prompt tokens at the resolved input rate when no modality rate exists (#47373) * fix(cost): bill Gemini audio/image/video prompt tokens at the resolved input rate when no modality rate exists Co-authored-by: shivam * style(cost): ruff format the modality cost calls --------- Backport of #47373 to stable/1.104.x Cherry-picked from 09e919351437851ea0ba689f7e878a7395627f57 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: shivam --- .../litellm_core_utils/llm_cost_calc/utils.py | 52 ++++++++++++---- .../llm_cost_calc/test_llm_cost_calc_utils.py | 60 +++++++++++++++++++ 2 files changed, 100 insertions(+), 12 deletions(-) diff --git a/litellm/litellm_core_utils/llm_cost_calc/utils.py b/litellm/litellm_core_utils/llm_cost_calc/utils.py index 46bf2ec2960..e65531121a6 100644 --- a/litellm/litellm_core_utils/llm_cost_calc/utils.py +++ b/litellm/litellm_core_utils/llm_cost_calc/utils.py @@ -1064,6 +1064,25 @@ def parse_completion_tokens_details(usage: Usage) -> CompletionTokensDetailsResu ) +def _modality_token_cost( + model_info: ModelInfo, + modality_cost_key: str, + tokens: int, + prompt_base_cost: float, + service_tier: str | None, +) -> float: + """ + Audio, image and video prompt tokens bill at their modality rate when the model has one. + Without one they are ordinary prompt tokens, so they bill at `prompt_base_cost`, which + `_get_token_base_cost` has already resolved for the service tier and long-context tier. + """ + tiered_key: Final = _get_service_tier_cost_key(modality_cost_key, service_tier) + cost_key: Final = tiered_key if model_info.get(tiered_key) is not None else modality_cost_key + if model_info.get(cost_key) is None: + return float(tokens) * prompt_base_cost + return calculate_cost_component(model_info, cost_key, tokens) + + def _calculate_input_cost( prompt_tokens_details: PromptTokensDetailsResult, model_info: ModelInfo, @@ -1094,28 +1113,37 @@ def _calculate_input_cost( if prompt_tokens_details["audio_tokens"] and not ( prompt_tokens_details["audio_length_seconds"] and model_info.get("input_cost_per_audio_per_second") is not None ): - audio_cost_key: Final = _get_service_tier_cost_key("input_cost_per_audio_token", service_tier) - prompt_cost += calculate_cost_component(model_info, audio_cost_key, prompt_tokens_details["audio_tokens"]) + prompt_cost += _modality_token_cost( + model_info, + "input_cost_per_audio_token", + prompt_tokens_details["audio_tokens"], + prompt_base_cost, + service_tier, + ) ### IMAGE TOKEN COST if prompt_tokens_details["image_tokens"] and not ( prompt_tokens_details["image_count"] and model_info.get("input_cost_per_image") is not None ): - # For image token costs: - # First check if input_cost_per_image_token is available. If not, default to generic input_cost_per_token. - image_token_cost_key = "input_cost_per_image_token" - if model_info.get(image_token_cost_key) is None: - image_token_cost_key = "input_cost_per_token" - prompt_cost += calculate_cost_component(model_info, image_token_cost_key, prompt_tokens_details["image_tokens"]) + prompt_cost += _modality_token_cost( + model_info, + "input_cost_per_image_token", + prompt_tokens_details["image_tokens"], + prompt_base_cost, + service_tier, + ) ### VIDEO TOKEN COST if prompt_tokens_details["video_tokens"] and not ( prompt_tokens_details["video_length_seconds"] and model_info.get("input_cost_per_video_per_second") is not None ): - video_token_cost_key = "input_cost_per_video_token" - if model_info.get(video_token_cost_key) is None: - video_token_cost_key = "input_cost_per_token" - prompt_cost += calculate_cost_component(model_info, video_token_cost_key, prompt_tokens_details["video_tokens"]) + prompt_cost += _modality_token_cost( + model_info, + "input_cost_per_video_token", + prompt_tokens_details["video_tokens"], + prompt_base_cost, + service_tier, + ) ### CACHE WRITING COST - Now uses tiered pricing if ( diff --git a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index 0afd989272e..2b5dd50fdec 100644 --- a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -450,6 +450,66 @@ def test_video_tokens_fallback_to_base_cost(): assert round(completion_cost, 12) == round((600 + 1120) * 2e-6, 12) +def test_prompt_audio_and_video_tokens_without_modality_rates_bill_at_tiered_input_rate(): + """Prompt audio/video tokens with no modality rate are prompt tokens, so a >200k prompt bills them above-200k.""" + from unittest.mock import patch + + mock_model_info = { + "input_cost_per_token": 2e-6, + "input_cost_per_token_above_200k_tokens": 4e-6, + "output_cost_per_token": 1.2e-5, + "output_cost_per_token_above_200k_tokens": 1.8e-5, + } + + usage = Usage( + prompt_tokens=816032, + completion_tokens=4559, + total_tokens=820591, + prompt_tokens_details=PromptTokensDetailsWrapper(text_tokens=9033, audio_tokens=14999, video_tokens=792000), + completion_tokens_details=CompletionTokensDetailsWrapper(text_tokens=4559), + ) + + with patch( + "litellm.litellm_core_utils.llm_cost_calc.utils.get_model_info", + return_value=mock_model_info, + ): + prompt_cost, completion_cost = generic_cost_per_token( + model="test-model", usage=usage, custom_llm_provider="vertex_ai" + ) + + assert round(prompt_cost, 9) == round(816032 * 4e-6, 9) + assert round(completion_cost, 9) == round(4559 * 1.8e-5, 9) + + +def test_prompt_modality_rates_still_win_over_tiered_input_rate(): + """An explicit input_cost_per_audio_token / input_cost_per_video_token beats the fallback, even above 200k.""" + from unittest.mock import patch + + mock_model_info = { + "input_cost_per_token": 2e-6, + "input_cost_per_token_above_200k_tokens": 4e-6, + "input_cost_per_audio_token": 3e-6, + "input_cost_per_video_token": 1e-6, + "output_cost_per_token": 1.2e-5, + } + + usage = Usage( + prompt_tokens=300000, + completion_tokens=10, + total_tokens=300010, + prompt_tokens_details=PromptTokensDetailsWrapper(text_tokens=100000, audio_tokens=100000, video_tokens=100000), + completion_tokens_details=CompletionTokensDetailsWrapper(text_tokens=10), + ) + + with patch( + "litellm.litellm_core_utils.llm_cost_calc.utils.get_model_info", + return_value=mock_model_info, + ): + prompt_cost, _ = generic_cost_per_token(model="test-model", usage=usage, custom_llm_provider="vertex_ai") + + assert round(prompt_cost, 9) == round(100000 * 4e-6 + 100000 * 3e-6 + 100000 * 1e-6, 9) + + def test_generic_cost_per_token_above_200k_tokens(_local_model_cost_map): # gemini-2.5-pro-exp-03-25 was removed; gemini-2.5-pro has same above-200k pricing model = "gemini-2.5-pro" From 811cecdc3b62235348f6c170a36c27947812bb5e Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Mon, 19 Oct 2026 16:26:41 -0700 Subject: [PATCH 27/66] fix(anthropic): apply tool_config cache-control points on chat and /v1/messages (#47394) * fix(anthropic): apply tool_config cache-control points on chat and /v1/messages A cache_control_injection_points entry with location tool_config was spread into the Anthropic request body on /v1/chat/completions, which Anthropic rejected with 400 Extra inputs are not permitted, and the native /v1/messages path dropped the point silently. Both paths now put the point's control on the last tool Anthropic caches and never forward the key. Co-authored-by: Tan Nguyen * refactor(anthropic): validate tool_config inputs instead of casting them Keeps the lint gates flat: the helper takes untyped tools and points and narrows them with the existing object validators, the chat transform builds the body with the marked tools instead of writing into optional_params, and the handler reads a typed view of kwargs. * fix(openai): keep tool_config cache points out of extra_body, add integration test The cache hook hands a tool_config point on for the provider step, and for providers that call through the OpenAI SDK every non-OpenAI param rides in extra_body, so OpenAI answered 400 Unrecognized request argument supplied. The new integration file drives a live proxy against scripted Anthropic, Bedrock Converse and OpenAI upstreams for /v1/chat/completions and /v1/messages. * test(integration): cover tool_config cache points on bridged /v1/messages Three new cases on /v1/messages for models without a native Anthropic messages path: OpenAI through the Responses bridge and Gemini through the chat bridge never see cache_control_injection_points in the body, and Bedrock Nova through the chat bridge gets the cachePoint on toolConfig --------- Backport of #47394 to stable/1.104.x Cherry-picked from 93b79d2587d186fb7266556a34a22d03f187a3da (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Tan Nguyen --- litellm/llms/anthropic/chat/transformation.py | 15 ++++ litellm/llms/anthropic/common_utils.py | 43 ++++++++- .../messages/handler.py | 10 ++- .../anthropic_cache_control_hook.py | 2 +- litellm/utils.py | 5 +- .../test_anthropic_chat_transformation.py | 90 ++++++++++++++++++- ...erimental_pass_through_messages_handler.py | 49 +++++++++- tests/unit/test_utils.py | 31 +++++-- 8 files changed, 230 insertions(+), 15 deletions(-) diff --git a/litellm/llms/anthropic/chat/transformation.py b/litellm/llms/anthropic/chat/transformation.py index 3bffee48d6a..c641ebecdb4 100644 --- a/litellm/llms/anthropic/chat/transformation.py +++ b/litellm/llms/anthropic/chat/transformation.py @@ -103,6 +103,7 @@ from ..common_utils import ( process_anthropic_headers, requires_native_compaction_beta, strip_advisor_blocks_from_messages, + tools_marked_for_a_tool_config_point, ) if TYPE_CHECKING: @@ -2056,6 +2057,19 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig): # Remove internal LiteLLM parameters that should not be sent to Anthropic API optional_params.pop("is_vertex_request", None) optional_params.pop("client_metadata", None) + request_params: Final = cast( # cast-ok: optional_params is the untyped dict of the shared transform signature + dict[str, object], optional_params + ) + marked_tools: Final = tools_marked_for_a_tool_config_point( + request_params.get("tools"), request_params.pop("cache_control_injection_points", None) + ) + if marked_tools is not None: + from litellm.integrations.anthropic_cache_control_hook import AnthropicCacheControlHook + + request_litellm_params: Final = cast( # cast-ok: litellm_params is the untyped dict of the shared signature + Mapping[str, object], litellm_params + ) + AnthropicCacheControlHook.record_gateway_injection(request_litellm_params, 1) # ``top_k`` is a provider-specific kwarg that bypasses # ``map_openai_params``; gate it here, the single boundary shared by @@ -2075,6 +2089,7 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig): "model": model, "messages": anthropic_messages, **optional_params, + **({} if marked_tools is None else {"tools": list(marked_tools)}), } self._apply_output_config(data=data, model=model, optional_params=optional_params) diff --git a/litellm/llms/anthropic/common_utils.py b/litellm/llms/anthropic/common_utils.py index bf2d588dd3a..68439e5a12c 100644 --- a/litellm/llms/anthropic/common_utils.py +++ b/litellm/llms/anthropic/common_utils.py @@ -33,6 +33,7 @@ from litellm.types.llms.anthropic import ( ANTHROPIC_HOSTED_TOOLS, ANTHROPIC_OAUTH_BETA_HEADER, ANTHROPIC_OAUTH_TOKEN_PREFIX, + ANTHROPIC_TOOL_SEARCH_TOOL_TYPES, AllAnthropicToolsValues, AnthropicMcpServerTool, AnthropicMessagesToolChoice, @@ -73,7 +74,7 @@ _DATED_RELEASE_SUFFIX_RE: Final = re.compile(r"-\d{8}$") _DOTTED_VERSION_RE: Final = re.compile(r"(\d)\.(\d)") _CLAUDE_CODE_BILLING_HEADER_PREFIX: Final = "x-anthropic-billing-header:" _CLAUDE_CODE_OBJECT_MAPPING_ADAPTER: Final = TypeAdapter(dict[object, object]) -_CLAUDE_CODE_OBJECT_LIST_ADAPTER: Final = TypeAdapter(list[object]) +OBJECT_LIST_ADAPTER: Final = TypeAdapter(list[object]) _CLAUDE_CODE_USER_AGENT_PREFIXES: Final = ("claude-cli/", "claude-code/") @@ -115,6 +116,40 @@ def supports_anthropic_cache_control(model: str, custom_llm_provider: str | None ) +def _tool_config_point_control(points: object) -> Mapping[object, object] | None: + point_fields: Final = tuple(_validated_claude_code_mapping(point) for point in validated_object_list(points) or ()) + tool_config_point: Final = next( + (fields for fields in point_fields if fields is not None and fields.get("location") == "tool_config"), None + ) + if tool_config_point is None: + return None + control: Final = tool_config_point.get("control") + return {"type": "ephemeral"} if control is None else _validated_claude_code_mapping(control) + + +def tools_marked_for_a_tool_config_point(tools: object, points: object) -> tuple[object, ...] | None: + """Put the ``tool_config`` point's breakpoint on the last tool Anthropic caches. + + Anthropic caches tools as one prefix ending at the marked tool, so the last one carries + the mark, skipping tool-search tools whose transform drops cache markers. A client that + already marked a tool keeps its own breakpoint. Returns ``None`` when nothing is marked. + """ + control: Final = _tool_config_point_control(points) + tool_list: Final = validated_object_list(tools) or () + tool_fields: Final = tuple(_validated_claude_code_mapping(tool) for tool in tool_list) + if control is None or any(fields is not None and "cache_control" in fields for fields in tool_fields): + return None + cacheable: Final = tuple( + (position, fields) + for position, fields in enumerate(tool_fields) + if fields is not None and fields.get("type") not in ANTHROPIC_TOOL_SEARCH_TOOL_TYPES + ) + if not cacheable: + return None + position, fields = cacheable[-1] + return (*tool_list[:position], {**fields, "cache_control": control}, *tool_list[position + 1 :]) + + def is_claude_code_user_agent(user_agent: str) -> bool: """Claude Code sends its API calls through the Anthropic SDK as `claude-cli/` and its own fetches, such as gateway model discovery, as `claude-code/`""" @@ -128,9 +163,9 @@ def _validated_claude_code_mapping(value: object) -> dict[object, object] | None return None -def _validated_claude_code_list(value: object) -> list[object] | None: +def validated_object_list(value: object) -> Sequence[object] | None: try: - return _CLAUDE_CODE_OBJECT_LIST_ADAPTER.validate_python(value) + return OBJECT_LIST_ADAPTER.validate_python(value) except ValidationError: return None @@ -157,7 +192,7 @@ def _claude_code_billing_fields(text: str) -> tuple[tuple[str, str], ...] | None def _claude_code_billing_texts(system: object) -> tuple[str, ...] | None: if isinstance(system, str): return (system,) - blocks: Final = _validated_claude_code_list(system) + blocks: Final = validated_object_list(system) if blocks is None: return None block_mappings: Final = tuple(_validated_claude_code_mapping(block) for block in blocks) diff --git a/litellm/llms/anthropic/experimental_pass_through/messages/handler.py b/litellm/llms/anthropic/experimental_pass_through/messages/handler.py index ac4240690c1..cd0e1dcd8a5 100644 --- a/litellm/llms/anthropic/experimental_pass_through/messages/handler.py +++ b/litellm/llms/anthropic/experimental_pass_through/messages/handler.py @@ -12,6 +12,7 @@ from functools import partial from typing import Any, Final, cast import litellm +from litellm.integrations.anthropic_cache_control_hook import AnthropicCacheControlHook from litellm.litellm_core_utils.exception_mapping_utils import exception_type from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj from litellm.llms.anthropic.common_utils import ( @@ -19,6 +20,7 @@ from litellm.llms.anthropic.common_utils import ( sanitize_tool_use_ids_in_anthropic_messages, strip_empty_content_blocks_from_anthropic_messages, strip_provider_specific_fields_from_anthropic_messages, + tools_marked_for_a_tool_config_point, ) from litellm.llms.base_llm.anthropic_messages.transformation import ( BaseAnthropicMessagesConfig, @@ -636,7 +638,13 @@ def anthropic_messages_handler( f"custom_llm_provider is required for Anthropic messages, passed in model={model}, custom_llm_provider={custom_llm_provider}" ) - local_vars.update(kwargs) + request_kwargs: Final = cast(dict[str, object], kwargs) # cast-ok: **kwargs of the handler is untyped + marked_tools: Final = tools_marked_for_a_tool_config_point( + local_vars.get("tools"), request_kwargs.pop("cache_control_injection_points", None) + ) + if marked_tools is not None: + AnthropicCacheControlHook.record_gateway_injection(request_kwargs, 1) + local_vars.update({**request_kwargs, **({"tools": list(marked_tools)} if marked_tools is not None else {})}) anthropic_messages_optional_request_params: Final = ( AnthropicMessagesRequestUtils.get_requested_anthropic_messages_optional_param( params=local_vars, diff --git a/litellm/types/integrations/anthropic_cache_control_hook.py b/litellm/types/integrations/anthropic_cache_control_hook.py index 20e7885a2bf..7f55612f2c7 100644 --- a/litellm/types/integrations/anthropic_cache_control_hook.py +++ b/litellm/types/integrations/anthropic_cache_control_hook.py @@ -22,7 +22,7 @@ class CacheControlMessageInjectionPoint(TypedDict): class CacheControlToolConfigInjectionPoint(TypedDict): - """Type for tool_config-level injection points (Bedrock).""" + """Type for tool_config-level injection points (Anthropic and Bedrock).""" location: Literal["tool_config"] control: ChatCompletionCachedContent | None diff --git a/litellm/utils.py b/litellm/utils.py index f6d775d1248..0fe759cf0c8 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -5027,6 +5027,9 @@ def get_optional_params( EXTRA_BODY_ROUTING_KEYS: Final = frozenset({"model"}) +LITELLM_ONLY_PARAMS: Final = frozenset(("cache_control_injection_points",)) + + def add_provider_specific_params_to_optional_params( optional_params: dict, passed_params: dict, @@ -5043,7 +5046,7 @@ def add_provider_specific_params_to_optional_params( if _should_drop_param(k="extra_body", additional_drop_params=additional_drop_params) is False: extra_body: Final = dict(passed_params.pop("extra_body", None) or {}) for k in passed_params: - if k not in openai_params and passed_params[k] is not None: + if k not in openai_params and k not in LITELLM_ONLY_PARAMS and passed_params[k] is not None: extra_body[k] = passed_params[k] if not isinstance(optional_params.get("extra_body"), dict): optional_params["extra_body"] = {} diff --git a/tests/unit/llms/anthropic/chat/test_anthropic_chat_transformation.py b/tests/unit/llms/anthropic/chat/test_anthropic_chat_transformation.py index 729f46ec57f..f2a7c4f44c2 100644 --- a/tests/unit/llms/anthropic/chat/test_anthropic_chat_transformation.py +++ b/tests/unit/llms/anthropic/chat/test_anthropic_chat_transformation.py @@ -29,7 +29,7 @@ from litellm.llms.bedrock.chat.invoke_transformations.anthropic_claude3_transfor from litellm.llms.vertex_ai.vertex_ai_partner_models.anthropic.transformation import ( VertexAIAnthropicConfig, ) -from litellm.types.llms.anthropic import ANTHROPIC_BETA_HEADER_VALUES +from litellm.types.llms.anthropic import ANTHROPIC_BETA_HEADER_VALUES, ANTHROPIC_TOOL_SEARCH_TOOL_TYPES from litellm.types.utils import ServerToolUse, Usage @@ -6798,3 +6798,91 @@ def test_chat_dummy_tool_result_for_an_orphaned_tool_call_replays_a_byte_identic _assert_prefix_stable(requests) assert [m["role"] for m in requests[0]["messages"]] == ["user", "assistant", "user"] assert requests[0]["messages"][2]["content"][0]["type"] == "tool_result" + + +def _make_transform_request(optional_params: dict, litellm_params: dict) -> dict: + return AnthropicConfig().transform_request( + model="claude-3-5-sonnet-20241022", + messages=[{"role": "user", "content": "hi"}], + optional_params=optional_params, + litellm_params=litellm_params, + headers={}, + ) + + +def _two_function_tools() -> list[dict]: + return [ + { + "type": "function", + "function": {"name": f"tool_{i}", "description": f"Tool {i}", "parameters": {"type": "object"}}, + } + for i in range(2) + ] + + +@pytest.mark.parametrize( + "control, expected_control", + [ + (None, {"type": "ephemeral"}), + ({"type": "ephemeral", "ttl": "1h"}, {"type": "ephemeral", "ttl": "1h"}), + ], +) +def test_transform_request_tool_config_point_marks_last_tool_and_drops_the_key(control, expected_control): + """LIT-9880: a tool_config injection point used to be spread into the Anthropic body, which + Anthropic rejected with 400 Extra inputs are not permitted.""" + tools = _two_function_tools() + tools_before = copy.deepcopy(tools) + point = {"location": "tool_config", **({"control": control} if control is not None else {})} + litellm_params = {"metadata": {}, "model_info": {"id": "deployment-1"}} + + data = _make_transform_request( + optional_params={"tools": tools, "cache_control_injection_points": [point]}, + litellm_params=litellm_params, + ) + + assert "cache_control_injection_points" not in data + assert data["tools"][-1]["cache_control"] == expected_control + assert "cache_control" not in data["tools"][0] + assert tools == tools_before + assert litellm_params["metadata"]["litellm_gateway_injected_cache"] == "deployment-1" + + +def test_transform_request_tool_config_point_keeps_the_clients_tool_marker(): + tools = _two_function_tools() + tools[0]["cache_control"] = {"type": "ephemeral"} + + data = _make_transform_request( + optional_params={"tools": tools, "cache_control_injection_points": [{"location": "tool_config"}]}, + litellm_params={}, + ) + + assert "cache_control_injection_points" not in data + assert data["tools"][0]["cache_control"] == {"type": "ephemeral"} + assert "cache_control" not in data["tools"][1] + + +def test_transform_request_tool_config_point_skips_tool_search_tools(): + tool_search_type = next(iter(ANTHROPIC_TOOL_SEARCH_TOOL_TYPES)) + tools = [*_two_function_tools(), {"type": tool_search_type, "name": "tool_search"}] + + data = _make_transform_request( + optional_params={"tools": tools, "cache_control_injection_points": [{"location": "tool_config"}]}, + litellm_params={}, + ) + + assert data["tools"][1]["cache_control"] == {"type": "ephemeral"} + assert "cache_control" not in data["tools"][2] + assert "cache_control" not in data["tools"][0] + + +def test_transform_request_tool_config_point_without_tools_drops_the_key(): + litellm_params = {"metadata": {}} + + data = _make_transform_request( + optional_params={"cache_control_injection_points": [{"location": "tool_config"}]}, + litellm_params=litellm_params, + ) + + assert "cache_control_injection_points" not in data + assert "tools" not in data + assert litellm_params["metadata"] == {} diff --git a/tests/unit/llms/anthropic/experimental_pass_through/messages/test_anthropic_experimental_pass_through_messages_handler.py b/tests/unit/llms/anthropic/experimental_pass_through/messages/test_anthropic_experimental_pass_through_messages_handler.py index 507467b721f..c1287fa4c17 100644 --- a/tests/unit/llms/anthropic/experimental_pass_through/messages/test_anthropic_experimental_pass_through_messages_handler.py +++ b/tests/unit/llms/anthropic/experimental_pass_through/messages/test_anthropic_experimental_pass_through_messages_handler.py @@ -1,4 +1,5 @@ import asyncio +import copy import json import os import uuid @@ -1480,6 +1481,7 @@ async def test_provider_messages_api_base_env_is_not_shadowed_by_the_chat_defaul assert seen_urls == ["https://deepseek.internal.example/anthropic/v1/messages"] + @pytest.mark.asyncio async def test_anthropic_messages_forwards_safeguards_and_unknown_beta_to_anthropic(): """Shapes are what Claude Code 2.1.278 sends and api.anthropic.com returns, captured 2026-09-21.""" @@ -1594,7 +1596,9 @@ def _claude_code_auto_mode_request() -> tuple[list[dict[str, object]], list[dict return safeguards, safeguard_results -def _upstream_answering_with(safeguard_results: list[dict[str, object]], captured: dict[str, object]) -> AsyncHTTPHandler: +def _upstream_answering_with( + safeguard_results: list[dict[str, object]], captured: dict[str, object] +) -> AsyncHTTPHandler: def upstream_records_the_request(request: httpx.Request) -> httpx.Response: captured["body"] = json.loads(request.content) captured["anthropic-beta"] = request.headers.get("anthropic-beta") @@ -1620,7 +1624,9 @@ def _upstream_answering_with(safeguard_results: list[dict[str, object]], capture _CLIENT_BETA_HEADERS: Final = ( - pytest.param({"anthropic-beta": "dangerous-tool-use-2026-09-03,interleaved-thinking-2025-05-14"}, id="client_sends_beta"), + pytest.param( + {"anthropic-beta": "dangerous-tool-use-2026-09-03,interleaved-thinking-2025-05-14"}, id="client_sends_beta" + ), pytest.param({"anthropic-beta": "interleaved-thinking-2025-05-14"}, id="client_omits_beta"), pytest.param({}, id="client_sends_no_beta_header"), ) @@ -1685,3 +1691,42 @@ async def test_anthropic_messages_forwards_safeguards_and_dangerous_tool_use_bet assert "anthropic_beta" not in captured["body"] assert captured["anthropic-beta"].split(",").count("dangerous-tool-use-2026-09-03") == 1 assert response["safeguard_results"] == safeguard_results + + +def test_native_messages_tool_config_point_marks_last_tool_and_drops_the_key(monkeypatch): + """LIT-9880 on /v1/messages: the hook wrote the tool_config point back into kwargs and the + native path dropped it silently, so the tools went out without any cache breakpoint.""" + from litellm.llms.anthropic.experimental_pass_through.messages import handler + + captured = {} + + def fake_native(**kwargs): + captured["params"] = kwargs["anthropic_messages_optional_request_params"] + captured["kwargs"] = kwargs["kwargs"] + captured["messages"] = kwargs["messages"] + return "native-passthrough" + + monkeypatch.setattr(handler.base_llm_http_handler, "anthropic_messages_handler", fake_native) + tools = [{"name": f"tool_{i}", "description": f"Tool {i}", "input_schema": {"type": "object"}} for i in range(2)] + tools_before = copy.deepcopy(tools) + + result = handler.anthropic_messages_handler( + max_tokens=100, + messages=[{"role": "user", "content": "Hello"}], + model="anthropic/claude-opus-4-6", + api_key="sk-test", + tools=tools, + litellm_metadata={}, + cache_control_injection_points=[ + {"location": "message", "role": "user"}, + {"location": "tool_config", "control": {"type": "ephemeral", "ttl": "1h"}}, + ], + ) + + assert result == "native-passthrough" + assert "cache_control_injection_points" not in captured["params"] + assert "cache_control_injection_points" not in captured["kwargs"] + assert captured["params"]["tools"][-1]["cache_control"] == {"type": "ephemeral", "ttl": "1h"} + assert "cache_control" not in captured["params"]["tools"][0] + assert captured["messages"][0]["content"][-1]["cache_control"] == {"type": "ephemeral"} + assert tools == tools_before diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py index e80ca2a5820..fd254dc2c3f 100644 --- a/tests/unit/test_utils.py +++ b/tests/unit/test_utils.py @@ -3134,9 +3134,7 @@ class TestExtraBodyCannotOverrideModel: } ] - untouched = litellm.get_optional_params( - model="my-vllm-model", custom_llm_provider="hosted_vllm", tools=tools() - ) + untouched = litellm.get_optional_params(model="my-vllm-model", custom_llm_provider="hosted_vllm", tools=tools()) assert untouched["tools"][0]["function"]["custom_marker"] == "LEAK", untouched result = litellm.get_optional_params( @@ -4516,7 +4514,13 @@ _SUCCESS_RESPONSES_BY_CALL_TYPE: Final = ( pytest.param(EmbeddingResponse(model="text-embedding-3-small"), CallTypes.aembedding, id="embedding"), pytest.param( ResponsesAPIResponse( - id="resp_abc", created_at=1, output=[], parallel_tool_calls=False, tool_choice="auto", tools=[], model="gpt-5.6" + id="resp_abc", + created_at=1, + output=[], + parallel_tool_calls=False, + tool_choice="auto", + tools=[], + model="gpt-5.6", ), CallTypes.aresponses, id="responses", @@ -4544,7 +4548,9 @@ async def test_success_deployment_hook_raising_keeps_response_and_runs_later_hoo assert result is response assert second_hook.seen_responses == (response,) - failure_logs: Final = tuple(r for r in caplog.records if "async_post_call_success_deployment_hook error" in r.message) + failure_logs: Final = tuple( + r for r in caplog.records if "async_post_call_success_deployment_hook error" in r.message + ) assert len(failure_logs) == 1 assert "_ChatShapedSuccessDeploymentHook" in failure_logs[0].message assert str(call_type) in failure_logs[0].message @@ -6353,3 +6359,18 @@ def test_function_setup_never_logs_the_ocr_data_uri_payload() -> None: assert logged == [{"role": "user", "content": f"data:application/pdf;base64 ({len(payload)} chars)"}] assert payload not in str(logged) + + +def test_get_optional_params_keeps_a_tool_config_cache_point_out_of_the_openai_extra_body(): + """LIT-9880: the hook hands a tool_config point on for the provider step, and OpenAI has no + step that consumes it, so it must not ride along in extra_body and 400 at OpenAI.""" + optional_params = litellm.utils.get_optional_params( + model="gpt-4.1", + custom_llm_provider="openai", + tools=[{"type": "function", "function": {"name": "get_weather", "parameters": {"type": "object"}}}], + cache_control_injection_points=[{"location": "tool_config", "control": {"type": "ephemeral"}}], + extra_body={"kept": True}, + ) + + assert optional_params["extra_body"] == {"kept": True} + assert "cache_control_injection_points" not in optional_params From ee8a1a5abd7c55d8e9fc9c59275301b99024ced9 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Mon, 19 Oct 2026 16:55:13 -0700 Subject: [PATCH 28/66] fix(proxy): price the estimated input tokens on a read-timed-out request's spend row (#47435) Backport of #47435 to stable/1.104.x Cherry-picked from 7b76b2b15fe6826e091e289a574b23c1e96fd627 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/proxy/utils.py | 60 ++++++++++- tests/test_litellm/proxy/test_proxy_utils.py | 107 +++++++++++++++++-- 2 files changed, 154 insertions(+), 13 deletions(-) diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py index b8cc30ad8a7..eb4704a0fa8 100644 --- a/litellm/proxy/utils.py +++ b/litellm/proxy/utils.py @@ -46,6 +46,7 @@ from typing import ( overload, ) +import httpx from typing_extensions import ReadOnly, TypedDict from litellm import _custom_logger_compatible_callbacks_literal @@ -939,12 +940,17 @@ def _failure_usage_to_lift( model_call_details: Mapping[str, object], request_body: Mapping[str, object], dispatched: bool, + provider_billed: bool = False, ) -> tuple[object, object] | None: """A stream that broke mid-flight still billed the provider for the chunks already delivered; the streaming handler stashes that recovered usage and cost in model_call_details, so prefer it. Otherwise a request that was dispatched to a provider and failed without upstream usage gets an - estimated input-side Usage with zero cost. The raw request body backfills + estimated input-side Usage. When the failure is one the provider bills + anyway (``provider_billed``: a read timeout, where the provider had the + prompt and kept working after LiteLLM hung up) that + usage is priced at the model's input rate; any other post-dispatch failure + stays at zero cost. The raw request body backfills the system prompt when the SDK bridges an endpoint (e.g. /v1/messages on a chat-completions provider) without filling optional_params. Returns the (combined_usage_object, response_cost) pair to lift, or None.""" @@ -969,7 +975,27 @@ def _failure_usage_to_lift( ) if estimated_usage is None: return None - return estimated_usage, 0.0 + if not provider_billed: + return estimated_usage, 0.0 + return estimated_usage, _estimated_input_cost(model_call_details, estimated_usage.prompt_tokens) + + +def _estimated_input_cost(model_call_details: Mapping[str, object], prompt_tokens: int) -> float: + """Input price for the estimated prompt at the cost map's rate; an unmapped model keeps the + row at $0 rather than dropping the failure row.""" + try: + model: Final = str(model_call_details.get("model") or "") + estimated_input_cost, _ = litellm.cost_per_token( + model=model, + custom_llm_provider=str(model_call_details.get("custom_llm_provider") or "") or None, + prompt_tokens=prompt_tokens, + ) + except Exception as exc: # noqa: BLE001 # cost_per_token raises BadRequestError for an unmapped model and the row must still be written + verbose_proxy_logger.debug( + "failure spend estimate: could not price %s: %s", model_call_details.get("model"), exc + ) + return 0.0 + return estimated_input_cost _EMPTY_LIFT: Final = MappingProxyType({}) @@ -1085,7 +1111,28 @@ def _call_type_for_route(route: str | None) -> str | None: _PROXY_ONLY_LLM_API_ERRORS: Final = (HTTPException, ProxyException, GuardrailRaisedException) -def _failure_fields_to_lift(request_data: Mapping[str, object]) -> Mapping[str, object]: +_EXCEPTION_CHAIN_MAX_DEPTH: Final = 16 + + +def _exception_chain(exception: BaseException) -> tuple[BaseException, ...]: + chain: Final[list[BaseException]] = [exception] # mutable-ok: built once, returned frozen + for _ in range(_EXCEPTION_CHAIN_MAX_DEPTH): + following = chain[-1].__cause__ or chain[-1].__context__ + if following is None or following in chain: + break + chain.append(following) + return tuple(chain) + + +def _timed_out_reading_from_provider(exception: Exception) -> bool: + """A read timeout means the request was sent and the provider was working on it; a connect + timeout (``httpx.ConnectTimeout``) never reached the provider, so it is not billed.""" + return isinstance(exception, litellm.Timeout) and any( + isinstance(cause, httpx.ReadTimeout) for cause in _exception_chain(exception) + ) + + +def _failure_fields_to_lift(request_data: Mapping[str, object], provider_billed: bool = False) -> Mapping[str, object]: """Failure-path callbacks run after ``litellm_logging_obj`` is popped from request_data (it is not serialisable), so the caller merges these fields onto request_data first: the request start and first-handoff instants for @@ -1101,6 +1148,7 @@ def _failure_fields_to_lift(request_data: Mapping[str, object]) -> Mapping[str, model_call_details=_model_call_details, request_body=request_data, dispatched=_first_handoff is not None, + provider_billed=provider_billed, ) _entries: Final = ( ("start_time", _model_call_details.get("start_time")), @@ -3252,7 +3300,11 @@ class ProxyLogging: original_exception=original_exception, ) - request_data.update(await offload_token_count(_failure_fields_to_lift)(request_data)) + request_data.update( + await offload_token_count(_failure_fields_to_lift)( + request_data, provider_billed=_timed_out_reading_from_provider(original_exception) + ) + ) # Remove before callbacks iterate — not serialisable request_data.pop("litellm_logging_obj", None) diff --git a/tests/test_litellm/proxy/test_proxy_utils.py b/tests/test_litellm/proxy/test_proxy_utils.py index ea1870d3b73..6a597f4ee12 100644 --- a/tests/test_litellm/proxy/test_proxy_utils.py +++ b/tests/test_litellm/proxy/test_proxy_utils.py @@ -2,6 +2,7 @@ import datetime as real_datetime import smtplib from typing import Final +import httpx import pytest from fastapi import HTTPException @@ -687,11 +688,13 @@ class TestPostCallFailureHookEstimatesDispatchedInputTokens: """A non-stream request that failed after dispatch (timeout, provider error) consumed provider-billed input tokens but recovered no usage. post_call_failure_hook must estimate the input side onto request_data so - the spend log's failure row records what was sent instead of zero, while - never charging spend for the failure (LIT-5690). + the spend log's failure row records what was sent instead of zero + (LIT-5690). On a timeout that estimate is priced at the model's input + rate since the provider bills the prompt it accepted (LIT-145); other + post-dispatch failures keep zero spend. """ - async def _run(self, request_data): + async def _run(self, request_data, original_exception: Exception | None = None): from unittest.mock import AsyncMock, patch from litellm.proxy._types import UserAPIKeyAuth @@ -701,17 +704,81 @@ class TestPostCallFailureHookEstimatesDispatchedInputTokens: with patch.object(proxy_logging_obj, "update_request_status", new=AsyncMock()): await proxy_logging_obj.post_call_failure_hook( request_data=request_data, - original_exception=Exception("boom"), + original_exception=original_exception or Exception("boom"), user_api_key_dict=UserAPIKeyAuth(), ) + def _timeout(self, model: str, cause: Exception) -> Exception: + try: + try: + raise cause + except Exception as inner: + raise litellm.Timeout("Request timed out.", model=model, llm_provider="openai") from inner + except litellm.Timeout as timed_out: + return timed_out + def _logging_obj(self, model_call_details): logging_obj = MagicMock() logging_obj.model_call_details = model_call_details return logging_obj @pytest.mark.asyncio - async def test_dispatched_failure_estimates_input_tokens_with_zero_cost(self): + async def test_timed_out_request_estimates_input_tokens_priced_at_input_rate(self): + from datetime import datetime + + from litellm.types.utils import Usage + + request_data = { + "litellm_logging_obj": self._logging_obj( + { + "first_api_call_start_time": datetime.now(), + "model": "gpt-3.5-turbo", + "messages": [{"role": "user", "content": "count these input tokens please"}], + "call_type": "acompletion", + } + ), + "metadata": {}, + "response_cost": 123.0, + } + await self._run( + request_data, original_exception=self._timeout("gpt-3.5-turbo", httpx.ReadTimeout("no bytes in time")) + ) + + estimated = request_data["combined_usage_object"] + assert isinstance(estimated, Usage) + assert estimated.prompt_tokens > 0 + assert estimated.completion_tokens == 0 + assert estimated.total_tokens == estimated.prompt_tokens + expected_input_cost, _ = litellm.cost_per_token(model="gpt-3.5-turbo", prompt_tokens=estimated.prompt_tokens) + assert expected_input_cost > 0 + assert request_data["response_cost"] == pytest.approx(expected_input_cost) + + @pytest.mark.asyncio + async def test_connect_timeout_never_reached_the_provider_stays_zero_cost(self): + from datetime import datetime + + from litellm.types.utils import Usage + + request_data = { + "litellm_logging_obj": self._logging_obj( + { + "first_api_call_start_time": datetime.now(), + "model": "gpt-3.5-turbo", + "messages": [{"role": "user", "content": "count these input tokens please"}], + "call_type": "acompletion", + } + ), + "metadata": {}, + } + await self._run( + request_data, original_exception=self._timeout("gpt-3.5-turbo", httpx.ConnectTimeout("no route")) + ) + + assert isinstance(request_data["combined_usage_object"], Usage) + assert request_data["response_cost"] == 0.0 + + @pytest.mark.asyncio + async def test_dispatched_non_timeout_failure_estimates_input_tokens_with_zero_cost(self): from datetime import datetime from litellm.types.utils import Usage @@ -733,8 +800,6 @@ class TestPostCallFailureHookEstimatesDispatchedInputTokens: estimated = request_data["combined_usage_object"] assert isinstance(estimated, Usage) assert estimated.prompt_tokens > 0 - assert estimated.completion_tokens == 0 - assert estimated.total_tokens == estimated.prompt_tokens assert request_data["response_cost"] == 0.0 @pytest.mark.asyncio @@ -1901,7 +1966,28 @@ def test_usage_the_stream_already_recovered_beats_an_estimate(): assert lifted == (recovered, 0.25) -def test_a_request_that_reached_a_provider_bills_its_input_at_no_cost(): +def test_a_timed_out_request_on_an_unmapped_model_keeps_its_row_at_zero_cost(): + from litellm.proxy.utils import _failure_usage_to_lift + + lifted = _failure_usage_to_lift( + model_call_details={ + "call_type": "acompletion", + "model": "my-unmapped-model", + "custom_llm_provider": "openai", + "messages": ONE_USER_MESSAGE, + }, + request_body={}, + dispatched=True, + provider_billed=True, + ) + + assert lifted is not None + usage, response_cost = lifted + assert usage.prompt_tokens > 0 + assert response_cost == 0.0 + + +def test_a_request_that_timed_out_at_a_provider_bills_its_input_at_the_input_rate(): from litellm.proxy.utils import _failure_usage_to_lift lifted = _failure_usage_to_lift( @@ -1912,13 +1998,16 @@ def test_a_request_that_reached_a_provider_bills_its_input_at_no_cost(): }, request_body={}, dispatched=True, + provider_billed=True, ) assert lifted is not None usage, response_cost = lifted assert usage.prompt_tokens > 0 assert usage.completion_tokens == 0 - assert response_cost == 0.0 + expected_input_cost, _ = litellm.cost_per_token(model=FAILURE_USAGE_MODEL, prompt_tokens=usage.prompt_tokens) + assert expected_input_cost > 0 + assert response_cost == pytest.approx(expected_input_cost) @pytest.mark.parametrize( From 744f63b8dbde33897d7cb20ed6e1381daebe1322 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Mon, 19 Oct 2026 17:59:53 -0700 Subject: [PATCH 29/66] fix(logging): do not stamp a provider handoff when pre_call runs for a proxy-only failure (#47456) Backport of #47456 to stable/1.104.x Cherry-picked from 3fa1587f4367fad5706d58545c47f413a9dea8b8 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/litellm_core_utils/litellm_logging.py | 24 +++++++---- tests/test_litellm/proxy/test_proxy_utils.py | 41 +++++++++++++++++++ .../test_litellm_logging.py | 16 +++++++- 3 files changed, 71 insertions(+), 10 deletions(-) diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py index f601503824d..efa6fd5f1e8 100644 --- a/litellm/litellm_core_utils/litellm_logging.py +++ b/litellm/litellm_core_utils/litellm_logging.py @@ -42,6 +42,7 @@ from litellm.constants import ( DEFAULT_MOCK_RESPONSE_COMPLETION_TOKEN_COUNT, DEFAULT_MOCK_RESPONSE_PROMPT_TOKEN_COUNT, EMPTY_MAPPING, + LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL, PROVIDER_REQUEST_ID_HEADERS, SENTRY_DENYLIST, SENTRY_PII_DENYLIST, @@ -1401,15 +1402,20 @@ class Logging(LiteLLMLoggingBaseClass): "LiteLLM.LoggingError: [Non-Blocking] Exception occurred while logging %s", e ) - self.model_call_details["api_call_start_time"] = datetime.datetime.now() - # Set-once first provider-handoff instant. api_call_start_time - # is overwritten on every retry, so it can't measure one-time - # preprocessing; pinning the first attempt excludes retry loops - # + backoff. Logging object only — must NOT go into - # litellm_params["metadata"] (caller request metadata, typed - # Dict[str, str], echoed downstream; a datetime breaks it). - if self.model_call_details.get("first_api_call_start_time") is None: - self.model_call_details["first_api_call_start_time"] = self.model_call_details["api_call_start_time"] + # A proxy-gate failure (auth, rate limit, client disconnect) fires pre_call for its callbacks + # without any provider handoff, so it must not stamp the handoff instants. + if LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL not in self.model_call_details: + self.model_call_details["api_call_start_time"] = datetime.datetime.now() + # Set-once first provider-handoff instant. api_call_start_time + # is overwritten on every retry, so it can't measure one-time + # preprocessing; pinning the first attempt excludes retry loops + # + backoff. Logging object only — must NOT go into + # litellm_params["metadata"] (caller request metadata, typed + # Dict[str, str], echoed downstream; a datetime breaks it). + if self.model_call_details.get("first_api_call_start_time") is None: + self.model_call_details["first_api_call_start_time"] = self.model_call_details[ + "api_call_start_time" + ] # Input Integration Logging -> If you want to log the fact that an attempt to call the model was made callbacks: Final = litellm.input_callback + (self.dynamic_input_callbacks or []) for callback in callbacks: diff --git a/tests/test_litellm/proxy/test_proxy_utils.py b/tests/test_litellm/proxy/test_proxy_utils.py index 6a597f4ee12..7a85dedf813 100644 --- a/tests/test_litellm/proxy/test_proxy_utils.py +++ b/tests/test_litellm/proxy/test_proxy_utils.py @@ -444,6 +444,47 @@ class TestPostCallFailureHookLiftsFirstApiCallStartTime: assert "litellm_logging_obj" not in request_data +class TestPostCallFailureHookDoesNotInventAProviderHandoff: + """A failure the proxy raised before any provider call (here an auth error) is logged through + _handle_logging_proxy_only_error, which fires pre_call for the callbacks. That must not stamp a + handoff instant onto the request, or every downstream reader (preprocessing latency, the + dispatched check behind the failure-row estimate) sees a provider call that never happened.""" + + @pytest.mark.asyncio + async def test_proxy_only_failure_lifts_no_first_api_call_start_time(self): + from datetime import datetime + from unittest.mock import AsyncMock, patch + + from litellm.litellm_core_utils.litellm_logging import Logging + from litellm.proxy._types import ProxyErrorTypes, UserAPIKeyAuth + + logging_obj = Logging( + model="gpt-4.1", + messages=[{"role": "user", "content": "hi"}], + stream=False, + call_type="acompletion", + start_time=datetime.now(), + litellm_call_id="pre-handoff-auth-failure", + function_id="pre-handoff", + ) + request_data: Final[dict[str, object]] = {"litellm_logging_obj": logging_obj, "model": "gpt-4.1", "metadata": {}} + proxy_logging_obj = ProxyLogging(user_api_key_cache=DualCache()) + proxy_logging_obj.alert_types = [] + with ( + patch.object(proxy_logging_obj, "update_request_status", new=AsyncMock()), + patch.object(proxy_logging_obj, "_dispatch_proxy_only_failure_handlers", new=AsyncMock()), + ): + await proxy_logging_obj.post_call_failure_hook( + request_data=request_data, + original_exception=Exception("Authentication Error, invalid key"), + user_api_key_dict=UserAPIKeyAuth(request_route="/v1/chat/completions"), + error_type=ProxyErrorTypes.auth_error, + ) + + assert request_data.get("first_api_call_start_time") is None + assert "api_call_start_time" not in logging_obj.model_call_details + + class TestPostCallFailureHookLiftsRecoveredPartialSpend: """A stream that broke mid-flight still billed the provider for the chunks already delivered. The streaming handler stashes that recovered usage and diff --git a/tests/unit/litellm_core_utils/test_litellm_logging.py b/tests/unit/litellm_core_utils/test_litellm_logging.py index d5aa0159b8d..10bc65201a1 100644 --- a/tests/unit/litellm_core_utils/test_litellm_logging.py +++ b/tests/unit/litellm_core_utils/test_litellm_logging.py @@ -20,7 +20,7 @@ from openai._legacy_response import HttpxBinaryResponseContent import litellm from litellm._logging import session_id_var, trace_id_var -from litellm.constants import SENTRY_DENYLIST, SENTRY_PII_DENYLIST +from litellm.constants import LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL, SENTRY_DENYLIST, SENTRY_PII_DENYLIST from litellm.cost_calculator import ocr_batch_cost from litellm.integrations.custom_logger import CustomLogger from litellm.litellm_core_utils.litellm_logging import Logging as LitellmLogging @@ -334,6 +334,20 @@ def test_get_masked_api_base(logging_obj): assert type(masked_api_base) == str +@pytest.mark.parametrize("no_upstream_call", [False, True]) +def test_pre_call_stamps_the_provider_handoff_only_when_a_provider_call_is_made(logging_obj, no_upstream_call): + """The proxy fires pre_call for a failure it raised itself (auth, rate limit, client disconnect) + so callbacks see it; that call never reached a provider, so neither handoff instant may be set.""" + logging_obj.update_environment_variables(litellm_params={}, optional_params={}) + if no_upstream_call: + logging_obj.model_call_details[LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL] = True + + logging_obj.pre_call(input="", api_key="") + + assert ("api_call_start_time" in logging_obj.model_call_details) is not no_upstream_call + assert (logging_obj.model_call_details.get("first_api_call_start_time") is not None) is not no_upstream_call + + def test_pre_call_tolerates_missing_api_base(logging_obj): """Presigned batch retrieves (Mistral, Bedrock) build their own URL and pass api_base=None to pre_call; masking must not raise or the request's pre-call logging is silently lost.""" From 96684a257066ef21e8b2a74e20fa4e353e0ca0c8 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Mon, 19 Oct 2026 18:17:29 -0700 Subject: [PATCH 30/66] fix(vertex_ai): bill per-character text embeddings on Google's billableCharacterCount (#47460) Vertex text embedding predict responses report metadata.billableCharacterCount, the unit Google bills text-embedding-005 and text-multilingual-embedding-002 on. Carry it into usage.prompt_tokens_details.character_count and, when the model carries input_cost_per_character, bill that count instead of the token count so the prompt is charged under one unit. Per-token embeddings (gemini-embedding-001) are unchanged. Backport of #47460 to stable/1.104.x Cherry-picked from d29200fa0511ae50f41b692de5922659a1f176c0 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../litellm_core_utils/llm_cost_calc/utils.py | 8 ++++- .../vertex_embeddings/transformation.py | 34 +++++++++++++++++-- .../llm_cost_calc/test_llm_cost_calc_utils.py | 25 ++++++++++++++ .../vertex_ai/vertex_embeddings/__init__.py | 0 .../test_embedding_handler.py | 30 ++++++++++++++++ 5 files changed, 93 insertions(+), 4 deletions(-) create mode 100644 tests/unit/llms/vertex_ai/vertex_embeddings/__init__.py create mode 100644 tests/unit/llms/vertex_ai/vertex_embeddings/test_embedding_handler.py diff --git a/litellm/litellm_core_utils/llm_cost_calc/utils.py b/litellm/litellm_core_utils/llm_cost_calc/utils.py index e65531121a6..35ebf68e7d1 100644 --- a/litellm/litellm_core_utils/llm_cost_calc/utils.py +++ b/litellm/litellm_core_utils/llm_cost_calc/utils.py @@ -1094,8 +1094,14 @@ def _calculate_input_cost( ) -> float: """ Calculates the input cost for a given model, prompt tokens, and completion tokens. + + A model priced per character (`input_cost_per_character`) bills the reported character count + in place of its text tokens, so the same prompt is never charged under both units. """ - prompt_cost = float(prompt_tokens_details["text_tokens"]) * prompt_base_cost + bills_characters: Final = ( + prompt_tokens_details["character_count"] > 0 and model_info.get("input_cost_per_character") is not None + ) + prompt_cost = 0.0 if bills_characters else float(prompt_tokens_details["text_tokens"]) * prompt_base_cost ### CACHE READ COST - Now uses tiered pricing cache_hit_audio_tokens: Final = prompt_tokens_details["cache_hit_audio_tokens"] diff --git a/litellm/llms/vertex_ai/vertex_embeddings/transformation.py b/litellm/llms/vertex_ai/vertex_embeddings/transformation.py index e4bbdd1bd0d..e4f7c513eb9 100644 --- a/litellm/llms/vertex_ai/vertex_embeddings/transformation.py +++ b/litellm/llms/vertex_ai/vertex_embeddings/transformation.py @@ -1,14 +1,34 @@ import types from typing import Final, Literal -from pydantic import BaseModel +from pydantic import BaseModel, TypeAdapter +from typing_extensions import ReadOnly, TypedDict from litellm.llms.vertex_ai.common_utils import pop_vertex_request_labels -from litellm.types.utils import EmbeddingResponse, Usage +from litellm.types.utils import EmbeddingResponse, PromptTokensDetailsWrapper, Usage from .types import * +class _PredictMetadata(TypedDict, total=False): + billableCharacterCount: ReadOnly[int] + + +class _PredictResponseMetadata(TypedDict, total=False): + metadata: ReadOnly[_PredictMetadata] + + +_PREDICT_RESPONSE_METADATA: Final = TypeAdapter(_PredictResponseMetadata) + + +def billable_character_count(response: _PredictResponseMetadata) -> int | None: + """ + `metadata.billableCharacterCount` of a Vertex text embedding predict response, the count Google + bills per-character embedding models (text-embedding-005, text-multilingual-embedding-002) on. + """ + return response.get("metadata", {}).get("billableCharacterCount") + + class VertexAITextEmbeddingConfig(BaseModel): """ Reference: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api#TextEmbeddingInput @@ -248,7 +268,15 @@ class VertexAITextEmbeddingConfig(BaseModel): model_response.object = "list" model_response.data = embedding_response model_response.model = model - usage: Final = Usage(prompt_tokens=input_tokens, completion_tokens=0, total_tokens=input_tokens) + billable_characters: Final = billable_character_count(_PREDICT_RESPONSE_METADATA.validate_python(response)) + usage: Final = Usage( + prompt_tokens=input_tokens, + completion_tokens=0, + total_tokens=input_tokens, + prompt_tokens_details=( + None if billable_characters is None else PromptTokensDetailsWrapper(character_count=billable_characters) + ), + ) setattr(model_response, "usage", usage) return model_response diff --git a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index 2b5dd50fdec..38bea4b2a76 100644 --- a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -99,6 +99,31 @@ def test_generic_cost_per_token_bills_cache_reads_at_input_rate_when_no_cache_re assert completion_cost == pytest.approx(380 * 9.7e-7) +@pytest.mark.parametrize( + ("model_info", "expected_prompt_cost"), + [ + ({"input_cost_per_token": 1e-7, "input_cost_per_character": 2.5e-8, "output_cost_per_token": 0.0}, 35 * 2.5e-8), + ({"input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0}, 11 * 1.5e-7), + ], + ids=["character_priced_model_bills_characters_instead_of_tokens", "token_priced_model_ignores_the_character_count"], +) +def test_generic_cost_per_token_bills_a_character_counted_prompt_under_one_unit( + model_info: ModelInfo, expected_prompt_cost: float +) -> None: + usage = Usage( + prompt_tokens=11, + completion_tokens=0, + total_tokens=11, + prompt_tokens_details=PromptTokensDetailsWrapper(character_count=35), + ) + + prompt_cost, completion_cost = generic_cost_per_token( + model="embedding-fixture", usage=usage, custom_llm_provider="vertex_ai", model_info=model_info + ) + + assert (prompt_cost, completion_cost) == (pytest.approx(expected_prompt_cost), 0.0) + + def test_apply_provider_cache_read_default_only_derives_a_rate_for_fireworks() -> None: openai_info: ModelInfo = {"input_cost_per_token": 2e-6} fireworks_info: ModelInfo = {"input_cost_per_token": 2e-6} diff --git a/tests/unit/llms/vertex_ai/vertex_embeddings/__init__.py b/tests/unit/llms/vertex_ai/vertex_embeddings/__init__.py new file mode 100644 index 00000000000..e69de29bb2d diff --git a/tests/unit/llms/vertex_ai/vertex_embeddings/test_embedding_handler.py b/tests/unit/llms/vertex_ai/vertex_embeddings/test_embedding_handler.py new file mode 100644 index 00000000000..cbc074b4e94 --- /dev/null +++ b/tests/unit/llms/vertex_ai/vertex_embeddings/test_embedding_handler.py @@ -0,0 +1,30 @@ +from typing import Final + +import pytest + +from litellm.llms.vertex_ai.vertex_embeddings.transformation import VertexAITextEmbeddingConfig +from litellm.types.utils import EmbeddingResponse + + +def _gecko_prediction(values: list[float], token_count: int) -> dict[str, object]: + return {"embeddings": {"values": values, "statistics": {"token_count": token_count, "truncated": False}}} + + +@pytest.mark.parametrize( + ("metadata", "character_count"), + [({"metadata": {"billableCharacterCount": 10}}, 10), ({}, None)], + ids=["billable_character_count_reported", "no_metadata"], +) +def test_vertex_embedding_usage_carries_the_billable_character_count_google_prices_on( + metadata: dict[str, object], character_count: int | None +) -> None: + payload: Final = {"predictions": [_gecko_prediction([0.1, 0.2, 0.3], 3), _gecko_prediction([1, 2.0, 3], 5)], **metadata} + + response: Final = VertexAITextEmbeddingConfig().transform_vertex_response_to_openai( + response=payload, model="text-embedding-005", model_response=EmbeddingResponse() + ) + + assert (response.usage.prompt_tokens, getattr(response.usage.prompt_tokens_details, "character_count", None)) == ( + 8, + character_count, + ) From 21a84f9e8f9b5cfc3ffbe5e880e8dae485a7e38a Mon Sep 17 00:00:00 2001 From: joshua-berri Date: Tue, 20 Oct 2026 16:08:57 -0700 Subject: [PATCH 31/66] fix(batch): preserve recoverable costs and prevent poll starvation (#47190) Backport of #47190 to stable/1.104.x. Cherry-picked from 0ede0e10e7ee694c46f14afd1606885d8c369342 (main). Ported by hand onto the line's poller (the ManagedObjectRow protocol is the line's local _ManagedObjectRow; _finalize_unbilled_terminal_job keeps the line's None return). Test conflicts take this PR's assertions; the line-item poller tests from main are not on this line. --- .../proxy/common_utils/check_batch_cost.py | 128 ++++++---- .../spend/test_batch_poll_starvation.py | 230 ++++++++++++++++-- .../common_utils/test_check_batch_cost.py | 204 ++++++++++------ 3 files changed, 431 insertions(+), 131 deletions(-) diff --git a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py index 6b839e7cece..92c4aa3b89a 100644 --- a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py +++ b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py @@ -3,7 +3,8 @@ Polls LiteLLM_ManagedObjectTable to check if the batch job is complete, and if t """ import json -from collections.abc import Sequence +import re +from collections.abc import Mapping, Sequence from dataclasses import replace as dataclasses_replace from datetime import datetime, timedelta, timezone from types import MappingProxyType @@ -28,7 +29,12 @@ if TYPE_CHECKING: from litellm.types.utils import LiteLLMBatch +def _error_names_resource(error: Exception, resource_id: str) -> bool: + return resource_id in re.findall(r"""[^\s"'`]+""", str(error)) + + CHECK_BATCH_COST_USER_AGENT = "LiteLLM Proxy/CheckBatchCost" +RECENT_BATCH_POLL_WINDOW: Final = timedelta(hours=48) PROVIDER_TERMINAL_BATCH_STATUSES: Final[Tuple[str, ...]] = ( "completed", @@ -45,6 +51,12 @@ TERMINAL_MANAGED_OBJECT_STATUSES: Final[Tuple[str, ...]] = ( class _ManagedObjectRow(Protocol): + @property + def created_at(self) -> datetime: ... + + @property + def updated_at(self) -> datetime: ... + @property def id(self) -> str: ... @@ -99,6 +111,11 @@ class CheckBatchCost: # the guaranteed-failing primary query on every subsequent cycle. self._has_batch_processed_column: bool = True self.batch_processed_support_confirmed: bool = False + self._poll_cursor: tuple[datetime, str] | None = None + self._poll_before: datetime = datetime.now(timezone.utc) + self._arrival_cursor: tuple[datetime, str] | None = None + self._arrival_before: datetime = self._poll_before + self._poll_arrivals: bool = False @staticmethod def _is_missing_batch_processed_column_error(err: Exception) -> bool: @@ -270,29 +287,9 @@ class CheckBatchCost: f"(older than {MANAGED_OBJECT_STALENESS_CUTOFF_DAYS} days) as stale_expired" ) - if not self._has_batch_processed_column: - return - - # A row already in a terminal status is never rewritten by the sweep above, so - # without this it keeps a poll-page slot forever and starves newer batches. - retired: Final = await _managed_object_table(self.prisma_client).update_many( - where={ - "file_purpose": "batch", - "batch_processed": False, - "status": {"in": ["complete", "completed"]}, - "created_at": {"lt": cutoff}, - }, - data={"batch_processed": True}, - ) - if retired > 0: - verbose_proxy_logger.warning( - f"CheckBatchCost: gave up on {retired} completed managed objects older than " - f"{MANAGED_OBJECT_STALENESS_CUTOFF_DAYS} days that were never costed" - ) - async def _fallback_find_jobs(self) -> "Sequence[_ManagedObjectRow]": """Query batch jobs without the batch_processed filter (for older schemas).""" - return await _managed_object_table(self.prisma_client).find_many( + return await self._find_jobs( where={ "file_purpose": "batch", "status": { @@ -306,10 +303,59 @@ class CheckBatchCost: ] }, }, - take=MAX_OBJECTS_PER_POLL_CYCLE, - order={"created_at": "asc"}, ) + async def _find_jobs(self, where: Mapping[str, object]) -> Sequence[_ManagedObjectRow]: + arrivals: Final = self._poll_arrivals + page: Final = await self._find_job_page(where, arrivals=arrivals) + self._poll_arrivals = not arrivals if page else arrivals + if page: + return page + return await self._find_job_page(where, arrivals=not arrivals) + + async def _find_job_page(self, where: Mapping[str, object], *, arrivals: bool) -> Sequence[_ManagedObjectRow]: + cursor: Final = self._arrival_cursor if arrivals else self._poll_cursor + if cursor is None: + if arrivals: + self._arrival_before = datetime.now(timezone.utc) + else: + self._poll_before = datetime.now(timezone.utc) - RECENT_BATCH_POLL_WINDOW + before: Final = self._arrival_before if arrivals else self._poll_before + page: Final = await _managed_object_table(self.prisma_client).find_many( + where={ + **where, + "created_at": { + "lte": before, + **({"gt": before - RECENT_BATCH_POLL_WINDOW} if arrivals else {}), + }, + **( + { + "OR": [ + {"created_at": {"gt": cursor[0]}}, + {"created_at": cursor[0], "id": {"gt": cursor[1]}}, + ] + } + if cursor is not None + else {} + ), + }, + take=MAX_OBJECTS_PER_POLL_CYCLE, + order=[{"created_at": "asc"}, {"id": "asc"}], + ) + next_cursor: Final = (page[-1].created_at, page[-1].id) if len(page) == MAX_OBJECTS_PER_POLL_CYCLE else None + if arrivals: + self._arrival_cursor = next_cursor + else: + self._poll_cursor = next_cursor + return page + + def _unprocessed_snapshot(self, job: _ManagedObjectRow) -> Mapping[str, object]: + return { + "id": job.id, + "updated_at": job.updated_at, + **({"batch_processed": False} if self._has_batch_processed_column else {}), + } + async def _retire_job(self, job: "_ManagedObjectRow", reason: str) -> None: """ Take a row that can never be costed out of the poll page. Leaving it selectable @@ -317,20 +363,16 @@ class CheckBatchCost: once enough such rows accumulate no newer batch is ever reached. Older schemas without batch_processed can only be excluded through the status filter. """ - data: Final = ( - {"batch_processed": True} - if self._has_batch_processed_column - else {"status": "stale_expired"} - ) + data: Final = {"batch_processed": True} if self._has_batch_processed_column else {"status": "stale_expired"} try: - await _managed_object_table(self.prisma_client).update( - where={"id": job.id}, + retired: Final = await _managed_object_table(self.prisma_client).update_many( + where=self._unprocessed_snapshot(job), data=data, ) except Exception as db_err: - verbose_proxy_logger.error( - f"CheckBatchCost: failed to retire uncostable job {job.id} ({reason}): {db_err}" - ) + verbose_proxy_logger.error(f"CheckBatchCost: failed to retire uncostable job {job.id} ({reason}): {db_err}") + return + if retired == 0: return verbose_proxy_logger.warning( f"CheckBatchCost: job {job.id} can never be costed ({reason}), " @@ -421,13 +463,13 @@ class CheckBatchCost: from litellm.exceptions import NotFoundError - return isinstance(error, (NotFoundError, openai.NotFoundError)) and batch_id in str(error) + return isinstance(error, (NotFoundError, openai.NotFoundError)) and _error_names_resource(error, batch_id) def _batch_deployment_exists(self, model_id: str) -> bool: """A 404 only proves the batch is gone when it came from the batch's own deployment. Once that deployment leaves the router, default fallbacks can silently send the retrieve to a provider that never saw the batch, so its - 404 must not retire the row; the staleness sweep bounds it instead.""" + 404 must not retire a potentially recoverable row.""" return self.llm_router.get_deployment(model_id=model_id) is not None @staticmethod @@ -442,7 +484,7 @@ class CheckBatchCost: if not output_file_id: return False - return isinstance(error, (NotFoundError, openai.NotFoundError)) and output_file_id in str(error) + return isinstance(error, (NotFoundError, openai.NotFoundError)) and _error_names_resource(error, output_file_id) async def _finalize_unbilled_terminal_job( self, job: "_ManagedObjectRow", response: "LiteLLMBatch" @@ -464,15 +506,17 @@ class CheckBatchCost: db_batch_object=job, unified_batch_id=_is_base64_encoded_unified_file_id(job.unified_object_id), ) - update_data: Final[dict] = { + update_data: Final[dict[str, object]] = { "status": response.status, "file_object": response.model_dump_json(), **({"batch_processed": True} if self._has_batch_processed_column else {}), } - await _managed_object_table(self.prisma_client).update( - where={"id": job.id}, + finalized: Final = await _managed_object_table(self.prisma_client).update_many( + where=self._unprocessed_snapshot(job), data=update_data, ) + if finalized == 0: + return verbose_proxy_logger.info( f"CheckBatchCost: marked job {job.id} as {response.status} in DB" ) @@ -980,7 +1024,7 @@ class CheckBatchCost: # endpoint may transition a batch to "complete" before # CheckBatchCost runs. The batch_processed=False filter # already prevents reprocessing finished batches. - jobs = await _managed_object_table(self.prisma_client).find_many( + jobs = await self._find_jobs( where={ "file_purpose": "batch", "batch_processed": False, @@ -993,8 +1037,6 @@ class CheckBatchCost: ] }, }, - take=MAX_OBJECTS_PER_POLL_CYCLE, - order={"created_at": "asc"}, ) self.batch_processed_support_confirmed = True except Exception as query_err: diff --git a/tests/integration/spend/test_batch_poll_starvation.py b/tests/integration/spend/test_batch_poll_starvation.py index f68f10e3d8a..51f5f0871f5 100644 --- a/tests/integration/spend/test_batch_poll_starvation.py +++ b/tests/integration/spend/test_batch_poll_starvation.py @@ -1,14 +1,20 @@ import json import os +from datetime import datetime, timezone +from functools import partial from hashlib import sha256 +from itertools import chain from typing import Final +from uuid import uuid4 +import httpx import pytest from integration._support.client import JSON_OBJECT, Gateway, Scenario, eventually, object_value, string_value -from integration._support.database import read_rows -from integration._support.upstream import delete_scenario, register_scenario +from integration._support.database import read_rows, write_rows +from integration._support.prisma_clients import connected_proxy_prisma +from integration._support.upstream import ScenarioHandle, delete_scenario, register_scenario from integration.cost_calculation.cost_tracking_case import JsonResponse, RoutedResponse, TextResponse -from pydantic import JsonValue +from pydantic import JsonValue, TypeAdapter from litellm.constants import MAX_OBJECTS_PER_POLL_CYCLE @@ -59,17 +65,17 @@ def _accepting_routes() -> dict[str, JsonResponse | TextResponse]: } -def _gone_at_provider_routes() -> RoutedResponse: +def _gone_at_provider_routes(*, retryable: bool = False) -> RoutedResponse: return RoutedResponse( content_type="application/x-routed", routes={ **_accepting_routes(), "GET /batches/batch-$REQUEST_ID": JsonResponse( content_type="application/json", - status=404, + status=503 if retryable else 404, body={ "error": { - "message": "No batch found with id 'batch-$REQUEST_ID'.", + "message": "Temporary failure" if retryable else "No batch found with id 'batch-$REQUEST_ID'.", "type": "invalid_request_error", "param": "id", "code": "batch_not_found", @@ -80,7 +86,7 @@ def _gone_at_provider_routes() -> RoutedResponse: ) -def _completed_routes() -> RoutedResponse: +def _completed_routes(*, ready: bool = True) -> RoutedResponse: output_line: Final = { "id": "batch_req_1", "custom_id": "r1", @@ -106,7 +112,8 @@ def _completed_routes() -> RoutedResponse: routes={ **_accepting_routes(), "GET /batches/batch-$REQUEST_ID": JsonResponse( - content_type="application/json", body=_batch("completed", "file-out-$REQUEST_ID") + content_type="application/json", + body=_batch("completed", "file-out-$REQUEST_ID") if ready else _batch("in_progress", None), ), "GET /files/file-out-$REQUEST_ID/content": TextResponse( content_type="application/jsonl", body=json.dumps(output_line, separators=(",", ":")) + "\n" @@ -115,7 +122,37 @@ def _completed_routes() -> RoutedResponse: ) -def _scripted_deployment(scenario: Scenario, marker: str, routes: RoutedResponse) -> str: +def _batch_was_polled(upstream: ScenarioHandle) -> bool: + response: Final = httpx.get(f"{upstream.control_url}/__observations", timeout=15, trust_env=False) + response.raise_for_status() + observations: Final = TypeAdapter(dict[str, list[dict[str, JsonValue]]]).validate_json(response.content) + return any( + item.get("method") == "GET" and string_value(item["path"]).startswith(f"/{upstream.scenario_id}/batches/") + for item in observations["requests"] + ) + + +def _missing_output_routes() -> RoutedResponse: + return RoutedResponse( + content_type="application/x-routed", + routes={ + **_completed_routes().routes, + "GET /files/file-out-$REQUEST_ID/content": JsonResponse( + content_type="application/json", + status=404, + body={ + "error": { + "message": "No file found with id 'file-out-$REQUEST_ID'.", + "type": "invalid_request_error", + "code": "file_not_found", + } + }, + ), + }, + ) + + +def _scripted_deployment(scenario: Scenario, marker: str, routes: RoutedResponse) -> tuple[str, ScenarioHandle]: scenario_id: Final = f"poll-{marker}-{sha256(os.urandom(16)).hexdigest()[:12]}" handle: Final = register_scenario(scenario_id, routes) scenario.cleanups.callback(delete_scenario, handle) @@ -133,7 +170,7 @@ def _scripted_deployment(scenario: Scenario, marker: str, routes: RoutedResponse }, ) scenario.cleanups.callback(scenario.delete_model, string_value(object_value(created["model_info"])["id"])) - return string_value(created["model_name"]) + return string_value(created["model_name"]), handle def _submitted_batch_id(gateway: Gateway, key: str, model_name: str) -> str: @@ -173,20 +210,51 @@ def _managed_rows(batch_ids: tuple[str, ...]) -> list[dict[str, JsonValue]]: ) +@pytest.mark.parametrize( + ("retryable", "old_completed", "backlog"), + [(False, False, 0), (False, True, 0), (True, False, 0), (True, True, 0), (True, False, 1000)], +) @pytest.mark.timeout(180) @pytest.mark.covers("quota_management.spend_tracking.batch_costs.uncostable_rows_retire_so_newer_batches_are_costed") -def test_batches_gone_at_provider_do_not_starve_a_newer_batch_out_of_cost_polling(gateway: Gateway) -> None: +def test_uncostable_batches_do_not_starve_billable_batches( + gateway: Gateway, retryable: bool, old_completed: bool, backlog: int +) -> None: with gateway.scenario() as scenario: - key: Final = scenario.key() + owner: Final = f"batch-backlog-{uuid4().hex}" + if backlog: + _insert_scan_rows(owner, "old", backlog, datetime(2000, 1, 1, tzinfo=timezone.utc)) + scenario.cleanups.callback( + write_rows, 'DELETE FROM "LiteLLM_ManagedObjectTable" WHERE created_by = %s', (owner,) + ) + team_id: Final = scenario.team() + key: Final = scenario.key(team_id=team_id) gone_batch_ids: Final = tuple( _submitted_batch_id( - gateway, key, _scripted_deployment(scenario, f"gone{index}", _gone_at_provider_routes()) + gateway, + key, + _scripted_deployment(scenario, f"gone{index}", _gone_at_provider_routes(retryable=retryable))[0], ) for index in range(MAX_OBJECTS_PER_POLL_CYCLE) ) - costable_batch_id: Final = _submitted_batch_id( - gateway, key, _scripted_deployment(scenario, "costable", _completed_routes()) + missing_output_id: Final = _submitted_batch_id( + gateway, key, _scripted_deployment(scenario, "missing-output", _missing_output_routes())[0] ) + model, upstream = _scripted_deployment(scenario, "costable", _completed_routes(ready=False)) + costable_batch_id: Final = _submitted_batch_id(gateway, key, model) + for batch_id in (*gone_batch_ids, missing_output_id, costable_batch_id): + scenario.cleanups.callback( + write_rows, + 'DELETE FROM "LiteLLM_ManagedObjectTable" WHERE unified_object_id = %s', + (batch_id,), + ) + if old_completed: + write_rows( + 'UPDATE "LiteLLM_ManagedObjectTable" SET status = %s, ' + "created_at = NOW() - INTERVAL '30 days' WHERE unified_object_id = %s", + ("completed", costable_batch_id), + ) + assert eventually(lambda: _batch_was_polled(upstream), bool, seconds=120) + register_scenario(upstream.scenario_id, _completed_routes(), control_url=upstream.control_url) spend_rows: Final = eventually( lambda: read_rows( 'SELECT call_type, status, prompt_tokens, completion_tokens, spend FROM "LiteLLM_SpendLogs" ' @@ -209,4 +277,134 @@ def test_batches_gone_at_provider_do_not_starve_a_newer_batch_out_of_cost_pollin } ] assert _managed_rows((costable_batch_id,)) == [{"batch_processed": True}] - assert _managed_rows(gone_batch_ids) == [{"batch_processed": True}] * MAX_OBJECTS_PER_POLL_CYCLE + assert eventually( + lambda: _managed_rows((missing_output_id,)), + lambda rows: rows == [{"batch_processed": True}], + seconds=120, + ) == [{"batch_processed": True}] + expected_blockers: Final = [{"batch_processed": not retryable}] * MAX_OBJECTS_PER_POLL_CYCLE + blockers: Final = eventually( + lambda: _managed_rows(gone_batch_ids), lambda rows: rows == expected_blockers, seconds=120 + ) + assert blockers == expected_blockers + + expected_spend: Final = BATCH_COST_SHARE * ( + PROMPT_TOKENS * INPUT_COST_PER_TOKEN + COMPLETION_TOKENS * OUTPUT_COST_PER_TOKEN + ) + for table, column, identity in ( + ("LiteLLM_VerificationToken", "token", sha256(key.encode()).hexdigest()), + ("LiteLLM_TeamTable", "team_id", team_id), + ): + balance: Final = eventually( + partial(read_rows, f'SELECT spend FROM "{table}" WHERE {column} = %s', (identity,)), + lambda rows: len(rows) == 1 and rows[0]["spend"] == pytest.approx(expected_spend), + seconds=70, + ) + assert balance == [{"spend": pytest.approx(expected_spend)}] + + +def _insert_scan_rows(owner: str, group: str, size: int, created_at: datetime) -> tuple[str, ...]: + prefix: Final = f"{owner}-{group}-" + write_rows( + 'INSERT INTO "LiteLLM_ManagedObjectTable" ' + "(id, unified_object_id, model_object_id, file_object, file_purpose, status, created_by, created_at, updated_at) " + "SELECT %s || lpad(n::text, 8, '0'), %s || n, %s || n, '{}'::jsonb, 'batch', 'completed', %s, " + "%s::timestamptz, NOW() FROM generate_series(0, %s::int - 1) n", + (prefix, prefix, prefix, owner, created_at.isoformat(), str(size)), + ) + return tuple(f"{prefix}{index:08}" for index in range(size)) + + +@pytest.mark.asyncio +@pytest.mark.parametrize("count", [2 * MAX_OBJECTS_PER_POLL_CYCLE, 2 * MAX_OBJECTS_PER_POLL_CYCLE + 1, 1000]) +async def test_arrivals_progress_while_retry_scan_advances_and_wraps(count: int) -> None: + from litellm.proxy.common_utils.user_api_key_cache import UserApiKeyCache + from litellm.proxy.utils import ProxyLogging + from litellm.router import Router + from litellm_enterprise.proxy.common_utils.check_batch_cost import CheckBatchCost + + owner: Final = f"batch-scan-{uuid4().hex}" + + try: + old_ids: Final = _insert_scan_rows(owner, "old", count, datetime(2000, 1, 1, tzinfo=timezone.utc)) + async with connected_proxy_prisma() as prisma: + logging: Final = ProxyLogging(UserApiKeyCache()) + router: Final = Router() + poller: Final = CheckBatchCost(logging, prisma, router) + where: Final = {"created_by": owner, "batch_processed": False} + first: Final = await poller._find_jobs(where) + assert tuple(row.id for row in first) == old_ids[:MAX_OBJECTS_PER_POLL_CYCLE] + + recent_ids: Final = _insert_scan_rows( + owner, "recent", MAX_OBJECTS_PER_POLL_CYCLE + 1, datetime.now(timezone.utc) + ) + + async def poll_with_arrival(turn: int) -> tuple[str, ...]: + if turn % 4 == 0: + _insert_scan_rows(owner, f"arrival-{turn}", 1, datetime.now(timezone.utc)) + page: Final = await poller._find_jobs(where) + assert len(page) <= MAX_OBJECTS_PER_POLL_CYCLE + write_rows( + 'UPDATE "LiteLLM_ManagedObjectTable" SET batch_processed = true ' + "WHERE created_by = %s AND id = ANY(%s) AND id LIKE %s", + (owner, [row.id for row in page], f"{owner}-arrival-%"), + ) + return tuple(row.id for row in page) + + pages: Final = tuple( + [await poll_with_arrival(turn) for turn in range(4 * (count // MAX_OBJECTS_PER_POLL_CYCLE + 2))] + ) + selected: Final = tuple(chain.from_iterable(pages)) + assert all(selected.count(identity) >= 2 for identity in recent_ids) + selected_old: Final = tuple(identity for identity in selected if identity in old_ids) + assert selected_old[: count - MAX_OBJECTS_PER_POLL_CYCLE] == old_ids[MAX_OBJECTS_PER_POLL_CYCLE:] + assert set(old_ids).issubset(selected_old) + + latest_ids: Final = _insert_scan_rows(owner, "latest", 1, datetime.now(timezone.utc)) + followups: Final = tuple([await poller._find_jobs(where) for _ in range(12)]) + assert any(latest_ids[0] in tuple(row.id for row in page) for page in followups) + + restarted: Final = CheckBatchCost(logging, prisma, router) + restart_page: Final = await restarted._find_jobs(where) + assert tuple(row.id for row in restart_page) == old_ids[:MAX_OBJECTS_PER_POLL_CYCLE] + finally: + write_rows('DELETE FROM "LiteLLM_ManagedObjectTable" WHERE created_by = %s', (owner,)) + + +@pytest.mark.asyncio +@pytest.mark.parametrize("steady_arrivals", [False, True]) +@pytest.mark.parametrize("backlog", [0, 1000]) +async def test_recent_batches_are_revisited_without_scanning_old_backlog(steady_arrivals: bool, backlog: int) -> None: + from litellm.proxy.common_utils.user_api_key_cache import UserApiKeyCache + from litellm.proxy.utils import ProxyLogging + from litellm.router import Router + from litellm_enterprise.proxy.common_utils.check_batch_cost import CheckBatchCost + + owner: Final = f"batch-repeat-{uuid4().hex}" + try: + _insert_scan_rows(owner, "old", backlog, datetime(2000, 1, 1, tzinfo=timezone.utc)) + async with connected_proxy_prisma() as prisma: + poller: Final = CheckBatchCost(ProxyLogging(UserApiKeyCache()), prisma, Router()) + where: Final = {"created_by": owner, "batch_processed": False} + await poller._find_jobs(where) + target: Final = _insert_scan_rows(owner, "target", 1, datetime.now(timezone.utc))[0] + assert target in tuple(row.id for row in await poller._find_jobs(where)) + for cycle in range(3): + if steady_arrivals: + _insert_scan_rows(owner, f"arrival-{cycle}", 1, datetime.now(timezone.utc)) + pages: Final = tuple([await poller._find_jobs(where) for _ in range(4)]) + assert any(target in tuple(row.id for row in page) for page in pages) + assert all(len(page) <= MAX_OBJECTS_PER_POLL_CYCLE for page in pages) + write_rows( + 'UPDATE "LiteLLM_ManagedObjectTable" SET batch_processed = true WHERE created_by = %s AND id != %s', + (owner, target), + ) + write_rows( + 'UPDATE "LiteLLM_ManagedObjectTable" SET created_at = %s WHERE id = %s', + (datetime(2000, 1, 1, tzinfo=timezone.utc), target), + ) + recovery: Final = tuple([await poller._find_jobs(where) for _ in range(4)]) + assert any(target in tuple(row.id for row in page) for page in recovery) + + finally: + write_rows('DELETE FROM "LiteLLM_ManagedObjectTable" WHERE created_by = %s', (owner,)) diff --git a/tests/unit/proxy/common_utils/test_check_batch_cost.py b/tests/unit/proxy/common_utils/test_check_batch_cost.py index 8a5b3402e4d..198e20d1c02 100644 --- a/tests/unit/proxy/common_utils/test_check_batch_cost.py +++ b/tests/unit/proxy/common_utils/test_check_batch_cost.py @@ -9,6 +9,8 @@ ARN unified_object_id) batches with no managed unified id. import asyncio import json from contextlib import contextmanager +from copy import copy +from datetime import datetime, timezone from hashlib import sha256 from typing import TYPE_CHECKING, Final from unittest.mock import AsyncMock, MagicMock, patch @@ -204,7 +206,7 @@ class TestCheckBatchCost: find_call = mock_prisma_client.db.litellm_managedobjecttable.find_many.call_args assert find_call[1]["take"] == MAX_OBJECTS_PER_POLL_CYCLE - assert find_call[1]["order"] == {"created_at": "asc"} + assert find_call[1]["order"] == [{"created_at": "asc"}, {"id": "asc"}] not_in = find_call[1]["where"]["status"]["not_in"] assert "stale_expired" in not_in # "complete"/"completed" are intentionally NOT excluded from the @@ -229,15 +231,13 @@ class TestCheckBatchCost: ) # First find_many (primary query) raises with a schema error; second (fallback) returns empty mock_prisma_client.db.litellm_managedobjecttable.find_many = AsyncMock( - side_effect=[Exception("column batch_processed does not exist"), []] + side_effect=[Exception("column batch_processed does not exist"), [], []] ) await check_batch_cost_instance.check_batch_cost() - calls = ( - mock_prisma_client.db.litellm_managedobjecttable.find_many.call_args_list - ) - assert len(calls) == 2 + calls = mock_prisma_client.db.litellm_managedobjecttable.find_many.call_args_list + assert len(calls) == 3 fallback_where = calls[1][1]["where"] assert "batch_processed" not in fallback_where assert "stale_expired" in fallback_where["status"]["not_in"] @@ -264,15 +264,8 @@ class TestCheckBatchCost: await check_batch_cost_instance.check_batch_cost() - # Only one find_many call — the fallback directly, no primary query attempt - assert ( - mock_prisma_client.db.litellm_managedobjecttable.find_many.call_count == 1 - ) - fallback_where = ( - mock_prisma_client.db.litellm_managedobjecttable.find_many.call_args[1][ - "where" - ] - ) + assert mock_prisma_client.db.litellm_managedobjecttable.find_many.call_count == 2 + fallback_where = mock_prisma_client.db.litellm_managedobjecttable.find_many.call_args[1]["where"] assert "batch_processed" not in fallback_where @pytest.mark.asyncio @@ -771,7 +764,7 @@ class TestCheckBatchCost: await check_batch_cost_instance.check_batch_cost() - assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count >= 3, ( + assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2, ( "Expected update() to be called exactly once for the completed job" ) update_data = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args[1]["data"] @@ -904,7 +897,7 @@ class TestCheckBatchCost: mock_update_database.assert_awaited_once() assert mock_update_database.call_args.kwargs["response_cost"] == 0.01 - assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count >= 3, ( + assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2, ( "the job must still be marked processed once cost tracking succeeds" ) @@ -1020,12 +1013,10 @@ class TestCheckBatchCost: await check_batch_cost_instance.check_batch_cost() - assert ( - mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1 - ), f"Expected update() to be called exactly once for a {terminal_status} job" - update_data = mock_prisma_client.db.litellm_managedobjecttable.update.call_args[ - 1 - ]["data"] + assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2, ( + f"Expected update() to be called exactly once for a {terminal_status} job" + ) + update_data = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args[1]["data"] assert update_data["status"] == terminal_status assert ( update_data["batch_processed"] is True @@ -1131,9 +1122,13 @@ class TestCheckBatchCost: assert store_call.kwargs["user_api_key_dict"].user_id == "user-1" assert store_call.kwargs["user_api_key_dict"].team_id == "team-1" - assert mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1 - update_call = mock_prisma_client.db.litellm_managedobjecttable.update.call_args - assert update_call.kwargs["where"] == {"id": "job-terminal-mint-1"} + assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2 + update_call = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args + assert update_call.kwargs["where"] == { + "id": "job-terminal-mint-1", + "batch_processed": False, + "updated_at": mock_job.updated_at, + } update_data = update_call.kwargs["data"] assert update_data["status"] == terminal_status assert update_data["batch_processed"] is True @@ -1208,12 +1203,10 @@ class TestCheckBatchCost: ) as mock_afile_content: await check_batch_cost_instance.check_batch_cost() - assert ( - mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1 - ), "a completed batch with no output file must be marked processed exactly once" - update_data = mock_prisma_client.db.litellm_managedobjecttable.update.call_args[ - 1 - ]["data"] + assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2, ( + "a completed batch with no output file must be marked processed exactly once" + ) + update_data = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args[1]["data"] assert update_data["status"] == completed_status assert ( update_data["batch_processed"] is True @@ -1455,7 +1448,7 @@ class TestCheckBatchCost: mock_afile_content.await_count == 1 ), f"{terminal_status} batch with an output file must fetch results and be billed" mock_logging_obj.async_success_handler.assert_awaited_once() - assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count >= 3 + assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2 update_data = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args[1]["data"] assert update_data["batch_processed"] is True assert update_data["status"] == terminal_status, ( @@ -1638,12 +1631,10 @@ class TestCheckBatchCost: assert mock_afile_content.await_count == 1 mock_calculate.assert_not_awaited() - assert ( - mock_prisma_client.db.litellm_managedobjecttable.update.call_count == 1 - ), "a terminal batch with a 404ing output file must be retired, not retried forever" - update_data = mock_prisma_client.db.litellm_managedobjecttable.update.call_args[ - 1 - ]["data"] + assert mock_prisma_client.db.litellm_managedobjecttable.update_many.call_count == 2, ( + "a terminal batch with a 404ing output file must be retired, not retried forever" + ) + update_data = mock_prisma_client.db.litellm_managedobjecttable.update_many.call_args[1]["data"] assert update_data["status"] == "failed" assert update_data["batch_processed"] is True @@ -2056,7 +2047,7 @@ class TestUnmanagedVertexRouting: mock_logging_obj.async_success_handler.assert_awaited_once() assert mock_logging_obj.async_success_handler.call_args[1]["batch_cost"] == 0.01 - assert prisma.db.litellm_managedobjecttable.update_many.call_count >= 3 + assert prisma.db.litellm_managedobjecttable.update_many.call_count == 2 update_data = prisma.db.litellm_managedobjecttable.update_many.call_args[1]["data"] assert update_data["batch_processed"] is True assert update_data["status"] == "complete" @@ -2287,7 +2278,7 @@ class TestUnmanagedBedrockRouting: mock_logging_obj.async_success_handler.assert_awaited_once() assert mock_logging_obj.async_success_handler.call_args[1]["batch_cost"] == 0.02 - assert prisma.db.litellm_managedobjecttable.update_many.call_count >= 3 + assert prisma.db.litellm_managedobjecttable.update_many.call_count == 2 update_data = prisma.db.litellm_managedobjecttable.update_many.call_args[1]["data"] assert update_data["batch_processed"] is True assert update_data["status"] == "complete" @@ -2867,9 +2858,10 @@ class TestPollPageStarvation: await self._instance(prisma, llm_router).check_batch_cost() llm_router.aretrieve_batch.assert_not_awaited() - prisma.db.litellm_managedobjecttable.update.assert_awaited_once() - call = prisma.db.litellm_managedobjecttable.update.call_args[1] - assert call["where"] == {"id": "job-no-model"} + prisma.db.litellm_managedobjecttable.update_many.assert_awaited() + call = prisma.db.litellm_managedobjecttable.update_many.call_args[1] + assert call["where"]["id"] == "job-no-model" + assert call["where"]["batch_processed"] is False assert call["data"] == {"batch_processed": True} @pytest.mark.asyncio @@ -2897,10 +2889,8 @@ class TestPollPageStarvation: await self._instance(prisma, llm_router).check_batch_cost() - prisma.db.litellm_managedobjecttable.update.assert_awaited_once() - assert prisma.db.litellm_managedobjecttable.update.call_args[1]["data"] == { - "batch_processed": True - } + prisma.db.litellm_managedobjecttable.update_many.assert_awaited() + assert prisma.db.litellm_managedobjecttable.update_many.call_args[1]["data"] == {"batch_processed": True} @pytest.mark.asyncio async def test_provider_404_with_deployment_gone_keeps_job(self): @@ -2961,26 +2951,7 @@ class TestPollPageStarvation: await instance.check_batch_cost() - assert prisma.db.litellm_managedobjecttable.update.call_args[1]["data"] == { - "status": "stale_expired" - } - - @pytest.mark.asyncio - async def test_stale_cleanup_gives_up_on_never_costed_completed_rows(self): - """A row already in a terminal status is never rewritten by the staleness sweep, so - it needs its own bound or it starves newer batches indefinitely.""" - prisma = self._prisma([]) - - await self._instance(prisma, MagicMock()).check_batch_cost() - - calls = prisma.db.litellm_managedobjecttable.update_many.call_args_list - assert len(calls) == 2, "expected the staleness sweep plus the never-costed sweep" - where = calls[1][1]["where"] - assert where["file_purpose"] == "batch" - assert where["batch_processed"] is False - assert where["status"] == {"in": ["complete", "completed"]} - assert "created_at" in where - assert calls[1][1]["data"] == {"batch_processed": True} + assert prisma.db.litellm_managedobjecttable.update_many.call_args[1]["data"] == {"status": "stale_expired"} @pytest.mark.asyncio async def test_newer_batch_is_polled_once_dead_rows_are_retired(self): @@ -3020,7 +2991,8 @@ class TestPollPageStarvation: retired = [ call[1]["where"]["id"] - for call in prisma.db.litellm_managedobjecttable.update.call_args_list + for call in prisma.db.litellm_managedobjecttable.update_many.call_args_list + if "id" in call[1]["where"] ] assert retired == ["job-no-model", "job-gone"] assert ( @@ -3068,7 +3040,8 @@ class _FakeManagedObjectRow: self.team_id = None self.api_key = None self.request_tags = None - self.created_at = 1700000000 + self.created_at = datetime(9999, 1, 1, tzinfo=timezone.utc) + self.updated_at = datetime(2000, 1, 1, tzinfo=timezone.utc) self.file_object = json.dumps( {"id": "batch-456", "status": "in_progress", "input_file_id": "file-input-1", "output_file_id": _CLAIM_OUTPUT_FILE_ID} @@ -3094,7 +3067,9 @@ class _FakeManagedObjectTable: def _matches(self, where: dict) -> bool: for key, value in where.items(): if key == "created_at": - return False + if "lt" in value and not self.row.created_at < value["lt"]: + return False + continue if key == "status": if self.row.status in value.get("not_in", []): return False @@ -3107,7 +3082,9 @@ class _FakeManagedObjectTable: async def _update_many(self, *, where: dict, data: dict) -> int: if not self._matches(where): return 0 - if "batch_processed" in where: + if "updated_at" in where: + self.journal.append("finalize") + elif "batch_processed" in where: self.journal.append("claim" if data.get("batch_processed") else "release") for key, value in data.items(): setattr(self.row, key, value) @@ -3357,6 +3334,89 @@ class TestMultiPodBatchCostClaim: ["batch-test-model"] if deployment_model == "openai/batch-test-model" else ["batch-test-model"] * successes ) + @pytest.mark.asyncio + @pytest.mark.parametrize("error_source", ("batch", "output")) + async def test_a_404_for_another_identifier_preserves_recovery(self, error_source: str) -> None: + import base64 + + import httpx + import litellm + import respx + + from litellm.integrations.custom_logger import CustomLogger + from litellm.types.utils import SpecialEnums + + class SpendRecorder(CustomLogger): + def __init__(self) -> None: + super().__init__() + self.costs: tuple[float, ...] = () + + async def async_log_success_event( + self, kwargs: dict[str, object], response_obj: object, start_time: datetime, end_time: datetime + ) -> None: + if kwargs["call_type"] == "aretrieve_batch": + cost: Final = kwargs["response_cost"] + assert isinstance(cost, float) + self.costs += (cost,) + + recorder: Final = SpendRecorder() + litellm.logging_callback_manager.add_litellm_async_success_callback(recorder) + litellm.register_model( + { + "batch-recovery-model": { + "litellm_provider": "openai", + "mode": "chat", + "input_cost_per_token_batches": 0.01, + "output_cost_per_token_batches": 0.02, + } + } + ) + row: Final = _FakeManagedObjectRow() + row.unified_object_id = ( + base64.urlsafe_b64encode( + SpecialEnums.LITELLM_MANAGED_BATCH_COMPLETE_STR.value.format("model-123", "batch-456").encode() + ) + .decode() + .rstrip("=") + ) + router: Final = self._router() + response: Final = router.aretrieve_batch.return_value + error: Final = litellm.NotFoundError( + message=f"No object found with id '{'batch-456' if error_source == 'batch' else _CLAIM_OUTPUT_FILE_ID}0'.", + model="gpt-4", + llm_provider="openai", + ) + router.aretrieve_batch.side_effect = (error, response) if error_source == "batch" else (response, response) + prisma: Final = self._prisma(row, []) + output: Final = json.dumps( + { + "response": { + "status_code": 200, + "body": { + "model": "batch-recovery-model", + "usage": {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15}, + }, + }, + "error": None, + } + ).encode() + with respx.mock: + route: Final = respx.get(f"https://api.openai.com/v1/files/{_CLAIM_OUTPUT_FILE_ID}/content") + route.mock( + side_effect=error if error_source == "output" else None, + return_value=None if error_source == "output" else httpx.Response(200, content=output), + ) + await self._instance(prisma, router).check_batch_cost() + assert row.batch_processed is False + assert recorder.costs == () + route.mock(return_value=httpx.Response(200, content=output)) + await self._instance(prisma, router).check_batch_cost() + await self._instance(prisma, router).check_batch_cost() + + assert row.batch_processed is True + assert row.status == "complete" + assert recorder.costs == (pytest.approx(10 * 0.01 + 5 * 0.02),) + @staticmethod def _claim_calls(prisma) -> list: return [ From 15c8628664ba1fab553f9188be55725409fdcef9 Mon Sep 17 00:00:00 2001 From: Mrinal Chanshetty Date: Tue, 20 Oct 2026 16:12:44 -0700 Subject: [PATCH 32/66] chore(deps): bump aiohttp to 3.14.4 --- uv.lock | 477 +++++++++++++++++++++++++++----------------------------- 1 file changed, 227 insertions(+), 250 deletions(-) diff --git a/uv.lock b/uv.lock index fb9d8bbd9ac..af06b906e34 100644 --- a/uv.lock +++ b/uv.lock @@ -10,7 +10,7 @@ resolution-markers = [ ] [options] -exclude-newer = "2026-10-03T01:54:46.765163Z" +exclude-newer = "2026-10-17T23:12:37.361448Z" exclude-newer-span = "P3D" [manifest] @@ -85,7 +85,7 @@ wheels = [ [[package]] name = "aiohttp" -version = "3.14.3" +version = "3.14.4" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "aiohappyeyeballs" }, @@ -98,126 +98,127 @@ dependencies = [ { name = "typing-extensions", marker = "python_full_version < '3.13'" }, { name = "yarl" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/58/d9/22ce5786ac0c1653ae8b6c23bded02c1686d11f0dbb45b31ce128e0df985/aiohttp-3.14.3.tar.gz", hash = "sha256:9491196535a88924a60afd5b5f434b5b203b6cc616250878dbdb223a8f7844bc", size = 7971213, upload-time = "2026-07-23T01:57:27.037Z" } +sdist = { url = "https://files.pythonhosted.org/packages/93/2f/6a91adaa2dc26877d6ed2f54c0370c8910f019db7d77c5c6a194611e93ea/aiohttp-3.14.4.tar.gz", hash = "sha256:831fc5bd39ec2517851e348f613ddb5447a47cf4b71cb09845af7ad7ed45d8f9", size = 8077839, upload-time = "2026-10-05T17:43:48.309Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/2d/4d/4a99fb425c5e0cad715eea7bd190aff46f38b959a0a2dadb993705d34b26/aiohttp-3.14.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:eb0495d778817619273c108784292be161a924b9f5ae5cbbc70a2caa6838250b", size = 765848, upload-time = "2026-07-23T01:52:08.217Z" }, - { url = "https://files.pythonhosted.org/packages/74/e8/43b85dc55b8e950dc644babe762add781319ea881b57b33d2cce12017d12/aiohttp-3.14.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c3c200cf9757edd785051dc699c7ecbec22110dbfcb3fefc7a9f9695eda8ea7a", size = 517476, upload-time = "2026-07-23T01:52:10.846Z" }, - { url = "https://files.pythonhosted.org/packages/7f/9e/73b582c4dbbc3c12ef4473822475effaabf1f934b56f14f5b03fe5d3a2af/aiohttp-3.14.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:fd51ebf9d3a00c074df4ede271023f4d2dba289bcc740b88191872716014e3c5", size = 515334, upload-time = "2026-07-23T01:52:12.636Z" }, - { url = "https://files.pythonhosted.org/packages/79/03/e98c3c9e05a5bdf97defe5ff9169baba4f0ec9a901f2d60e0f060c2f051e/aiohttp-3.14.3-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:134ac5ddcf61c6fad984b9a5727d83492ada43d63471db20fb73042c13fca62f", size = 1708830, upload-time = "2026-07-23T01:52:14.538Z" }, - { url = "https://files.pythonhosted.org/packages/d7/2c/26e60b694844dfd2176c57f913a22d0cd6a16f9ff202cbda7580d0328b98/aiohttp-3.14.3-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:70c987b27534f9ae1a723f47ae921571d616da21d3208282bf4c52af5164ac43", size = 1674012, upload-time = "2026-07-23T01:52:16.486Z" }, - { url = "https://files.pythonhosted.org/packages/38/65/672df92e3172cd876aacfa97a952ac560877eb169384b2991ac5b273de4c/aiohttp-3.14.3-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:1b59533861b70a2185c8f4f350f791f39d64358ef6944ce71c5240c9ec0982c9", size = 1767015, upload-time = "2026-07-23T01:52:18.28Z" }, - { url = "https://files.pythonhosted.org/packages/9e/c5/228dec7bfec1c373cc2217cdeb47d6456dcd7a13a4c55144930a75ae3851/aiohttp-3.14.3-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:1c5281acc88b92396f88c7e1e2748f8466689df22b80170e4f51efa712fb47a8", size = 1858700, upload-time = "2026-07-23T01:52:20.08Z" }, - { url = "https://files.pythonhosted.org/packages/bd/ff/cb36724e8c8d17f90ada567a9ff3efe1d6e9b549fba697a242aece180f21/aiohttp-3.14.3-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:48d67b87db6279c044760787eb01f6413032c2e6f3ba1cafaa492b1c8e578479", size = 1714075, upload-time = "2026-07-23T01:52:22.071Z" }, - { url = "https://files.pythonhosted.org/packages/9f/3a/296a4135c6366376263aeef54b15caca1f07676c2ae0c525d7832f2f808a/aiohttp-3.14.3-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f53bcd52f585e1ac3e590d61434eb61f9a88c38df041b4ea126d97144344a77b", size = 1588234, upload-time = "2026-07-23T01:52:23.757Z" }, - { url = "https://files.pythonhosted.org/packages/7d/81/9d5d853ef892dc066d1eb6db0e87a47348b920c1c879aa554612fdbd9d79/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:0fdea2281997af69da84c77ffa6f5938a0285f21fb3887c249d67419ca865b3d", size = 1677300, upload-time = "2026-07-23T01:52:25.861Z" }, - { url = "https://files.pythonhosted.org/packages/68/96/021d386ae32d9b26d4b88df2e794546232ff56bb6be952bf6be227c0bbc7/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:cda5fd5c95ad7a125a2e8464acc78b98b94c475a3780d6aa0aa157c93f470f4d", size = 1691501, upload-time = "2026-07-23T01:52:28Z" }, - { url = "https://files.pythonhosted.org/packages/29/9f/af66adce26a14af135c003cbd0f44ccaa68cebd30ff8ac99ca47fb4958f7/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:6debfa7312ff9d4c124dc71d72e9a0a4b9e0879e48ba6fcb42bef5c3300289e2", size = 1735113, upload-time = "2026-07-23T01:52:29.995Z" }, - { url = "https://files.pythonhosted.org/packages/2f/90/28c390d4c9851effe52ac25b5a2e1d92246acd00728b4fc7975dafb67484/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:f4e05329faa0ea1a404b37de4f034fd2c2defcca06a68dc6745e4e56c88e8a48", size = 1577486, upload-time = "2026-07-23T01:52:31.937Z" }, - { url = "https://files.pythonhosted.org/packages/db/c2/00e23a1bf2abb70dd353f6987db7e7f2491d0261f7363997738c71c98f95/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:a3a8296e7ab5c295f53f1041487cb088e1480775aafbf7fe545d93b770a0f96f", size = 1751353, upload-time = "2026-07-23T01:52:33.688Z" }, - { url = "https://files.pythonhosted.org/packages/6e/7d/d51a706a8cbfa57f0611127daf61ab3ae02ab8420b0407412079227d1c65/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:5373dc80ad1aa2fb9ad95c83f24eef418bbda3a61375f128e5b0192e4f3f9b32", size = 1698681, upload-time = "2026-07-23T01:52:38.167Z" }, - { url = "https://files.pythonhosted.org/packages/ec/b0/90bd5cd9fdd9787cb4211d284d1fb8401339a933cb0227a15b71e789232f/aiohttp-3.14.3-cp310-cp310-win32.whl", hash = "sha256:a3e22975f905b89a55a488c2a08f2fdb2186175349e917d48985cc468a3d4c6e", size = 456733, upload-time = "2026-07-23T01:52:41.823Z" }, - { url = "https://files.pythonhosted.org/packages/d8/15/fe5b8f6a71ae112bc677163d0b0701bda5dc15005249582258ede0eb88c7/aiohttp-3.14.3-cp310-cp310-win_amd64.whl", hash = "sha256:bdd0e2834dce1a26c1bbe26464861e16bbe217042cbff619247c11594472518c", size = 480460, upload-time = "2026-07-23T01:52:43.905Z" }, - { url = "https://files.pythonhosted.org/packages/54/00/45e98b6645cd7f00a4b78b749ebd309094b0eaeb2d2e96157eadbc0d0050/aiohttp-3.14.3-cp310-cp310-win_arm64.whl", hash = "sha256:eac645b09bcfdf73df7536331f0678c1086ea250981118ddb5199e17ccef72bb", size = 453479, upload-time = "2026-07-23T01:52:46.075Z" }, - { url = "https://files.pythonhosted.org/packages/f8/5c/b3e4ff8ad43a8afef9602c5e90285936da1beaea8b029016b793891f03c3/aiohttp-3.14.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:e568e14940c09955aa51f4e645b6daa18a581c5dcfcd73744dcc86a856e3ced3", size = 764250, upload-time = "2026-07-23T01:52:48.525Z" }, - { url = "https://files.pythonhosted.org/packages/0e/da/f1b384465e51449d844056b75070461da03a9a23e6c1747003695bf4172a/aiohttp-3.14.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:54cfcdee2770dac994417cbb0ee1f3eb0e7cb6b30c79bf44f2c02ff79ec5124a", size = 516281, upload-time = "2026-07-23T01:52:51.047Z" }, - { url = "https://files.pythonhosted.org/packages/b9/3f/01264f820ee2e3712a827892b1cd6ff80f3300c1fcbffbb45714a915d47a/aiohttp-3.14.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:21c016079415ed3fd676963e9793700a566d85dbbd6bfc564b9b2d209147dcc8", size = 514742, upload-time = "2026-07-23T01:52:53.779Z" }, - { url = "https://files.pythonhosted.org/packages/9e/8d/a71c6f2db52ac1ed142b133f7feddaa6b70539c3f4de24d7e226c95b794c/aiohttp-3.14.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d6088ec9894113802bddb3c09e974929aed2c7b3a8c456219b8aab4481f1a239", size = 1780613, upload-time = "2026-07-23T01:52:56.948Z" }, - { url = "https://files.pythonhosted.org/packages/a5/11/3dd9b3fb3a170f6ec9011b5291d876a6fab4086714c9e158600edf01b4fd/aiohttp-3.14.3-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:16ea7e24c309fb7c0bbd505d149abe4fe4dccfb8db911db7dbec0921bc889a6f", size = 1737688, upload-time = "2026-07-23T01:52:59.294Z" }, - { url = "https://files.pythonhosted.org/packages/6d/3e/834c26918be7d88068822b40e0db30fca50b5f4fe79104aa16a93f1d74e6/aiohttp-3.14.3-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:56f355e79f71aef2a85c80305cc915f894b170dba76de5fe84f6351939b83c06", size = 1845742, upload-time = "2026-07-23T01:53:01.641Z" }, - { url = "https://files.pythonhosted.org/packages/cc/c9/49ab8572df7d66bc13d11e31f781292badb04180dd87ba98733066c6aed7/aiohttp-3.14.3-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:18c441d0a8fca6de8d1f546849b9f0ab20d435993e2c5b59562b2fae6be2f929", size = 1928412, upload-time = "2026-07-23T01:53:04.018Z" }, - { url = "https://files.pythonhosted.org/packages/a5/b9/2b8f0c0ce09c87a1daf80fd483431b56b1435d3f62789bc86f572e1245de/aiohttp-3.14.3-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:53e7b4ce82b54a8bcc71b3b67a5cbd177ca1d7f592cbc92cd38b7349f73482db", size = 1786220, upload-time = "2026-07-23T01:53:06.481Z" }, - { url = "https://files.pythonhosted.org/packages/85/00/9c45f81de11710460edfa1dc81317b6e882703b160926c879a9d20da9fcc/aiohttp-3.14.3-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f55119f7bf25f49ed210f6096090715da24f2943c62102448915fde3c62877ce", size = 1637231, upload-time = "2026-07-23T01:53:10.258Z" }, - { url = "https://files.pythonhosted.org/packages/19/ce/967d628e910756f3539c6107cb7844a1b69440dcb3029a5ee7871b09ab63/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:9aa6e61fdf20105c4144e755bd586008ff450791d67b1c8146fdc15959c4d51c", size = 1753161, upload-time = "2026-07-23T01:53:13.817Z" }, - { url = "https://files.pythonhosted.org/packages/11/b2/0c3d4114f0aee4f580f5b3b4eb71b24d7a23b834ea506a4dfebe76513f35/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:ccd4893707b3e2a13e39c90d43cf80edf2e4d0457935bcc103bf2346214c3f15", size = 1756356, upload-time = "2026-07-23T01:53:16.211Z" }, - { url = "https://files.pythonhosted.org/packages/63/5d/99e7d91c82f1399d1ae2a854e080bd1493fbc31e5e959dbc4ec33dac3bec/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:b2466434105a4e03113c36ec775cc2ebe6676b62eae326fa670bb607ef788c1c", size = 1819846, upload-time = "2026-07-23T01:53:18.289Z" }, - { url = "https://files.pythonhosted.org/packages/ad/05/d5e1cb6480eeffd3f901d40a2c5e2d1e7effdc797837da3b490272699f13/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:ba59d59aba08ac02fc03b0c8983ccd5ee39a199d0552ce9e6d2b4845b34d59ae", size = 1628531, upload-time = "2026-07-23T01:53:23.86Z" }, - { url = "https://files.pythonhosted.org/packages/c9/90/b934682bcaefae18a9e04f3dff5b68522ba810906358ae5029b68110ea3b/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:ed099d105449c4f9e84f24af203cd131349d4761d8813fa7e02c32e7128cd910", size = 1832712, upload-time = "2026-07-23T01:53:27.551Z" }, - { url = "https://files.pythonhosted.org/packages/21/df/6061679faaf81fac746e7307c7adb71e858071a5d34c27583afefc64f543/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:152516815ef926786a0b6ae2b8f1fd2e0c71582dee0b435636865316fd4891b7", size = 1775014, upload-time = "2026-07-23T01:53:30.223Z" }, - { url = "https://files.pythonhosted.org/packages/8a/1d/f854878bbc69b88faefe924b619a34a6f59ec05fd387c77690667eaa75eb/aiohttp-3.14.3-cp311-cp311-win32.whl", hash = "sha256:a4af35c443e0b1a1bd6a8af3f3485d7fda15c142751a00f3ff8090f0b93346fa", size = 456006, upload-time = "2026-07-23T01:53:34.97Z" }, - { url = "https://files.pythonhosted.org/packages/73/0c/2af9d1674baccd1dbd47282a93d660a22e57ef6167c856deb24b4214fbab/aiohttp-3.14.3-cp311-cp311-win_amd64.whl", hash = "sha256:e1e74298bab6ee0d6e749ed4fd1901c7e604bdda32c03d787a2cc71c46d0433d", size = 481069, upload-time = "2026-07-23T01:53:39.673Z" }, - { url = "https://files.pythonhosted.org/packages/8e/76/88401ff3fc95e85c5fc38d588f36f55e61ecb64343b2bc8d69326f453cc0/aiohttp-3.14.3-cp311-cp311-win_arm64.whl", hash = "sha256:03cd2bde3d7f085b64e549c985f4bb928cad7e8ecf5323bfca320db548d81b39", size = 453021, upload-time = "2026-07-23T01:53:43.749Z" }, - { url = "https://files.pythonhosted.org/packages/18/d4/eb96299230e20acf2efae207cb8d69051f1f68e357e5ea5e479bf6fb097a/aiohttp-3.14.3-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:39aded8c7f3b935b54aab1d8d73c70ec0ee2d3ec3b943e0e86611bc150ba47f5", size = 754690, upload-time = "2026-07-23T01:53:47.332Z" }, - { url = "https://files.pythonhosted.org/packages/88/11/e7a70a209eb9a067c0d3212b518a0134e3484f5178c7533878b6b514d469/aiohttp-3.14.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:5bcb6ff3fdab1258a192679ff1a05d44f59626430aa05cd1a9d2447423599228", size = 509484, upload-time = "2026-07-23T01:53:51.159Z" }, - { url = "https://files.pythonhosted.org/packages/30/07/4bbc222cc8dbe31d4c3e8a5baad2286e4d42026ac0c570027b89afce6344/aiohttp-3.14.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:617105e2c3018ee38d0c8ce5ee3c84f621a6d8b9f723202aacaff28449ca91ee", size = 511949, upload-time = "2026-07-23T01:53:55.083Z" }, - { url = "https://files.pythonhosted.org/packages/54/b9/42e74c46b7b7c794b995bbc1f573fb48950c38b19d8600c62a6804ee2d67/aiohttp-3.14.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f631fe87a6f30df5fbe6d79640b25e4cffb38c31c7fb6f10871517b84b0f8c1a", size = 1765282, upload-time = "2026-07-23T01:53:59.662Z" }, - { url = "https://files.pythonhosted.org/packages/6b/ed/62bc4d74363ad346d518e0720363a949f63e2e23439a79eb5813d4d29bb3/aiohttp-3.14.3-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:a94dbaae5ae27bd849c93570669bff91e0510f33a80805738e3de72a7be0447b", size = 1741511, upload-time = "2026-07-23T01:54:04.063Z" }, - { url = "https://files.pythonhosted.org/packages/d0/9f/181e8a8bc79e47d13c7fc4540bd7a3b729d9505609c61f392a8dd2fbfe55/aiohttp-3.14.3-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:8f2f1c4c032c7cedd7d8da6f54c97b70266c6570c3108d3fdffee7188bb70529", size = 1810680, upload-time = "2026-07-23T01:54:09.882Z" }, - { url = "https://files.pythonhosted.org/packages/5c/9a/dec94d6ad694552fe3424e3f1928d7a606a5d9d9433a04e7ecdd9d38ae7f/aiohttp-3.14.3-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:ea05e1f97ceea523942d9b2a7d7c0359d781d683d6b043f5943a602b14da4787", size = 1905646, upload-time = "2026-07-23T01:54:13.475Z" }, - { url = "https://files.pythonhosted.org/packages/52/b7/7cd31f29d6055bd711ae6e669367fba6f5ae9de463910a793e30556a8db7/aiohttp-3.14.3-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:543906c127fb1d929b95076db19b83fa2d46751006ff1e23b093aa5ac4d8db42", size = 1792122, upload-time = "2026-07-23T01:54:15.752Z" }, - { url = "https://files.pythonhosted.org/packages/66/73/10b1ef93afa61f4963c746257b70ced619cf31a4798671de5fdb2608501d/aiohttp-3.14.3-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0a5ff2dfbb9ce645fa5b8ef3e02c6c0b9cc3f6030ff863d0c51fffc50cb5541b", size = 1591127, upload-time = "2026-07-23T01:54:19.489Z" }, - { url = "https://files.pythonhosted.org/packages/49/ed/3b203fa6de1b338c14acdc06bf6ca9b043b7944f005966958c2ced932cde/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:041badb8f84396357c4d3ad26de6afd7a32b112f43d3c63045c0c8278cfd2043", size = 1725210, upload-time = "2026-07-23T01:54:24.129Z" }, - { url = "https://files.pythonhosted.org/packages/28/b7/1c2aab8c706436dcc28598452488ac9cd7c409da815237c28c27d58993e6/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:530125ee1163c4219af35dc3aa1206e541e7b31b6efc1a3f93b70a136f65d427", size = 1764848, upload-time = "2026-07-23T01:54:27.973Z" }, - { url = "https://files.pythonhosted.org/packages/54/50/94c28f08b131c4bf10984ea2c7a536c9920608bb2d6e7f95642c30cc87b7/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:c8653fd547c93a61aadc612007790f5555cdd18946fa48cf45e26d8ea4ea473d", size = 1777102, upload-time = "2026-07-23T01:54:31.775Z" }, - { url = "https://files.pythonhosted.org/packages/13/d4/e7d09ba7d345fb2d74440fd2fa033c5e079fac05552927705986f41a364f/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:89176250f686cb9853c0fb7ead90e639e915b84a6f43eedc2a4e7ec21f1037f0", size = 1580205, upload-time = "2026-07-23T01:54:34.518Z" }, - { url = "https://files.pythonhosted.org/packages/a3/84/072a91d68e1e1eb587985b54baab94221277f877e8ef274fc213a0ceae28/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:3a26434dafe408229ff3403458ca58de24fb51936504decac49ce6755f77e59d", size = 1797219, upload-time = "2026-07-23T01:54:36.995Z" }, - { url = "https://files.pythonhosted.org/packages/e0/eb/aad34e897e668424d6e995da5dff8a4a09af93363d3392488772957a63aa/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:d1558173930a5a8d3069cee5c92fc91c87c4dbcb099debbb3622053717145a19", size = 1768629, upload-time = "2026-07-23T01:54:40.103Z" }, - { url = "https://files.pythonhosted.org/packages/b6/2b/6bb88ddba0fecd9122aa3ebcad25996cf6c083a4a7040dbb3a4f97972af6/aiohttp-3.14.3-cp312-cp312-win32.whl", hash = "sha256:16100ad3ab8d649fdfbee87602d9d2dcdca9df0b9eda8a1b5fdc0d41f96da559", size = 451481, upload-time = "2026-07-23T01:54:42.547Z" }, - { url = "https://files.pythonhosted.org/packages/76/9b/f2f8f108da17ecef2cc3efc424e8b7ad3782b1a8360f7b8eae8ced84f6ea/aiohttp-3.14.3-cp312-cp312-win_amd64.whl", hash = "sha256:33a2d7c28d33797a2e99923dffa63f83d908a19b6bf26cfe80fa790aa5e1a75a", size = 476845, upload-time = "2026-07-23T01:54:44.853Z" }, - { url = "https://files.pythonhosted.org/packages/3e/44/28dac80a8941b604f4da10ce21097614ca1bf905ce93dca28d8d7de9c1e7/aiohttp-3.14.3-cp312-cp312-win_arm64.whl", hash = "sha256:362a3fd481769cac1a824514bcd86fda51c65e8fe6e051099e008fddde6db17c", size = 448050, upload-time = "2026-07-23T01:54:47.087Z" }, - { url = "https://files.pythonhosted.org/packages/57/be/5afd201cc0ab139029aadb75392efe85a293403d9dd3a3226161c21ce00c/aiohttp-3.14.3-cp313-cp313-android_21_arm64_v8a.whl", hash = "sha256:2e9878ae68e4a5f1c0abe4dd497dbc3d51946f5837b56759e2a02e78fa90ef86", size = 506269, upload-time = "2026-07-23T01:54:49.075Z" }, - { url = "https://files.pythonhosted.org/packages/22/09/dec8189d62b45ade009f6792a2264b942a90cb88aeaf181239933cd72c3c/aiohttp-3.14.3-cp313-cp313-android_21_x86_64.whl", hash = "sha256:f3d2669fe7dec7fc359ecdb5984b29b50d85d5d00f8c1cb61de4f4a24ee42627", size = 515166, upload-time = "2026-07-23T01:54:51.894Z" }, - { url = "https://files.pythonhosted.org/packages/28/24/2854869d29ed8a8b19d74f9ec6629515f7e04d02dd329d9d179201e58e47/aiohttp-3.14.3-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:cc7cb243a68167172f48c1fd43cee91ec4b1d40cefd190edd43369d1a6bc9c82", size = 486263, upload-time = "2026-07-23T01:54:54.223Z" }, - { url = "https://files.pythonhosted.org/packages/d4/dd/57187c8be2a35aea65eaee3bd2c3dcbbcf0204f5106c89637e3610380cd1/aiohttp-3.14.3-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:78253b573e6ffab5028924fc98bc281aae05445969982a10864bc360dea2016c", size = 492299, upload-time = "2026-07-23T01:54:56.236Z" }, - { url = "https://files.pythonhosted.org/packages/b9/11/06ae6ed8f0d414edf4068861e233d8fe23ee699bfd4b3ceb8663db948a62/aiohttp-3.14.3-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:7041d52c3a7fa20c9e8c182b534704abb19502c8bdcbde7ab23bfda6f642394f", size = 502235, upload-time = "2026-07-23T01:54:58.377Z" }, - { url = "https://files.pythonhosted.org/packages/7e/a3/559639c34a345d2cf7c52dff6838119f2eaf29eb508227b5b83f573af813/aiohttp-3.14.3-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:ac74facc01463f138b0da5580329cfcc82818dea5656e83ddcd11268fc12ff80", size = 750883, upload-time = "2026-07-23T01:55:00.65Z" }, - { url = "https://files.pythonhosted.org/packages/91/cd/41e131f13afd1e7b0172a9d9eda085ef90eb8439f41f0d279db81ed3ae60/aiohttp-3.14.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:d6218d92e450824e9b4881f44e8c09f1853b490f9a64130801024a4793b1b3b0", size = 508473, upload-time = "2026-07-23T01:55:02.945Z" }, - { url = "https://files.pythonhosted.org/packages/bc/6b/e7f13410d391c6e55b4c007a8de024355389d7d459e3d64c42b2d33617e5/aiohttp-3.14.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:11fb37ef075669eee52ab1928fbf6e1741fada40409fa309ebde9607a962aebf", size = 509190, upload-time = "2026-07-23T01:55:05.173Z" }, - { url = "https://files.pythonhosted.org/packages/97/21/6464573e53d69672cc1eada3e5c5cb2d2efa82701e8305a0f2047a576967/aiohttp-3.14.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:55bdcc472aafe2de4a253045cc128007a64f1e0264fb675791e132ea5edaa3bd", size = 1761478, upload-time = "2026-07-23T01:55:07.383Z" }, - { url = "https://files.pythonhosted.org/packages/1a/81/d217043a4c17fbce360905e3b2bdd20139ebc9a2de836d035d179c4da006/aiohttp-3.14.3-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:c39846c3aad97a8530c89d7a3869a8f8e9e3762c6ac0504481e5c80948f7e807", size = 1735092, upload-time = "2026-07-23T01:55:09.803Z" }, - { url = "https://files.pythonhosted.org/packages/a1/66/e13a02d0eeb1a9a502402a977abb4e4abff9fe4051c26f80558c57a7c975/aiohttp-3.14.3-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:5895ef58c4620afe02fa16044f023dc4dafec08158f9d08874a46a7dbc0341b8", size = 1800546, upload-time = "2026-07-23T01:55:12.012Z" }, - { url = "https://files.pythonhosted.org/packages/26/5e/57d42fca1d18cb5acc1cad945d017fabc5d6ae71d8a08ad66be8dc3ee544/aiohttp-3.14.3-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:fa9467a8113aa69d3d7c55a70ef0b7c636010a40993f3df9d9d0d73b3eb7ef24", size = 1895250, upload-time = "2026-07-23T01:55:14.357Z" }, - { url = "https://files.pythonhosted.org/packages/ca/1c/7da8d08e74d56f00070822f9638ff3f1c563f8ad87d1efa996c87bfc8644/aiohttp-3.14.3-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d7d2deec16eeedf55f2c7cf75b521ea3856a5177e123844f8fd0f114ce252cb5", size = 1789289, upload-time = "2026-07-23T01:55:16.668Z" }, - { url = "https://files.pythonhosted.org/packages/cd/0f/cf16bcf56896981c1a0319f5d5db9337994b5165730c48a8fa07e9b34be6/aiohttp-3.14.3-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:dd54d0e8717de95939766febac482ac0474d8ac3b048115f9f2b1d23a16e7db4", size = 1586706, upload-time = "2026-07-23T01:55:18.913Z" }, - { url = "https://files.pythonhosted.org/packages/fe/6f/76eac12a7f2480e1e304f842efdb07db33256b0d9165b866b6ef0806c202/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:df82f3787c940c94986b34222d59c9e38843fba85139f36e85255a82ad5355a9", size = 1724652, upload-time = "2026-07-23T01:55:21.296Z" }, - { url = "https://files.pythonhosted.org/packages/39/b6/19c8c592baeeb94b75f966547d40c02ac7590902306ec5863d5c027cf506/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:42a67efc36300d052fb4508a53e8b6901b9284b599ae63945c377569c5fcc1e1", size = 1756239, upload-time = "2026-07-23T01:55:23.705Z" }, - { url = "https://files.pythonhosted.org/packages/dc/c9/4e9383150296f97f873b680c4de8fb2cd88608fb9f48c79edcb111611abc/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:7a75aa63cbf9b21cfaf60dc2657e19df2c2867d91707d653fee171ffeedd1371", size = 1769161, upload-time = "2026-07-23T01:55:26.082Z" }, - { url = "https://files.pythonhosted.org/packages/aa/1e/147bdc6cc5de5f3ab011be8bf5d6e786633249f22c20bae06f85e45f5387/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:e92eb8acc45eb6a9f4935071a77edf5b85cc6f8dfad5cd99e97653c26593cdde", size = 1578759, upload-time = "2026-07-23T01:55:28.846Z" }, - { url = "https://files.pythonhosted.org/packages/fd/31/78388a9d6040ece2e11df62ea229a822cf5e52d238374b220ae9975b2623/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:b014a6ed7cf912e787149fdc529166d3ceabac23f26efeea3158c9aba2354e7e", size = 1792025, upload-time = "2026-07-23T01:55:31.457Z" }, - { url = "https://files.pythonhosted.org/packages/03/51/a3d29fdf2c25d796746af8ad6fe56a45d6256c38b0a8a2ed752e1160b3a2/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:3d4f72af88ac2474bb5bca640030320e3d38a0163a1d7533500e87be458eef71", size = 1768477, upload-time = "2026-07-23T01:55:33.87Z" }, - { url = "https://files.pythonhosted.org/packages/29/a6/442e18b5afeade534d877a2dc3c3e392aff8d49787890b0cf84790410267/aiohttp-3.14.3-cp313-cp313-win32.whl", hash = "sha256:5f08ec777f35ee70720233b8b9811d3bb5d728137f30ac91b7457709c3261ac0", size = 451069, upload-time = "2026-07-23T01:55:36.121Z" }, - { url = "https://files.pythonhosted.org/packages/9d/69/3d876ac02659f271cf7f6769f14a8e3de5b6e888ed8b5a7e998086a4cec8/aiohttp-3.14.3-cp313-cp313-win_amd64.whl", hash = "sha256:dff9461ec275f22135650d5ba4b4931a11f3958df7dfbb8db630000d4dee0883", size = 476518, upload-time = "2026-07-23T01:55:38.303Z" }, - { url = "https://files.pythonhosted.org/packages/b2/0e/50d6e6471cd31edce8b282bdec59375a3a69124d8a989a0b1313355cae52/aiohttp-3.14.3-cp313-cp313-win_arm64.whl", hash = "sha256:ddcac3c6b382e81f1dd0499199d4136b877beb4cb5ef770bbbfba56c4b8f55d2", size = 447676, upload-time = "2026-07-23T01:55:40.451Z" }, - { url = "https://files.pythonhosted.org/packages/c8/20/887fdcf832326571b370ffc347b3e70abe101096f3720126aac161b1d872/aiohttp-3.14.3-cp314-cp314-android_24_arm64_v8a.whl", hash = "sha256:49f7325beb0f85ef4aef5f48f490269575f83e6e2acad00a1d80b807eb027062", size = 509067, upload-time = "2026-07-23T01:55:42.618Z" }, - { url = "https://files.pythonhosted.org/packages/ad/a3/92cec936f78cc4bf0fa5554ebe593b73459d94e3c62303e1902a4cccb6f7/aiohttp-3.14.3-cp314-cp314-android_24_x86_64.whl", hash = "sha256:e3be98a7c30b8c25d573dafba7171d66dfb05ee6a9070fc46535464ff97700a6", size = 514774, upload-time = "2026-07-23T01:55:44.937Z" }, - { url = "https://files.pythonhosted.org/packages/29/ba/2a0c38df3fc557620b6a5acd98364af050053b6285b4dc7ee74100c63c18/aiohttp-3.14.3-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:614c61d478b83953e261d02bb2df750f17227cd33ef8002945bf5aebbde21919", size = 488134, upload-time = "2026-07-23T01:55:47.135Z" }, - { url = "https://files.pythonhosted.org/packages/48/d6/d51b7d4bf309af3693940d8ffd2b9ed0b682434ef85959b7c9c137f60cf8/aiohttp-3.14.3-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:1caa7b0d05f3e3a36f87788c59e970a7ee1cefcfcbb924a9f138c4a6551c9cb7", size = 494201, upload-time = "2026-07-23T01:55:49.451Z" }, - { url = "https://files.pythonhosted.org/packages/3f/5a/8f624384e5f1efabb5229b94157eb966b021e97bdb188c62860c2ae243c2/aiohttp-3.14.3-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:dfa68deb2a443bdaa3ea5297b0699c1464f08aef3812b486d1348eee61b07dc0", size = 502766, upload-time = "2026-07-23T01:55:51.656Z" }, - { url = "https://files.pythonhosted.org/packages/a6/26/4ff0164370deec18fb19254ee4ab10b7a73304ac0c860b13f5f84663759b/aiohttp-3.14.3-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:e72ee89e28d907a18f46959b4eb0bb06701cc7f8cf4366e00029e2ccfaaf5924", size = 756557, upload-time = "2026-07-23T01:55:53.964Z" }, - { url = "https://files.pythonhosted.org/packages/97/a3/7056b86dc0d9ec709ea9777eae3b0161428f943372f8b98c01c11593b682/aiohttp-3.14.3-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:ad4c8b7488d745d2ca4838ebd8ae5ba9b56341d30b1da43640e4ce87f9f49646", size = 510168, upload-time = "2026-07-23T01:55:56.22Z" }, - { url = "https://files.pythonhosted.org/packages/85/ed/0357a015892fd68058bf2d39d3fd1958e459b997a7db30aaa6aaa434ae96/aiohttp-3.14.3-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:db332af25642007330fca8be5c4d194caf2bea7a7fc84415aff3497af5dfee6b", size = 512957, upload-time = "2026-07-23T01:55:58.437Z" }, - { url = "https://files.pythonhosted.org/packages/47/d1/8aba53f15ccb2238405f5e9d30e2a8ca44f93878c26e7165ade00d374b1c/aiohttp-3.14.3-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:25bd2708db6bdf6a6630dd37bdcdfcb47c4434d22ac69c64665b802910140b30", size = 1750149, upload-time = "2026-07-23T01:56:00.856Z" }, - { url = "https://files.pythonhosted.org/packages/49/bd/40c3fee327529284375c6701cbb0fa4600cc2e8432af1378f897e2ef7d3a/aiohttp-3.14.3-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:cef89a58e628c4efcac3275c2d68083f82426dcdc89c1492a6f654f9f7ea6ab9", size = 1707685, upload-time = "2026-07-23T01:56:03.371Z" }, - { url = "https://files.pythonhosted.org/packages/2a/a3/ca0cc6724cca8114b05694abd916060758c79894c3aa5b012cdadc1bc28e/aiohttp-3.14.3-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:c23ec8ee9d5ab2f5421f9c7fffce208435607af27fd46d4a44e031954352838f", size = 1803911, upload-time = "2026-07-23T01:56:05.817Z" }, - { url = "https://files.pythonhosted.org/packages/95/b5/85b099c299c3ffd38ad9b3e43694c8a346934e4a30c88c4fd5a841234f77/aiohttp-3.14.3-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:e2667f0bbe7eb6c74eae5e9691441ad186e5845ca3cff63230fc09c4e7514f5d", size = 1876929, upload-time = "2026-07-23T01:56:08.413Z" }, - { url = "https://files.pythonhosted.org/packages/d5/b7/1da684a04175473fa4cddbf9a2f572e79514c3fd27a74597f43057d4f3da/aiohttp-3.14.3-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:18cb43369747b2ae007bd2655fb8e63a099c2ff1d207962943636dac989b3147", size = 1761112, upload-time = "2026-07-23T01:56:10.918Z" }, - { url = "https://files.pythonhosted.org/packages/d1/16/bc4b55e3e5cb175fd69c53c90d60d2f47797cb343da5106e23863dc4dba4/aiohttp-3.14.3-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:d77640cc618c1d99fc4f8589c0f24a730adfa54eb1e57ef7bf0c8dfb78da898c", size = 1583500, upload-time = "2026-07-23T01:56:13.613Z" }, - { url = "https://files.pythonhosted.org/packages/2a/e8/13a9d957a1ee40837f46aa30f0f4c657e673ad86a2e6362a9f9be20d26d9/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:53e5179d8abb5710f8e83ba207c41c8d1261fcffd4616500e15ca2b7a33be10a", size = 1713940, upload-time = "2026-07-23T01:56:15.969Z" }, - { url = "https://files.pythonhosted.org/packages/38/05/d33c680c1bcf1c7e130f9cbfc1fc02fe8bb0c4af2a94a53dd5fb56131e5c/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:cd817772b2fcf2b8c0905795318485f9ec16eae60b29feb7f4c77085311637f0", size = 1724413, upload-time = "2026-07-23T01:56:18.591Z" }, - { url = "https://files.pythonhosted.org/packages/85/1d/af798d306f7a74b6a632dbcabcf62a4c91391b7582d2a8c6d7712e2cc54e/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:4e3ac92d90e92773b2362d506068e9a948192bd553e743c5b2429e28527c8661", size = 1770748, upload-time = "2026-07-23T01:56:21.074Z" }, - { url = "https://files.pythonhosted.org/packages/a8/92/ad720d472556a995049206867765e9410969684f86ee09423ff9969044c1/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:3f42e9b78301f11c8f861746175d8b9c1ccef713fcad9eab396e2f6db8ed4a22", size = 1577564, upload-time = "2026-07-23T01:56:23.475Z" }, - { url = "https://files.pythonhosted.org/packages/60/ad/0ed7586cbef7a884e23a752fa2bb987a122e6a5dd50dab109258d0a95193/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:9d9edccfe496b476db5f398d97b865e9a6752bcf8aec4eef8390ce20fb64bb41", size = 1782080, upload-time = "2026-07-23T01:56:25.994Z" }, - { url = "https://files.pythonhosted.org/packages/97/ea/dbaed0d73e8a69aad653b045dab451c67c2454bb731a37b45a86593e9422/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:1c5ec8fb1bcc31a8466f74aaf26c345d5c386fa4bd08a3f0eb9c7a4a3fe8b5bf", size = 1745813, upload-time = "2026-07-23T01:56:28.604Z" }, - { url = "https://files.pythonhosted.org/packages/81/1b/6893d4bc57e434fc93a6c9217c637d967a0b651d989f6e3265179375754a/aiohttp-3.14.3-cp314-cp314-win32.whl", hash = "sha256:38901a84da3ce22249f6e860bf8f90d141bcab7da090cc398f8bb58c0e44b7da", size = 455872, upload-time = "2026-07-23T01:56:31.031Z" }, - { url = "https://files.pythonhosted.org/packages/f5/8b/c7baa1ba1eda4db6989baefe5de6d99834921b84ebd7918624febcb9f290/aiohttp-3.14.3-cp314-cp314-win_amd64.whl", hash = "sha256:8b3b60de05f3dcb6f6a00f818bb2ec781cee4de0645f59ccaf99b1d1823b6100", size = 481030, upload-time = "2026-07-23T01:56:33.365Z" }, - { url = "https://files.pythonhosted.org/packages/22/8c/c29d067df825a2df88ca432db848aa2fe8199598359cc06c12b09320cac9/aiohttp-3.14.3-cp314-cp314-win_arm64.whl", hash = "sha256:1576145bdceeb92382d899751e12743a3a5b8e460a841e3e50543859e54864dc", size = 453669, upload-time = "2026-07-23T01:56:35.731Z" }, - { url = "https://files.pythonhosted.org/packages/6a/a4/9c033beb355d39b6147980597ec9645e4729243f686ee4dc73945de72030/aiohttp-3.14.3-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:8800c996b01c2772a783e3e46f3e1abd5823029adca0df54231960de9bfefa5b", size = 791403, upload-time = "2026-07-23T01:56:37.972Z" }, - { url = "https://files.pythonhosted.org/packages/80/ca/87c32a0a7704583cfc49660bd817889bae5b830bf53b5dcb4e92145ac2da/aiohttp-3.14.3-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:ebe8e504f058fe91223351cecd2d9d6946c9d241bb0250d898ffbdf584cc72b0", size = 526413, upload-time = "2026-07-23T01:56:40.523Z" }, - { url = "https://files.pythonhosted.org/packages/9e/d8/8ec0e471248c500acdce2be3f46db8fb62b5eb60efef072529cc85ee1d26/aiohttp-3.14.3-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:30402d03a7c0ff52bce290b57e564e9079fd9d0cb545c8aba73f86a103162d2e", size = 532135, upload-time = "2026-07-23T01:56:42.876Z" }, - { url = "https://files.pythonhosted.org/packages/fe/45/f8919fd936e8b79fcd9bda7b6d8e62613462a713f4f17987fd7c34399142/aiohttp-3.14.3-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9fc7b5bfec6573f3ae844f457fdde5adeb713f8b8e4a81ad64fc207b49383716", size = 1922742, upload-time = "2026-07-23T01:56:45.528Z" }, - { url = "https://files.pythonhosted.org/packages/f6/ec/9ca76b28a27525b0cc53e20842e0228b022f301ce1f436b7d814b4aaf2df/aiohttp-3.14.3-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:8a5fd34f7f7410d1730d5c2ba873cacb2eed3fede366feb268a70ba22581ed8f", size = 1787371, upload-time = "2026-07-23T01:56:48.045Z" }, - { url = "https://files.pythonhosted.org/packages/b1/04/6acdbf17315f7b55f1937e3387acb89a3cddeb4995689553d064af8e92ab/aiohttp-3.14.3-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:270d3dace9ca2f10f0da5d8ebe519b7a310fc6112ed916e32df5866df0888553", size = 1912623, upload-time = "2026-07-23T01:56:50.605Z" }, - { url = "https://files.pythonhosted.org/packages/86/e6/438b0c79ca6f45eb9fd9817dd4c01a91919a38c0de5ee9e05e2b4dc0ece7/aiohttp-3.14.3-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:3ae5b3a59436d089b5395d910121a390feed4d00578eb95a0fd1a329fe963100", size = 2005515, upload-time = "2026-07-23T01:56:53.153Z" }, - { url = "https://files.pythonhosted.org/packages/bb/6b/62cbd6577758699525f5c712d1ddef57d9875fbab0ae8d5f5a202fd598f8/aiohttp-3.14.3-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2498f0fe69ead802f9675beca44a7c21c62fdaa4ec5145ea1c3ad6edbee29f85", size = 1879906, upload-time = "2026-07-23T01:56:55.818Z" }, - { url = "https://files.pythonhosted.org/packages/00/95/18bcbf830a21dc3aae24d8f6b6feaf3db1d2090242d00a7868db2ffb0b67/aiohttp-3.14.3-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:a0dc483c00da8b673abbb367eb6f8d8f4bcec30eb58529ea13cb42e7fd2dfa33", size = 1675849, upload-time = "2026-07-23T01:56:58.861Z" }, - { url = "https://files.pythonhosted.org/packages/a9/19/47f4968659c5e23606c3790c80fc624e691c153d036148449ee84d31b287/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:c7d3a97c678d34fc5b59da671ee9cd630096ddc643e7b5a30d54a2a6f3574d3f", size = 1843496, upload-time = "2026-07-23T01:57:01.591Z" }, - { url = "https://files.pythonhosted.org/packages/64/af/38c33c4dd82fddcb4e56c4653b6f1072a8edbc6b7fa15809f14932c41e2d/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:f8fb78a83c9e5f741ca3a68cfb455c1f5bb83b4e7249a3848b3cd78d0a8563b0", size = 1827746, upload-time = "2026-07-23T01:57:05.131Z" }, - { url = "https://files.pythonhosted.org/packages/a1/9d/0537cda4885ac8f5b7053d164dd06312f4c483a4edcb8ee5b8aaf2a989bf/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:74ab5b6a9fb13e873e5a90946588baecaf488745e1db1a4a5c433f971f035098", size = 1853810, upload-time = "2026-07-23T01:57:08.043Z" }, - { url = "https://files.pythonhosted.org/packages/19/fe/26f9c5e6458385aa86497836b0dea6fb2f027827d63f37c7856cce9286ee/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:bd52f811e65f6fb634b1047159657c98f52b407f8efec907bcfc09da9a4c0a25", size = 1668895, upload-time = "2026-07-23T01:57:10.837Z" }, - { url = "https://files.pythonhosted.org/packages/ec/4c/618b1db9b9ba079b8875d2cdf78e7c4a3bf72903bd5850fee7dd9544600a/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:f0f177d1b195b9e06376cfd7d308d8a1b920909a609d03ac82a8c73bbb16d3b9", size = 1883833, upload-time = "2026-07-23T01:57:13.672Z" }, - { url = "https://files.pythonhosted.org/packages/94/c6/bd959bd1e4771f9fd944e9e436224c48c77b018b73b519b5aad346335bcc/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:498c6c623134f8e09a3c4e60bcd607a0b4590dd7dbf08dd40851b27cbb520ccb", size = 1844251, upload-time = "2026-07-23T01:57:16.593Z" }, - { url = "https://files.pythonhosted.org/packages/5e/19/08d41839658bdd44a0ed2480f3891705ecb487ce28c0dde62c9040c997e0/aiohttp-3.14.3-cp314-cp314t-win32.whl", hash = "sha256:b304db572b4368edd8dda8a2274f73156fe15558fca4a917cb8a09fc47af5963", size = 474180, upload-time = "2026-07-23T01:57:19.306Z" }, - { url = "https://files.pythonhosted.org/packages/99/5d/3cd6ef0a2b2851f7ab913b5b079334781bd50ff56a323e4454063377a080/aiohttp-3.14.3-cp314-cp314t-win_amd64.whl", hash = "sha256:b20032766aedf6261c7a566585a40867d092ac03a0d81592d5370ef9b054f99b", size = 500528, upload-time = "2026-07-23T01:57:21.762Z" }, - { url = "https://files.pythonhosted.org/packages/a4/37/cfd1ed540a4d318da025590d96b728e63713c09e9377950fc655dadeb856/aiohttp-3.14.3-cp314-cp314t-win_arm64.whl", hash = "sha256:2e1161602f45a54de2ce0905243a95f58cb42dcd378402f3697f5e0b21e9d2e7", size = 469280, upload-time = "2026-07-23T01:57:24.241Z" }, + { url = "https://files.pythonhosted.org/packages/b3/08/290e4be6e3ed239751c446505c324406a4ae8a82a15009a12a3c550f18d9/aiohttp-3.14.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:dea3b3653c1d0d6babd8ce09cb9e5a7776864315d9cfb1c569f926389874a261", size = 834853, upload-time = "2026-10-05T17:37:45.079Z" }, + { url = "https://files.pythonhosted.org/packages/81/81/ed5e04508ba1fcf9a34e0449c78009956e8256f62ebef708e2948594cf94/aiohttp-3.14.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:3099a389e5b5900fc79c6f613015ff3f8fa06a519744e6001cc68a31ba418cac", size = 560957, upload-time = "2026-10-05T17:37:47.497Z" }, + { url = "https://files.pythonhosted.org/packages/90/28/1a91411c53704db0481cc64b0f0c9465aa9d738856abdcaa3a5bbbe18180/aiohttp-3.14.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:70247156fc76e92919f9aacb820556cb30289a54784299a31714d030bb604d84", size = 553475, upload-time = "2026-10-05T17:37:49.099Z" }, + { url = "https://files.pythonhosted.org/packages/cf/2e/1038f3fa8832f9f4bed0f9f751f70dbc52bc4a09c66788f97bbfb0ce3d88/aiohttp-3.14.4-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:fdf2d2a6ad402797422949f4a200a60d43e3a021695c8a7804aa1d5bbef22652", size = 1845211, upload-time = "2026-10-05T17:37:50.728Z" }, + { url = "https://files.pythonhosted.org/packages/ea/54/e2253f17604c5c1c69a05e3c12400b51cd6a5fb32d7175592114d8c7a470/aiohttp-3.14.4-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:ba835fad8d4b5eaea0d34f9461cf499737a720a5f8bc6768d2f6d98a1d3ba8b5", size = 1814629, upload-time = "2026-10-05T17:37:52.481Z" }, + { url = "https://files.pythonhosted.org/packages/f1/ef/7bd1e45db925376720555d7268c2d642b113105263d37a522e41e1ba3a6c/aiohttp-3.14.4-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:0d4415ca5c9c8b24bc2f5733f870d4eab4929e680203559ba60131dd1a27852a", size = 1898528, upload-time = "2026-10-05T17:37:54.078Z" }, + { url = "https://files.pythonhosted.org/packages/5d/40/26d09668e7e0cadc16027566765aa4ce26e8a41276bad6764848c8b04d11/aiohttp-3.14.4-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:f6757e02c2c2b0d7985f57be87cf4a7c5b35708f849e1feaea3f77656ddb9dff", size = 2024385, upload-time = "2026-10-05T17:37:55.626Z" }, + { url = "https://files.pythonhosted.org/packages/73/38/0f1c4aab1cc9518e1bf874e2481e59e541b3e32330b9542e52bb2712f86f/aiohttp-3.14.4-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2a950bd8418ef54eccf5f9f517f08e37c1adab4bc50a470a0422ee1cc1032e29", size = 1859130, upload-time = "2026-10-05T17:37:57.342Z" }, + { url = "https://files.pythonhosted.org/packages/5f/98/09d5998ba4b5fe9f0cb97d794fab9d1b3d8245c5ec6a5fb84e41a8cec142/aiohttp-3.14.4-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:34cf6f2fe4fc1d7183e8cc0d8c48bbdda828a740bc372d8278126149714d343c", size = 1714768, upload-time = "2026-10-05T17:37:58.831Z" }, + { url = "https://files.pythonhosted.org/packages/c2/63/39d01a74d525d6443084d47ad4aa8c719f44a030149d03566f3761527465/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:bc0fbe4f79c3b156d754dd062718ffe404c3b31ca878d9d2b88ecdbc72ef8369", size = 1813228, upload-time = "2026-10-05T17:38:00.611Z" }, + { url = "https://files.pythonhosted.org/packages/39/6b/183d7b969bdb7892e86af74147b4afedbb4e03b8cad5006e41aa2034c288/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:d3d50a5a07a2b31a4369b86dd4a3acf3c2577c45091dbd5e884b198dec56480b", size = 1831844, upload-time = "2026-10-05T17:38:02.272Z" }, + { url = "https://files.pythonhosted.org/packages/2c/be/4c6df02b62083efd3f008974cf9016a4afd2023f5a9d2c3fd55499fcbac6/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:de15c46a63f46da881d219e44a04778c40114c756e5575b5ea38143b20eb3713", size = 1868738, upload-time = "2026-10-05T17:38:03.831Z" }, + { url = "https://files.pythonhosted.org/packages/86/21/406be8b0cf1105a35a6a6da16a95796be39b354e29bfca0d1626d822835f/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:caa4c0fc9b25e8c679baac68337e9c00deb6baf6601fe6f07e8511469cc1ceba", size = 1700006, upload-time = "2026-10-05T17:38:05.631Z" }, + { url = "https://files.pythonhosted.org/packages/4e/e6/beac98020ea0885ea1ee3b2ef59ec952405590fe2ccef2fa4ef7614c3c2b/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:3647f8c090632c70abb1e80826e4ee24faea3f895f0283b60e91a0b17aea5e34", size = 1889997, upload-time = "2026-10-05T17:38:07.578Z" }, + { url = "https://files.pythonhosted.org/packages/c4/89/d608dd9571988a529c7fead5bc79ad36b56fd52bad7941f40774acbc87e9/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:3f3e8030169843fb652a60a3d32c206e03f260198aa398985a48b41cd7e42f0a", size = 1844619, upload-time = "2026-10-05T17:38:10.003Z" }, + { url = "https://files.pythonhosted.org/packages/7e/7d/7f51e6338d2c74b75173ee66fcb50d778d5407c32f34e76ef1c4b25d0d75/aiohttp-3.14.4-cp310-cp310-win32.whl", hash = "sha256:a1205cbdddfca1428129bb6d23e0b292b09e681df951fa828145d83a63ffc0ca", size = 489598, upload-time = "2026-10-05T17:38:11.795Z" }, + { url = "https://files.pythonhosted.org/packages/33/2a/3434e450a4395fc07f3070d6ac24553f0b170b173e949216b1723395028c/aiohttp-3.14.4-cp310-cp310-win_amd64.whl", hash = "sha256:e90980e0454a043f81b435309a089ac5deab883779557eb58d004f33990f61e4", size = 512204, upload-time = "2026-10-05T17:38:13.309Z" }, + { url = "https://files.pythonhosted.org/packages/53/c0/1d89303cf1bea5418268c1cb82b872661bad027e5fd785c2d30d0a31ee6f/aiohttp-3.14.4-cp310-cp310-win_arm64.whl", hash = "sha256:e63eecf9a4b670a24055d5c0486128af16f83b02d9817abd685d3238940f8752", size = 492725, upload-time = "2026-10-05T17:38:14.825Z" }, + { url = "https://files.pythonhosted.org/packages/81/e3/998dc75634ecd2a24f33bab480b57313059d55bcadff8825a46b7c80a8af/aiohttp-3.14.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:eb0093ca0817019d539f0d27bdf98e823944e05bb7efd9d2337a45b92e4d1b06", size = 832892, upload-time = "2026-10-05T17:38:16.373Z" }, + { url = "https://files.pythonhosted.org/packages/58/c9/9bacc26397854440d169f70ae00ea51721f504611d3a64cf043643792c32/aiohttp-3.14.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f482dc9c8309801b4259dd218609d3dae0a7bcdedeac56d90500eabaa0c23465", size = 559893, upload-time = "2026-10-05T17:38:18.74Z" }, + { url = "https://files.pythonhosted.org/packages/fa/f3/90c5856014328a8b1e9a753de794edea282182b776ff65f0602ad4ffa520/aiohttp-3.14.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:aa800bb7c1d00e166493931f2ddacb982db913292503dc2f4884db1f2bc5f105", size = 552850, upload-time = "2026-10-05T17:38:20.385Z" }, + { url = "https://files.pythonhosted.org/packages/9b/88/e71c29ce6daa78fcee0feb1992f0fdc408f09f42c3311b1f1c68c36f16ea/aiohttp-3.14.4-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d90e4dae71b26597f6d1fd12af7d092ae67551edf0e524b73e0687214b79ee33", size = 1928941, upload-time = "2026-10-05T17:38:22.218Z" }, + { url = "https://files.pythonhosted.org/packages/3a/4f/f0f3bebfa521a2ce5fd4302c937701cbc50cd6d908beaa597388639b0b98/aiohttp-3.14.4-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:5b681054b8c3b86aa6a0384b6ad7f5cb78dccbabab1f4a3a6793f98ad1378959", size = 1882092, upload-time = "2026-10-05T17:38:24.016Z" }, + { url = "https://files.pythonhosted.org/packages/b5/0d/5df041fd25dceb4f4cafbbee49bb2c1e2d54a91aedecaf03b77cbb404c44/aiohttp-3.14.4-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6dfe80b41bcf8d80d2125fb99a171adeb86db2fcb35c1a68e0226acba0ba7f03", size = 1986051, upload-time = "2026-10-05T17:38:26.022Z" }, + { url = "https://files.pythonhosted.org/packages/1a/07/e95eddafffef7c3a74446f67ac4e477a49cec2c78f2ab6c86d1acfd90d2d/aiohttp-3.14.4-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:71e4a59c6a8c5a6ae8b0b696c32635913e8f526cc01448762eaf5a3c59df8a4f", size = 2107840, upload-time = "2026-10-05T17:38:28.112Z" }, + { url = "https://files.pythonhosted.org/packages/da/6c/1f83990fea249dcb10f48086726953546efc9199c96b6be7114532ac361f/aiohttp-3.14.4-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f887c3b7fb3058fc1ccd917f52078540c18d938d12018cb9edd64b6811d20c57", size = 1930721, upload-time = "2026-10-05T17:38:30.046Z" }, + { url = "https://files.pythonhosted.org/packages/6f/d1/48184a186ea26df4f81dd466144dcab7f9cdd1e131bfee0f0e41278c6f0d/aiohttp-3.14.4-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0da4525e9ba145a11617d2cd7e44fe1acaf471f9c72a0cad28e72879c1020fbb", size = 1774508, upload-time = "2026-10-05T17:38:31.8Z" }, + { url = "https://files.pythonhosted.org/packages/0f/ef/a9ec758c6d3850453838c31b56d1e4499eb47c80883753a12dcb203f9afa/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:f7e8d3c5caa44fdbee3eba1aa1417aa58c74c95d4089fe3c451911117fcbb2f3", size = 1902311, upload-time = "2026-10-05T17:38:33.791Z" }, + { url = "https://files.pythonhosted.org/packages/d6/49/9a2be54900f2dea6e63bbf9628fced604686a2e301130ccde0b1aa2e7e53/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:09092cf906c18c824b6b16881da5a89cc9cfa9b15344e496bcf880e9045bee33", size = 1912107, upload-time = "2026-10-05T17:38:35.614Z" }, + { url = "https://files.pythonhosted.org/packages/a2/2b/151254abfc0fe5cbb8e6c41ad04d52122db0af176fb31dbf3bc44e081bda/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:dfd144837e92264878bba6d3a7ffa8206668b21e87748740afd45d193e48c87e", size = 1960207, upload-time = "2026-10-05T17:38:37.322Z" }, + { url = "https://files.pythonhosted.org/packages/23/99/92c8dce336ac5784755a3144623528516f2e3b6b4871d02cad5a0642ae66/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:9413cffe4e0d654b9b524f9c99dde8cbdb37e0ed9a2c4edd2e63adbac6b374e8", size = 1760168, upload-time = "2026-10-05T17:38:39.214Z" }, + { url = "https://files.pythonhosted.org/packages/66/3e/f05fd8d1a9595730db8d522882eea76429b9be2ed5337609f7c6e3d9d49c/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:f50d719f97ba488dfb8e306cf8c8cc172ff0683ec0af53917b288229aa555ba5", size = 1979946, upload-time = "2026-10-05T17:38:40.927Z" }, + { url = "https://files.pythonhosted.org/packages/b9/14/8941aa73ffceabc2a0eb26878b4f1b2958fb7b5358f97cc49b1c00ed9258/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:68ed4824d96b7afec1f3a8d7fba190fe282718041c5772e20298003e1e3e5d66", size = 1923375, upload-time = "2026-10-05T17:38:43.184Z" }, + { url = "https://files.pythonhosted.org/packages/18/b5/ef275b63c8bfe0a21e7e8d3ef0e67c4745ed403f1894fe5205057cedd3b9/aiohttp-3.14.4-cp311-cp311-win32.whl", hash = "sha256:d7a41d1427136828e6b11d3f3fd194d4357d5205a5b610be7ae07b1ba52ab974", size = 488414, upload-time = "2026-10-05T17:38:44.978Z" }, + { url = "https://files.pythonhosted.org/packages/e7/0b/21bdd70a1e072222d9dbd96bed4fbed26f7c46c5a20af11b78d32fd049d6/aiohttp-3.14.4-cp311-cp311-win_amd64.whl", hash = "sha256:2efbdb87e79d596325c4eefaef0f4495d701145e882351310ebc538e854dc7a3", size = 512755, upload-time = "2026-10-05T17:38:47.036Z" }, + { url = "https://files.pythonhosted.org/packages/b7/4c/bb324a7d20a9598187bb028ca8d6bcf66c63589c8632420919dd576964ed/aiohttp-3.14.4-cp311-cp311-win_arm64.whl", hash = "sha256:ac6e6f90d9360e460c873f945f11dc8698db0a71fec6612823f1aaaab2c11faa", size = 492960, upload-time = "2026-10-05T17:38:49.006Z" }, + { url = "https://files.pythonhosted.org/packages/22/02/db5935d45347fa8ede56b777930740fb0e72bbb4473ddb6ff8541f6f2afa/aiohttp-3.14.4-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:55b0b335982b0db7117dff7f6a8e3aad43c4105f9e392ca04f9fc8d958a95cce", size = 817689, upload-time = "2026-10-05T17:38:50.69Z" }, + { url = "https://files.pythonhosted.org/packages/e6/56/f00aa46127e6342f019d567853eeeb932e04fb9b9424b5fb981ad68f4178/aiohttp-3.14.4-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:2d0d8e435582b0d53009dac99e26a3d2be932ed7c9dbfcfc70f3fce1cf943bd5", size = 549599, upload-time = "2026-10-05T17:38:52.525Z" }, + { url = "https://files.pythonhosted.org/packages/3f/bc/825c09b09962253a2103e4a88c04374ee939c0c8ea31c270daa0308efb07/aiohttp-3.14.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:bf734016932d68e1324cfb638cac7a0866a83933a33badf15e836a7e24efb8c0", size = 548132, upload-time = "2026-10-05T17:38:54.629Z" }, + { url = "https://files.pythonhosted.org/packages/40/80/8a1bc8036540fe7cb38219cc5c0aa67d32e9068165725e8199ea8200b08b/aiohttp-3.14.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:322e3d741b3133bcbb981a41d4f9b8ac3545c18de49c662c2b1f4e1c770b98ad", size = 1898485, upload-time = "2026-10-05T17:38:56.439Z" }, + { url = "https://files.pythonhosted.org/packages/3c/fe/65b464d8520ace0d65b4ca69bc9abe175f842c8ce8d1522d363d9669903f/aiohttp-3.14.4-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:15a3bb5f90a4e515071f3617a45dfe26560beb834a6b6e108cdf4bc9e9719ec3", size = 1875334, upload-time = "2026-10-05T17:38:58.536Z" }, + { url = "https://files.pythonhosted.org/packages/be/51/9c583be502720e927560a8414f4dfb7c7de41945e1a30ccf7003b93c6f85/aiohttp-3.14.4-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6c044e52df1a466af82cad3518c92ea80cc4ddcfea86966ff083bb34bab29bf4", size = 1937772, upload-time = "2026-10-05T17:39:00.376Z" }, + { url = "https://files.pythonhosted.org/packages/a2/3d/b56512df7ea9cbb5f59099a6b375088dd578356a5a3fb27198ab82e19832/aiohttp-3.14.4-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d613d7d51bf06fe9a5e3aab86ce06d835bb0ceb1a31ea9e8766df4a403ae62a6", size = 2066220, upload-time = "2026-10-05T17:39:02.54Z" }, + { url = "https://files.pythonhosted.org/packages/11/6c/a7a42701d9ea319140a3d44a24ec72a00b0b46d1b899b26d8a705e65bdd8/aiohttp-3.14.4-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c5e93ab6e6330dce40f5b43996f1fc5f2543296d263a5e4b59ff09e73870b7d8", size = 1922895, upload-time = "2026-10-05T17:39:04.638Z" }, + { url = "https://files.pythonhosted.org/packages/77/04/f8337bd824ca3fe3968d34dc5037ace1c4872551c4621f8266239311d301/aiohttp-3.14.4-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:20134dc8e68c67e7478124d516449428684c0545b2d3faa575691c8bcbd56678", size = 1712589, upload-time = "2026-10-05T17:39:06.671Z" }, + { url = "https://files.pythonhosted.org/packages/fe/a6/d20e2c940b592d7c4a21690889dbff64fe0ca3facd9190696368694e1488/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:f0daef5ef012369dddc391c61f604111424aa9a96313a69fb899018b09d1b01e", size = 1862251, upload-time = "2026-10-05T17:39:08.523Z" }, + { url = "https://files.pythonhosted.org/packages/f5/e4/d50edd5ae5d024b380a8e892e333840bb22967a9eb9c8492108a403f678a/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:19290a108de0718b73bc69b86e788975c6a59855c671ebe2a98a07a6f968328f", size = 1895155, upload-time = "2026-10-05T17:39:10.305Z" }, + { url = "https://files.pythonhosted.org/packages/c3/d3/f36f2931f807ccf8437ec15e8f8bfaa4748d4792639401cc767a866abaa0/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:1494877625baeffab669f4a25a09ec4eea721b49e35363081a2a8e4231fe141f", size = 1906623, upload-time = "2026-10-05T17:39:12.411Z" }, + { url = "https://files.pythonhosted.org/packages/5d/0a/94821b711493142bf5e11c27b0d7502776778f7792c77ecc6647357d20c1/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:a779ce4bf099ce4ad2cdfed62f1ca536d435f53237c54ff40172fddada24d1b5", size = 1698932, upload-time = "2026-10-05T17:39:14.446Z" }, + { url = "https://files.pythonhosted.org/packages/d9/76/3d5a0d28362f0053c1c457024749911932481e8fd105fddf8305b1f93c81/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:0b4cec9fca876e2d4f4c6cb32b177390132d04618867689f43fefabf3f5c3980", size = 1934528, upload-time = "2026-10-05T17:39:16.354Z" }, + { url = "https://files.pythonhosted.org/packages/a7/51/9784a21dc05d2e0f6acaf864f16db53dab0fbd7b0753cef168601eacb012/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:217707313e23aedde9bea67cf8365c7b138b549ae179121ef3f476cf67e3173a", size = 1901984, upload-time = "2026-10-05T17:39:18.299Z" }, + { url = "https://files.pythonhosted.org/packages/44/4f/f98c88703e6d620243aa08473a946ca4e3756b6288690e38f0d9f9c1d007/aiohttp-3.14.4-cp312-cp312-win32.whl", hash = "sha256:18a9fb9a3f6e6e63f4d27f9adeef313a2d3c69a84d31170a844623824e722534", size = 480278, upload-time = "2026-10-05T17:39:20.206Z" }, + { url = "https://files.pythonhosted.org/packages/b7/bc/8555013f84b53e4fdde423131b641af50e822c6d7d9118b24c52b31f6900/aiohttp-3.14.4-cp312-cp312-win_amd64.whl", hash = "sha256:69dcb02d33dfe415d5ee342cc63b7d320efcaf4b761701c7bd7bfb91c715481a", size = 506317, upload-time = "2026-10-05T17:39:22.706Z" }, + { url = "https://files.pythonhosted.org/packages/21/3f/ca5bad7bfdaa7ddca053a044a1c7c0d4f3ad9d1f12f96dcab10bfb9c50e7/aiohttp-3.14.4-cp312-cp312-win_arm64.whl", hash = "sha256:d36b0263e7c2fbf1750b9f35d4e7e48b0442d8c45e4a89e3e74168821fb014bb", size = 487683, upload-time = "2026-10-05T17:39:24.482Z" }, + { url = "https://files.pythonhosted.org/packages/23/ec/7fee140da700ec3f5aa5e0fd2319f67be5e86de197e2384d27e5e6209e0e/aiohttp-3.14.4-cp313-cp313-android_24_arm64_v8a.whl", hash = "sha256:264b5a7568306590c44ae4a0237ad1715e35d447ea44ebf324e4c8fd9f78f67a", size = 539114, upload-time = "2026-10-05T17:39:26.322Z" }, + { url = "https://files.pythonhosted.org/packages/4e/04/930c01ce9e186e787046433d7dc5b45b188885f8406c14b58435b4431974/aiohttp-3.14.4-cp313-cp313-android_24_x86_64.whl", hash = "sha256:17e5d7c7775d8dd8e894c7ef6ebfa26509de36868a9a6c7c4fcfaf6a1bf43d60", size = 553514, upload-time = "2026-10-05T17:39:28.104Z" }, + { url = "https://files.pythonhosted.org/packages/2c/d7/983e3cea81c07e95f35d34da4d1e182b5c05489c49b7560b198a83f0da79/aiohttp-3.14.4-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:e91dc8fe9cbd052d16f7f1267e285cf8bbac4d2194bd5741f05ef201c77ed09e", size = 521381, upload-time = "2026-10-05T17:39:30.419Z" }, + { url = "https://files.pythonhosted.org/packages/0e/2d/80baed11659093883f51245755105557d3253e45bd0b693d70df0059d68b/aiohttp-3.14.4-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:8df6157d31703972aec9e3b93963f039ff06318301e30b007c3e941ff8a7ac42", size = 528347, upload-time = "2026-10-05T17:39:32.344Z" }, + { url = "https://files.pythonhosted.org/packages/c8/18/bfda255c311096c08dab26dc65f3d219f090df37dc5f5f6345f8c3aefc1f/aiohttp-3.14.4-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:220912b351549dc736c59d104dc443fa615753102bb778a4e98f86e4d94bff6a", size = 539914, upload-time = "2026-10-05T17:39:34.265Z" }, + { url = "https://files.pythonhosted.org/packages/51/fc/3b6ca6117c0c42481d719411fff7b5d3970ebd906543d3dc1ba40fe2462f/aiohttp-3.14.4-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:2efa42b39bb3f524d5eca3760639b584afdd1143a6b047fda29910ffb75e4993", size = 813997, upload-time = "2026-10-05T17:39:36.061Z" }, + { url = "https://files.pythonhosted.org/packages/b5/f6/86e3e02a9712aadc1ae0a1076bb2d1adf3d9addfe5542a28190c8f9b6d9b/aiohttp-3.14.4-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:7e7356059c8262d2c1fd95242e2b7b70fbc6eee3135bf470049cbec3e968b5b0", size = 548058, upload-time = "2026-10-05T17:39:38.109Z" }, + { url = "https://files.pythonhosted.org/packages/85/7e/6b9c2e271419d40ca76589613b3c7ab185fd3050a407bd2565b6aa46f695/aiohttp-3.14.4-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:fac247d0cc956d732df1211ac2d8a9999ec8dc1a92a90401de9d52e4ead546f7", size = 545933, upload-time = "2026-10-05T17:39:40.193Z" }, + { url = "https://files.pythonhosted.org/packages/14/fc/33d6e24a5f8ac32423230088c415e2a1c6efee23d902b62f20506631e40b/aiohttp-3.14.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6e2eb0f8b03b4f2bd154ed8cf7c1a119a1ad04808c258bf58f90138c83b8c6d5", size = 1888265, upload-time = "2026-10-05T17:39:42.182Z" }, + { url = "https://files.pythonhosted.org/packages/8d/e8/2eca1d468d83a514621d1280f9992d08649191db2028c9236b4edfa7c723/aiohttp-3.14.4-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7fbe827d27e0e369fd7bb88ceeaa5b46ea006e73e015b9dd77e3723a53162293", size = 1872300, upload-time = "2026-10-05T17:39:44.195Z" }, + { url = "https://files.pythonhosted.org/packages/d6/f6/5872983de71b0214acdfb86822f5cca295b39be4832ec589fa224aee0f6c/aiohttp-3.14.4-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a70387146d03af9f047c629b71aa27d9594b3b31ec4c9c91e1a73d0d8bf38e0e", size = 1926213, upload-time = "2026-10-05T17:39:46.199Z" }, + { url = "https://files.pythonhosted.org/packages/ee/65/ebfefa11a546c33c717af63c67868408ecf0b33b23a9d75669af95485407/aiohttp-3.14.4-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0d0934926fc65744e2fdd44ce68b2d79d5ee608a1e23f0596b35dd696519bb7c", size = 2056609, upload-time = "2026-10-05T17:39:48.221Z" }, + { url = "https://files.pythonhosted.org/packages/69/c0/70667e82ec041f4122a17afce711bbcf94a71bec5888b69a49aed8817be2/aiohttp-3.14.4-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ff4b366510c733974adb7a4102c094e4a6308e6f369315a4cf14d2d0a619cf82", size = 1914740, upload-time = "2026-10-05T17:39:50.304Z" }, + { url = "https://files.pythonhosted.org/packages/bf/86/559e9dfea676206b20737d7ccb5b3716bff5e58d2a8d53682e5301724cd1/aiohttp-3.14.4-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:85fac7c99e0ac3dcbd6ae1c33774e0603bfc732ddb967a6fce4a731103c1888e", size = 1703390, upload-time = "2026-10-05T17:39:52.385Z" }, + { url = "https://files.pythonhosted.org/packages/fc/91/c98897d4cf23e120b2f3980042835cb34c86bbe3c653f3eaacf4bf986349/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ef1e9c3b4a2300023a5dc865889ce532cfaf6798ba4ef78fbbefe738a9d23efa", size = 1852642, upload-time = "2026-10-05T17:39:54.391Z" }, + { url = "https://files.pythonhosted.org/packages/14/13/0258f352cb2c236f358a5b57d138e15fa2566e17accc0758d968dbf2ceb6/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:97e65916588be0f952b3307aaa8460c0771fa98dbea2dd27dabc9f5d84d53c3b", size = 1890616, upload-time = "2026-10-05T17:39:56.466Z" }, + { url = "https://files.pythonhosted.org/packages/64/3c/f43e294ce1a06d1234a97bd862c1aa31acfa1a0eea3786c22fd0dc1ea731/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:840775cb39a9424f9edf142133a1192263ac5bd79117ad2a16602cef6a0c1e9d", size = 1896638, upload-time = "2026-10-05T17:39:58.585Z" }, + { url = "https://files.pythonhosted.org/packages/9f/f7/ce1e3a85b73d05037d729d3d32da7d6959b9e433435e9abd46c2fb38410f/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:54f9256430ca040d58affbd551513de13a5cff7d065204fc52b9a1b0af09a049", size = 1693003, upload-time = "2026-10-05T17:40:00.698Z" }, + { url = "https://files.pythonhosted.org/packages/1d/72/45eb900d6a9ee046728f5589f3d07f5d78f049b5fb84f48881fa4174d5df/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:6112d5931bf12c776188cab81b82bbb17d86e2e1381f2ade6edc43e6b240f0cb", size = 1927730, upload-time = "2026-10-05T17:40:02.943Z" }, + { url = "https://files.pythonhosted.org/packages/b2/43/a83ff79dc8375953a1f00b808a21c82590f4e68304fecccdcc42a25fb7d8/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:facc6df39047c4732cbd885bb62e40df20885fcd709fc399e11f81b45ce0fff9", size = 1891177, upload-time = "2026-10-05T17:40:04.989Z" }, + { url = "https://files.pythonhosted.org/packages/5c/ba/fbdc41608d4e2fb6084d960a41b392fa82beb5b126c2466de549b5c67fc8/aiohttp-3.14.4-cp313-cp313-win32.whl", hash = "sha256:7968634fa3a967a2bc0b9aeba1d5a1955501dcd7d0de44b96f7ebfb662797735", size = 479943, upload-time = "2026-10-05T17:40:07.402Z" }, + { url = "https://files.pythonhosted.org/packages/35/51/d75629750e705832fd5cd52516a82943ed58b6e09c30e14830f5d87452fa/aiohttp-3.14.4-cp313-cp313-win_amd64.whl", hash = "sha256:c0a894b0265d139cd4c2c8bd4643822cc289a4a5331e21e810881bd000ffb2dc", size = 506209, upload-time = "2026-10-05T17:40:09.49Z" }, + { url = "https://files.pythonhosted.org/packages/02/64/66452d2ffcc13e5e5ee4ba4a968656fa4a98c29ed5ff0205d4fde02b2943/aiohttp-3.14.4-cp313-cp313-win_arm64.whl", hash = "sha256:da16c3037178e72589d91de59536d271dffc92c2be2b47c38a45538cba54fd29", size = 487163, upload-time = "2026-10-05T17:40:11.526Z" }, + { url = "https://files.pythonhosted.org/packages/d2/fd/b653b1f969e2e949fe4726af7a8043e8ef117f202bed7757ac8564e077a1/aiohttp-3.14.4-cp314-cp314-android_24_arm64_v8a.whl", hash = "sha256:749bfc43bb1df71bbe6ed215044d5412d786698fc5771d2037436ca49622f3c9", size = 540738, upload-time = "2026-10-05T17:40:14.109Z" }, + { url = "https://files.pythonhosted.org/packages/90/b5/eea49a0bb697deffac5165d707ec53a24748d6720b3af77a544107b49573/aiohttp-3.14.4-cp314-cp314-android_24_x86_64.whl", hash = "sha256:c113e4b489d711f606ca278cd8dc89179746244ea841aa0638b1b134600afad0", size = 554494, upload-time = "2026-10-05T17:40:16.231Z" }, + { url = "https://files.pythonhosted.org/packages/11/ea/cf8f4efbbfa8572d9965cd43b3c6c84c581aa006772e5ce3ab4020027e9b/aiohttp-3.14.4-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:50969522bc7022026a2c7968e67da5c789f6b716b988edac55dc630390efd5df", size = 522653, upload-time = "2026-10-05T17:40:18.879Z" }, + { url = "https://files.pythonhosted.org/packages/a3/24/9f6721f0b52323789cb1041ffc3afa729462d9925607e733a065b6fc5e17/aiohttp-3.14.4-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:cbf92cd7a1c800cee244558dd5630abb45c1c1093ef7b0d546a99f526ff7a9eb", size = 529697, upload-time = "2026-10-05T17:40:21.296Z" }, + { url = "https://files.pythonhosted.org/packages/9c/a4/399debc3c2ca0ab88a08e3082b4c4f62d0f66978af60243c63f2345ef337/aiohttp-3.14.4-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:fc76be08ff407fba717a769aff04ca1b4bf9ecfdcb5caadef84a563fdbbd146d", size = 540526, upload-time = "2026-10-05T17:40:23.548Z" }, + { url = "https://files.pythonhosted.org/packages/a2/97/90379813b18b795bccdeb3a5a85e9b93ac2c69f9c2a5d0faba59da3ad6d1/aiohttp-3.14.4-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:9b416f995b68a921069e6ec61fa07f2ac3ff033d92e97a69f673af89f5bb954d", size = 818866, upload-time = "2026-10-05T17:40:25.842Z" }, + { url = "https://files.pythonhosted.org/packages/78/70/824fd0dac819652f1df895b3f621a75bf0a3050c30e38d8d2316e34ab821/aiohttp-3.14.4-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:2c9585101cfca10e74a07cc0ef2bdc6d90616e6750926b20456f429d0608f740", size = 549666, upload-time = "2026-10-05T17:40:28.523Z" }, + { url = "https://files.pythonhosted.org/packages/8c/45/eafb2dd200dd2b770ed25a2dc5731c4ba5d58ab3fa8e2e82494bb946808e/aiohttp-3.14.4-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:3c4dcf611b095e7983421f49d01ffbed7ed574891533d606ea115fc23e7c4e90", size = 548961, upload-time = "2026-10-05T17:40:30.613Z" }, + { url = "https://files.pythonhosted.org/packages/a7/bc/6c733a1c71300293471ac7ef1dffd12b5b4dc9a43c53461224b2b8a7f667/aiohttp-3.14.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f8f61a9b5fa56c58e3441f9dc64137f786232d40fb89127190d0e0f84e1e5865", size = 1883165, upload-time = "2026-10-05T17:40:33.062Z" }, + { url = "https://files.pythonhosted.org/packages/37/34/885ddbd351679a31141b25e0d1a5e4f67738806e564c858b399709b61239/aiohttp-3.14.4-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:d43e538dfc85b705fd832620d050970ef5613b3869a7169b44a554b9dab9eee9", size = 1844119, upload-time = "2026-10-05T17:40:35.266Z" }, + { url = "https://files.pythonhosted.org/packages/cc/ef/0a64dac53c11d569851efb3e7eddb43551df72b2c172ebb34cccc93bcd3f/aiohttp-3.14.4-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:4135c4bb4b7682a7633fadc7170ea969d843f83aa7224e70111a20675105c985", size = 1930222, upload-time = "2026-10-05T17:40:37.527Z" }, + { url = "https://files.pythonhosted.org/packages/69/5f/774792ed8f973e0d234fcb06b0f0bc9f29e9a0a0dd847f6418c2904be7d9/aiohttp-3.14.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:9055324f156a94fdf6dc9a825ae60f9a2947b88f591ea81ee80826633de62ae7", size = 2038842, upload-time = "2026-10-05T17:40:39.815Z" }, + { url = "https://files.pythonhosted.org/packages/cb/05/e00f35581c97656d9e864edaa03292382c620dd1d9c836a4f73a2279acc4/aiohttp-3.14.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fb22c8e4b60385a9b414c70c6e8b2d0f4b23ff7fc4bb572ceb58297b228169f1", size = 1887845, upload-time = "2026-10-05T17:40:42.359Z" }, + { url = "https://files.pythonhosted.org/packages/ca/2e/07e3eff5b4c1b082a2eaf0ffb508b409b21ea1ddc9fdc57f3eabb51469a1/aiohttp-3.14.4-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:3b6945559a260112742ed58cde2165488d2fc51aeea34afbaa99d9371b43e1b5", size = 1702533, upload-time = "2026-10-05T17:40:44.569Z" }, + { url = "https://files.pythonhosted.org/packages/75/44/816844b7f876e6f8fee4ecb088269fcd92241da712e4814a4d624eda13a9/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:8f4078a90b174f15efb2c8725e8720c40dbd3b2cf6350dbc085c964a938d9de7", size = 1849058, upload-time = "2026-10-05T17:40:47.818Z" }, + { url = "https://files.pythonhosted.org/packages/ae/bd/163242e12464a1f3e58a77e28beca949652ddce84abdd5500a91c70a1e0d/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:f433c5654e32f72de3ef074d715eb5c7604eb6d28a5c2f3c9e5056f20fe6b306", size = 1854600, upload-time = "2026-10-05T17:40:50.401Z" }, + { url = "https://files.pythonhosted.org/packages/f2/59/5c1ae708a89524eddfd9c727b87cae26b5c50c3c76683b910ac06151ead0/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:871035fe79c636b6bc126ed78df37d72b830dfc751612cb4b1040360edf2719f", size = 1896565, upload-time = "2026-10-05T17:40:52.625Z" }, + { url = "https://files.pythonhosted.org/packages/37/45/95300a7de69241fe47d3f838f3fb582c712782e172d447ff650a013ea673/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:2617132524f66338f6c1d218cd16081576aefc40df4f2bcba338a99fbf67fec1", size = 1693092, upload-time = "2026-10-05T17:40:54.862Z" }, + { url = "https://files.pythonhosted.org/packages/ff/33/01a8e61d48d0094121092c74125df14c0f8f10ee3149bfe68b6f869409a9/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:d8bc326133272deee8ef337581550450e4bb735c0520be893b950a1f5baaf41a", size = 1917073, upload-time = "2026-10-05T17:40:57.656Z" }, + { url = "https://files.pythonhosted.org/packages/9e/d6/1a4f24624cda6686d5b927e26d5d1ae3ebb692faf88e93017fab4b391fd0/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:3ec57223e261b7fa9979c12dbce009ca53439be76cac3af27f860d3e4b1d6f7a", size = 1872656, upload-time = "2026-10-05T17:41:00.123Z" }, + { url = "https://files.pythonhosted.org/packages/be/be/ed286fcfa2d22061ae021b568c790123505cd482df35e23023339ecaed96/aiohttp-3.14.4-cp314-cp314-win32.whl", hash = "sha256:7242043e71fc449a19a47d92f4e9fd1e0ae8d3f88488982381f422bf6d651218", size = 485461, upload-time = "2026-10-05T17:41:02.686Z" }, + { url = "https://files.pythonhosted.org/packages/c0/74/e040e6f65f4da305777f1adb3023d47401693489e4a337c983b52d2a0a6b/aiohttp-3.14.4-cp314-cp314-win_amd64.whl", hash = "sha256:019587c7b3a44917dd61bcb312fd5c034f341dc9851b83e7b41b65e08b68ca0f", size = 512147, upload-time = "2026-10-05T17:41:04.98Z" }, + { url = "https://files.pythonhosted.org/packages/2e/5e/bddb33ae15fdd5a68a10a986587aa9916c418a712fdd110d3b3ae9b51407/aiohttp-3.14.4-cp314-cp314-win_arm64.whl", hash = "sha256:60dc71d38db0988f37e78f6ad4a010a2f6355cfac3fff5f130cf5ef2231f3f0d", size = 494685, upload-time = "2026-10-05T17:41:07.366Z" }, + { url = "https://files.pythonhosted.org/packages/22/2e/7b884014b40573f919fc3a528e5028bc37b249e31a93928ba61bdd25c960/aiohttp-3.14.4-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:674f53ab9d2794e2dd767619a3384bf1006f8d075e43c19d449a645f8ff641c2", size = 855696, upload-time = "2026-10-05T17:41:09.514Z" }, + { url = "https://files.pythonhosted.org/packages/5f/e6/b6e2b4f580ab6ae39241bb9182aca60e6e1915cdad0148faaa04db3f366b/aiohttp-3.14.4-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:6d243221f73e5ac546c2ed9255100423e4bc092b08b944f23498e8cf3096c26c", size = 567931, upload-time = "2026-10-05T17:41:11.685Z" }, + { url = "https://files.pythonhosted.org/packages/63/99/ae8e3a1a18adcbf636839d18b3cccc51007836ccdae5209381c5cf82d1ae/aiohttp-3.14.4-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:0daa016eb74e7888ed5f9ceec6eea3158999c1c4a115ef5cbe88baa8d924f94c", size = 567421, upload-time = "2026-10-05T17:41:13.836Z" }, + { url = "https://files.pythonhosted.org/packages/63/38/c5d4bb58be72b967a4090d2deeb38571f8c992852936c51dbbbeae49db1c/aiohttp-3.14.4-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:70c031a622aa20add05ebd234b90adaf6bf51c1c88cc305ec760721af83308c3", size = 2054173, upload-time = "2026-10-05T17:41:16.098Z" }, + { url = "https://files.pythonhosted.org/packages/eb/87/3c8a9c7670f56d478a75c5bb84b336fb61a67b908e36c30a4a96ed8c8e86/aiohttp-3.14.4-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7df363fa7c38945a896e12c69af4a1a56cbd4152791d9e41fd0bac396b72de38", size = 1918296, upload-time = "2026-10-05T17:41:18.478Z" }, + { url = "https://files.pythonhosted.org/packages/49/97/bd00e499c0a1505b44f5e23b9739034ea9be792ad42537f2894211ba1c07/aiohttp-3.14.4-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:02a508ba5ad91c4d730523584c0adc65882274bba5e37c33bc2f475e37577256", size = 2027513, upload-time = "2026-10-05T17:41:20.874Z" }, + { url = "https://files.pythonhosted.org/packages/23/1d/a3666a7c224f86a881f18d673a8ffdc92fa4c35274fb4361822f8f0dc566/aiohttp-3.14.4-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0cb3edece6fe6a944eaf97d803b88f606da6bc1600b1894c2969e78ffdc1fc29", size = 2152686, upload-time = "2026-10-05T17:41:23.181Z" }, + { url = "https://files.pythonhosted.org/packages/46/7e/f4204b8c4959c46f6367c182afbbacef08a1b53874281912c52fbd80151c/aiohttp-3.14.4-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:21ce1223b461bcc5fb389a7204001578f1c0b85c2da60a84d915ebb021294245", size = 2006431, upload-time = "2026-10-05T17:41:25.776Z" }, + { url = "https://files.pythonhosted.org/packages/33/43/091e69d42967cbea833ceb355c5457f8f70748fe08b88c9d91491b3fafb8/aiohttp-3.14.4-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:35d5432f0dc1c8b71307e9112461b52f336da225e344283eec4779222c0a1dff", size = 1789101, upload-time = "2026-10-05T17:41:28.095Z" }, + { url = "https://files.pythonhosted.org/packages/47/7b/b57cbe533c01098c5d30471f057e7c3c19f281122f756acc9c716b636e2c/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:d6ec364493057c118d08292f7cd60865965c209167d8657b45643a26aef77495", size = 1974472, upload-time = "2026-10-05T17:41:30.499Z" }, + { url = "https://files.pythonhosted.org/packages/9f/44/79acce03611450e4ed8594f96f1cea40d70bc84fb4e918f94d7d9454a4af/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:70492983b7aed9e61bda82fe1ce80bcba9199610886443133783a288638923c0", size = 1956340, upload-time = "2026-10-05T17:41:33.009Z" }, + { url = "https://files.pythonhosted.org/packages/da/bb/36e6cbd6720e3377a02f8709aec6fe80de729ef41e78ba01f13d50363c73/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:a77776673331577147e9d25cd7833a72e8891b47556336cff06ba1569e488b99", size = 1965771, upload-time = "2026-10-05T17:41:35.506Z" }, + { url = "https://files.pythonhosted.org/packages/69/0f/879735ac70ce5e6852916eed51c706a517b205150a8d384f9fa60933a3fc/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:73799000dd6fd5247094fd8e6d3e1eb871e41aab5cc35dff9d9f654cd230bc24", size = 1780297, upload-time = "2026-10-05T17:41:38.284Z" }, + { url = "https://files.pythonhosted.org/packages/01/5d/7c030ca5b6baf3b02eccd11afc3d58f0b35e407031d5cc78cae9c24921c0/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:27b370fb532e707e8c96d04fa0c96301fb7dba2d50aaca57f6c456cdfffec5bd", size = 2001374, upload-time = "2026-10-05T17:41:40.888Z" }, + { url = "https://files.pythonhosted.org/packages/80/1e/ddacbb8141d727034c51dd192d17749521d5b30b03f84aa034325396089e/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:884e0d1c707b6217fee3080b9b4029eee7551af788ee761010df19be158414b7", size = 1968531, upload-time = "2026-10-05T17:41:43.62Z" }, + { url = "https://files.pythonhosted.org/packages/3a/08/2214f823701eebc3e57db141faeae76df7bfd415f254cc7c1692258f228d/aiohttp-3.14.4-cp314-cp314t-win32.whl", hash = "sha256:f2e3d34edb151d3e27f93a8338e2da33e2c7261cd4c879ce5f5fe280cc190ea5", size = 504126, upload-time = "2026-10-05T17:41:46.321Z" }, + { url = "https://files.pythonhosted.org/packages/91/a1/90e9b6fd23310b4e82d0c0a37b5ecc2944053350473c57533c1da9647235/aiohttp-3.14.4-cp314-cp314t-win_amd64.whl", hash = "sha256:88cf889e51092537fe44adfbff96c2a22d6479d6f92b97b3d413fbfd0a4decf4", size = 531494, upload-time = "2026-10-05T17:41:48.849Z" }, + { url = "https://files.pythonhosted.org/packages/97/ab/5b501472c92b9b1dc53742591d6210dccb262962f4721299300d3a9f664b/aiohttp-3.14.4-cp314-cp314t-win_arm64.whl", hash = "sha256:ca450c6d42fda7c0bfaf0e200f32f77c5f2c960a33be1e14d197c84588b7f5f6", size = 510544, upload-time = "2026-10-05T17:41:51.358Z" }, + { url = "https://files.pythonhosted.org/packages/2b/27/5e1f8446545be98e9416af59c396b1ed1f9f3294afb0a40ee3a709889273/aiohttp-3.14.4-py3-none-any.whl", hash = "sha256:5c6758ba62aea282c537179cfc8474a90f2b5f7b089cc5ff66d8920d86a9bfdd", size = 279487, upload-time = "2026-10-05T17:43:44.905Z" }, ] [[package]] @@ -10779,142 +10780,118 @@ wheels = [ [[package]] name = "yarl" -version = "1.23.0" +version = "1.25.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "idna" }, { name = "multidict" }, { name = "propcache" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/23/6e/beb1beec874a72f23815c1434518bfc4ed2175065173fb138c3705f658d4/yarl-1.23.0.tar.gz", hash = "sha256:53b1ea6ca88ebd4420379c330aea57e258408dd0df9af0992e5de2078dc9f5d5", size = 194676, upload-time = "2026-03-01T22:07:53.373Z" } +sdist = { url = "https://files.pythonhosted.org/packages/75/16/e8be8e2fb175bbf41a0680381a319f1199fae256588241a2ac8677eafb49/yarl-1.25.1.tar.gz", hash = "sha256:03dd38de09bc213e9a8b29761eec33ee1d5318dac0e49d8af36e4d27830e23a7", size = 246245, upload-time = "2026-09-15T19:35:02.264Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/8b/0d/9cc638702f6fc3c7a3685bcc8cf2a9ed7d6206e932a49f5242658047ef51/yarl-1.23.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:cff6d44cb13d39db2663a22b22305d10855efa0fa8015ddeacc40bc59b9d8107", size = 123764, upload-time = "2026-03-01T22:04:09.7Z" }, - { url = "https://files.pythonhosted.org/packages/7a/35/5a553687c5793df5429cd1db45909d4f3af7eee90014888c208d086a44f0/yarl-1.23.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e4c53f8347cd4200f0d70a48ad059cabaf24f5adc6ba08622a23423bc7efa10d", size = 86282, upload-time = "2026-03-01T22:04:11.892Z" }, - { url = "https://files.pythonhosted.org/packages/68/2e/c5a2234238f8ce37a8312b52801ee74117f576b1539eec8404a480434acc/yarl-1.23.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2a6940a074fb3c48356ed0158a3ca5699c955ee4185b4d7d619be3c327143e05", size = 86053, upload-time = "2026-03-01T22:04:13.292Z" }, - { url = "https://files.pythonhosted.org/packages/74/3f/bbd8ff36fb038622797ffbaf7db314918bb4d76f1cc8a4f9ca7a55fe5195/yarl-1.23.0-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ed5f69ce7be7902e5c70ea19eb72d20abf7d725ab5d49777d696e32d4fc1811d", size = 99395, upload-time = "2026-03-01T22:04:15.133Z" }, - { url = "https://files.pythonhosted.org/packages/77/04/9516bc4e269d2a3ec9c6779fcdeac51ce5b3a9b0156f06ac7152e5bba864/yarl-1.23.0-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:389871e65468400d6283c0308e791a640b5ab5c83bcee02a2f51295f95e09748", size = 92143, upload-time = "2026-03-01T22:04:16.829Z" }, - { url = "https://files.pythonhosted.org/packages/c7/63/88802d1f6b1cb1fc67d67a58cd0cf8a1790de4ce7946e434240f1d60ab4a/yarl-1.23.0-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:dda608c88cf709b1d406bdfcd84d8d63cff7c9e577a403c6108ce8ce9dcc8764", size = 107643, upload-time = "2026-03-01T22:04:18.519Z" }, - { url = "https://files.pythonhosted.org/packages/8e/db/4f9b838f4d8bdd6f0f385aed8bbf21c71ed11a0b9983305c302cbd557815/yarl-1.23.0-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:8c4fe09e0780c6c3bf2b7d4af02ee2394439d11a523bbcf095cf4747c2932007", size = 108700, upload-time = "2026-03-01T22:04:20.373Z" }, - { url = "https://files.pythonhosted.org/packages/50/12/95a1d33f04a79c402664070d43b8b9f72dc18914e135b345b611b0b1f8cc/yarl-1.23.0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:31c9921eb8bd12633b41ad27686bbb0b1a2a9b8452bfdf221e34f311e9942ed4", size = 102769, upload-time = "2026-03-01T22:04:23.055Z" }, - { url = "https://files.pythonhosted.org/packages/86/65/91a0285f51321369fd1a8308aa19207520c5f0587772cfc2e03fc2467e90/yarl-1.23.0-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:5f10fd85e4b75967468af655228fbfd212bdf66db1c0d135065ce288982eda26", size = 101114, upload-time = "2026-03-01T22:04:25.031Z" }, - { url = "https://files.pythonhosted.org/packages/58/80/c7c8244fc3e5bc483dc71a09560f43b619fab29301a0f0a8f936e42865c7/yarl-1.23.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:dbf507e9ef5688bada447a24d68b4b58dd389ba93b7afc065a2ba892bea54769", size = 98883, upload-time = "2026-03-01T22:04:27.281Z" }, - { url = "https://files.pythonhosted.org/packages/86/e7/71ca9cc9ca79c0b7d491216177d1aed559d632947b8ffb0ee60f7d8b23e3/yarl-1.23.0-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:85e9beda1f591bc73e77ea1c51965c68e98dafd0fec72cdd745f77d727466716", size = 94172, upload-time = "2026-03-01T22:04:28.554Z" }, - { url = "https://files.pythonhosted.org/packages/6a/3f/6c6c8a0fe29c26fb2db2e8d32195bb84ec1bfb8f1d32e7f73b787fcf349b/yarl-1.23.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:0e1fdaa14ef51366d7757b45bde294e95f6c8c049194e793eedb8387c86d5993", size = 107010, upload-time = "2026-03-01T22:04:30.385Z" }, - { url = "https://files.pythonhosted.org/packages/56/38/12730c05e5ad40a76374d440ed8b0899729a96c250516d91c620a6e38fc2/yarl-1.23.0-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:75e3026ab649bf48f9a10c0134512638725b521340293f202a69b567518d94e0", size = 100285, upload-time = "2026-03-01T22:04:31.752Z" }, - { url = "https://files.pythonhosted.org/packages/34/92/6a7be9239f2347234e027284e7a5f74b1140cc86575e7b469d13fba1ebfe/yarl-1.23.0-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:80e6d33a3d42a7549b409f199857b4fb54e2103fc44fb87605b6663b7a7ff750", size = 108230, upload-time = "2026-03-01T22:04:33.844Z" }, - { url = "https://files.pythonhosted.org/packages/5e/81/4aebccfa9376bd98b9d8bfad20621a57d3e8cfc5b8631c1fa5f62cdd03f4/yarl-1.23.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:5ec2f42d41ccbd5df0270d7df31618a8ee267bfa50997f5d720ddba86c4a83a6", size = 103008, upload-time = "2026-03-01T22:04:35.856Z" }, - { url = "https://files.pythonhosted.org/packages/38/0f/0b4e3edcec794a86b853b0c6396c0a888d72dfce19b2d88c02ac289fb6c1/yarl-1.23.0-cp310-cp310-win32.whl", hash = "sha256:debe9c4f41c32990771be5c22b56f810659f9ddf3d63f67abfdcaa2c6c9c5c1d", size = 83073, upload-time = "2026-03-01T22:04:38.268Z" }, - { url = "https://files.pythonhosted.org/packages/a0/71/ad95c33da18897e4c636528bbc24a1dd23fe16797de8bc4ec667b8db0ba4/yarl-1.23.0-cp310-cp310-win_amd64.whl", hash = "sha256:ab5f043cb8a2d71c981c09c510da013bc79fd661f5c60139f00dd3c3cc4f2ffb", size = 87328, upload-time = "2026-03-01T22:04:39.558Z" }, - { url = "https://files.pythonhosted.org/packages/e2/14/dfa369523c79bccf9c9c746b0a63eb31f65db9418ac01275f7950962e504/yarl-1.23.0-cp310-cp310-win_arm64.whl", hash = "sha256:263cd4f47159c09b8b685890af949195b51d1aa82ba451c5847ca9bc6413c220", size = 82463, upload-time = "2026-03-01T22:04:41.454Z" }, - { url = "https://files.pythonhosted.org/packages/a2/aa/60da938b8f0997ba3a911263c40d82b6f645a67902a490b46f3355e10fae/yarl-1.23.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:b35d13d549077713e4414f927cdc388d62e543987c572baee613bf82f11a4b99", size = 123641, upload-time = "2026-03-01T22:04:42.841Z" }, - { url = "https://files.pythonhosted.org/packages/24/84/e237607faf4e099dbb8a4f511cfd5efcb5f75918baad200ff7380635631b/yarl-1.23.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cbb0fef01f0c6b38cb0f39b1f78fc90b807e0e3c86a7ff3ce74ad77ce5c7880c", size = 86248, upload-time = "2026-03-01T22:04:44.757Z" }, - { url = "https://files.pythonhosted.org/packages/b2/0d/71ceabc14c146ba8ee3804ca7b3d42b1664c8440439de5214d366fec7d3a/yarl-1.23.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:dc52310451fc7c629e13c4e061cbe2dd01684d91f2f8ee2821b083c58bd72432", size = 85988, upload-time = "2026-03-01T22:04:46.365Z" }, - { url = "https://files.pythonhosted.org/packages/8c/6c/4a90d59c572e46b270ca132aca66954f1175abd691f74c1ef4c6711828e2/yarl-1.23.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b2c6b50c7b0464165472b56b42d4c76a7b864597007d9c085e8b63e185cf4a7a", size = 100566, upload-time = "2026-03-01T22:04:47.639Z" }, - { url = "https://files.pythonhosted.org/packages/49/fb/c438fb5108047e629f6282a371e6e91cf3f97ee087c4fb748a1f32ceef55/yarl-1.23.0-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:aafe5dcfda86c8af00386d7781d4c2181b5011b7be3f2add5e99899ea925df05", size = 92079, upload-time = "2026-03-01T22:04:48.925Z" }, - { url = "https://files.pythonhosted.org/packages/d9/13/d269aa1aed3e4f50a5a103f96327210cc5fa5dd2d50882778f13c7a14606/yarl-1.23.0-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:9ee33b875f0b390564c1fb7bc528abf18c8ee6073b201c6ae8524aca778e2d83", size = 108741, upload-time = "2026-03-01T22:04:50.838Z" }, - { url = "https://files.pythonhosted.org/packages/85/fb/115b16f22c37ea4437d323e472945bea97301c8ec6089868fa560abab590/yarl-1.23.0-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:4c41e021bc6d7affb3364dc1e1e5fa9582b470f283748784bd6ea0558f87f42c", size = 108099, upload-time = "2026-03-01T22:04:52.499Z" }, - { url = "https://files.pythonhosted.org/packages/9a/64/c53487d9f4968045b8afa51aed7ca44f58b2589e772f32745f3744476c82/yarl-1.23.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:99c8a9ed30f4164bc4c14b37a90208836cbf50d4ce2a57c71d0f52c7fb4f7598", size = 102678, upload-time = "2026-03-01T22:04:55.176Z" }, - { url = "https://files.pythonhosted.org/packages/85/59/cd98e556fbb2bf8fab29c1a722f67ad45c5f3447cac798ab85620d1e70af/yarl-1.23.0-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f2af5c81a1f124609d5f33507082fc3f739959d4719b56877ab1ee7e7b3d602b", size = 100803, upload-time = "2026-03-01T22:04:56.588Z" }, - { url = "https://files.pythonhosted.org/packages/9e/c0/b39770b56d4a9f0bb5f77e2f1763cd2d75cc2f6c0131e3b4c360348fcd65/yarl-1.23.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:6b41389c19b07c760c7e427a3462e8ab83c4bb087d127f0e854c706ce1b9215c", size = 100163, upload-time = "2026-03-01T22:04:58.492Z" }, - { url = "https://files.pythonhosted.org/packages/e7/64/6980f99ab00e1f0ff67cb84766c93d595b067eed07439cfccfc8fb28c1a6/yarl-1.23.0-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:1dc702e42d0684f42d6519c8d581e49c96cefaaab16691f03566d30658ee8788", size = 93859, upload-time = "2026-03-01T22:05:00.268Z" }, - { url = "https://files.pythonhosted.org/packages/38/69/912e6c5e146793e5d4b5fe39ff5b00f4d22463dfd5a162bec565ac757673/yarl-1.23.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:0e40111274f340d32ebcc0a5668d54d2b552a6cca84c9475859d364b380e3222", size = 108202, upload-time = "2026-03-01T22:05:02.273Z" }, - { url = "https://files.pythonhosted.org/packages/59/97/35ca6767524687ad64e5f5c31ad54bc76d585585a9fcb40f649e7e82ffed/yarl-1.23.0-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:4764a6a7588561a9aef92f65bda2c4fb58fe7c675c0883862e6df97559de0bfb", size = 99866, upload-time = "2026-03-01T22:05:03.597Z" }, - { url = "https://files.pythonhosted.org/packages/d3/1c/1a3387ee6d73589f6f2a220ae06f2984f6c20b40c734989b0a44f5987308/yarl-1.23.0-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:03214408cfa590df47728b84c679ae4ef00be2428e11630277be0727eba2d7cc", size = 107852, upload-time = "2026-03-01T22:05:04.986Z" }, - { url = "https://files.pythonhosted.org/packages/a4/b8/35c0750fcd5a3f781058bfd954515dd4b1eab45e218cbb85cf11132215f1/yarl-1.23.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:170e26584b060879e29fac213e4228ef063f39128723807a312e5c7fec28eff2", size = 102919, upload-time = "2026-03-01T22:05:06.397Z" }, - { url = "https://files.pythonhosted.org/packages/e5/1c/9a1979aec4a81896d597bcb2177827f2dbee3f5b7cc48b2d0dadb644b41d/yarl-1.23.0-cp311-cp311-win32.whl", hash = "sha256:51430653db848d258336cfa0244427b17d12db63d42603a55f0d4546f50f25b5", size = 82602, upload-time = "2026-03-01T22:05:08.444Z" }, - { url = "https://files.pythonhosted.org/packages/93/22/b85eca6fa2ad9491af48c973e4c8cf6b103a73dbb271fe3346949449fca0/yarl-1.23.0-cp311-cp311-win_amd64.whl", hash = "sha256:bf49a3ae946a87083ef3a34c8f677ae4243f5b824bfc4c69672e72b3d6719d46", size = 87461, upload-time = "2026-03-01T22:05:10.145Z" }, - { url = "https://files.pythonhosted.org/packages/93/95/07e3553fe6f113e6864a20bdc53a78113cda3b9ced8784ee52a52c9f80d8/yarl-1.23.0-cp311-cp311-win_arm64.whl", hash = "sha256:b39cb32a6582750b6cc77bfb3c49c0f8760dc18dc96ec9fb55fbb0f04e08b928", size = 82336, upload-time = "2026-03-01T22:05:11.554Z" }, - { url = "https://files.pythonhosted.org/packages/88/8a/94615bc31022f711add374097ad4144d569e95ff3c38d39215d07ac153a0/yarl-1.23.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:1932b6b8bba8d0160a9d1078aae5838a66039e8832d41d2992daa9a3a08f7860", size = 124737, upload-time = "2026-03-01T22:05:12.897Z" }, - { url = "https://files.pythonhosted.org/packages/e3/6f/c6554045d59d64052698add01226bc867b52fe4a12373415d7991fdca95d/yarl-1.23.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:411225bae281f114067578891bc75534cfb3d92a3b4dfef7a6ca78ba354e6069", size = 87029, upload-time = "2026-03-01T22:05:14.376Z" }, - { url = "https://files.pythonhosted.org/packages/19/2a/725ecc166d53438bc88f76822ed4b1e3b10756e790bafd7b523fe97c322d/yarl-1.23.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:13a563739ae600a631c36ce096615fe307f131344588b0bc0daec108cdb47b25", size = 86310, upload-time = "2026-03-01T22:05:15.71Z" }, - { url = "https://files.pythonhosted.org/packages/99/30/58260ed98e6ff7f90ba84442c1ddd758c9170d70327394a6227b310cd60f/yarl-1.23.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9cbf44c5cb4a7633d078788e1b56387e3d3cf2b8139a3be38040b22d6c3221c8", size = 97587, upload-time = "2026-03-01T22:05:17.384Z" }, - { url = "https://files.pythonhosted.org/packages/76/0a/8b08aac08b50682e65759f7f8dde98ae8168f72487e7357a5d684c581ef9/yarl-1.23.0-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:53ad387048f6f09a8969631e4de3f1bf70c50e93545d64af4f751b2498755072", size = 92528, upload-time = "2026-03-01T22:05:18.804Z" }, - { url = "https://files.pythonhosted.org/packages/52/07/0b7179101fe5f8385ec6c6bb5d0cb9f76bd9fb4a769591ab6fb5cdbfc69a/yarl-1.23.0-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:4a59ba56f340334766f3a4442e0efd0af895fae9e2b204741ef885c446b3a1a8", size = 105339, upload-time = "2026-03-01T22:05:20.235Z" }, - { url = "https://files.pythonhosted.org/packages/d3/8a/36d82869ab5ec829ca8574dfcb92b51286fcfb1e9c7a73659616362dc880/yarl-1.23.0-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:803a3c3ce4acc62eaf01eaca1208dcf0783025ef27572c3336502b9c232005e7", size = 105061, upload-time = "2026-03-01T22:05:22.268Z" }, - { url = "https://files.pythonhosted.org/packages/66/3e/868e5c3364b6cee19ff3e1a122194fa4ce51def02c61023970442162859e/yarl-1.23.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a3d2bff8f37f8d0f96c7ec554d16945050d54462d6e95414babaa18bfafc7f51", size = 100132, upload-time = "2026-03-01T22:05:23.638Z" }, - { url = "https://files.pythonhosted.org/packages/cf/26/9c89acf82f08a52cb52d6d39454f8d18af15f9d386a23795389d1d423823/yarl-1.23.0-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:c75eb09e8d55bceb4367e83496ff8ef2bc7ea6960efb38e978e8073ea59ecb67", size = 99289, upload-time = "2026-03-01T22:05:25.749Z" }, - { url = "https://files.pythonhosted.org/packages/6f/54/5b0db00d2cb056922356104468019c0a132e89c8d3ab67d8ede9f4483d2a/yarl-1.23.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:877b0738624280e34c55680d6054a307aa94f7d52fa0e3034a9cc6e790871da7", size = 96950, upload-time = "2026-03-01T22:05:27.318Z" }, - { url = "https://files.pythonhosted.org/packages/f6/40/10fa93811fd439341fad7e0718a86aca0de9548023bbb403668d6555acab/yarl-1.23.0-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:b5405bb8f0e783a988172993cfc627e4d9d00432d6bbac65a923041edacf997d", size = 93960, upload-time = "2026-03-01T22:05:28.738Z" }, - { url = "https://files.pythonhosted.org/packages/bc/d2/8ae2e6cd77d0805f4526e30ec43b6f9a3dfc542d401ac4990d178e4bf0cf/yarl-1.23.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:1c3a3598a832590c5a3ce56ab5576361b5688c12cb1d39429cf5dba30b510760", size = 104703, upload-time = "2026-03-01T22:05:30.438Z" }, - { url = "https://files.pythonhosted.org/packages/2f/0c/b3ceacf82c3fe21183ce35fa2acf5320af003d52bc1fcf5915077681142e/yarl-1.23.0-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:8419ebd326430d1cbb7efb5292330a2cf39114e82df5cc3d83c9a0d5ebeaf2f2", size = 98325, upload-time = "2026-03-01T22:05:31.835Z" }, - { url = "https://files.pythonhosted.org/packages/9d/e0/12900edd28bdab91a69bd2554b85ad7b151f64e8b521fe16f9ad2f56477a/yarl-1.23.0-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:be61f6fff406ca40e3b1d84716fde398fc08bc63dd96d15f3a14230a0973ed86", size = 105067, upload-time = "2026-03-01T22:05:33.358Z" }, - { url = "https://files.pythonhosted.org/packages/15/61/74bb1182cf79c9bbe4eb6b1f14a57a22d7a0be5e9cedf8e2d5c2086474c3/yarl-1.23.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:3ceb13c5c858d01321b5d9bb65e4cf37a92169ea470b70fec6f236b2c9dd7e34", size = 100285, upload-time = "2026-03-01T22:05:35.4Z" }, - { url = "https://files.pythonhosted.org/packages/69/7f/cd5ef733f2550de6241bd8bd8c3febc78158b9d75f197d9c7baa113436af/yarl-1.23.0-cp312-cp312-win32.whl", hash = "sha256:fffc45637bcd6538de8b85f51e3df3223e4ad89bccbfca0481c08c7fc8b7ed7d", size = 82359, upload-time = "2026-03-01T22:05:36.811Z" }, - { url = "https://files.pythonhosted.org/packages/f5/be/25216a49daeeb7af2bec0db22d5e7df08ed1d7c9f65d78b14f3b74fd72fc/yarl-1.23.0-cp312-cp312-win_amd64.whl", hash = "sha256:f69f57305656a4852f2a7203efc661d8c042e6cc67f7acd97d8667fb448a426e", size = 87674, upload-time = "2026-03-01T22:05:38.171Z" }, - { url = "https://files.pythonhosted.org/packages/d2/35/aeab955d6c425b227d5b7247eafb24f2653fedc32f95373a001af5dfeb9e/yarl-1.23.0-cp312-cp312-win_arm64.whl", hash = "sha256:6e87a6e8735b44816e7db0b2fbc9686932df473c826b0d9743148432e10bb9b9", size = 81879, upload-time = "2026-03-01T22:05:40.006Z" }, - { url = "https://files.pythonhosted.org/packages/9a/4b/a0a6e5d0ee8a2f3a373ddef8a4097d74ac901ac363eea1440464ccbe0898/yarl-1.23.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:16c6994ac35c3e74fb0ae93323bf8b9c2a9088d55946109489667c510a7d010e", size = 123796, upload-time = "2026-03-01T22:05:41.412Z" }, - { url = "https://files.pythonhosted.org/packages/67/b6/8925d68af039b835ae876db5838e82e76ec87b9782ecc97e192b809c4831/yarl-1.23.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:4a42e651629dafb64fd5b0286a3580613702b5809ad3f24934ea87595804f2c5", size = 86547, upload-time = "2026-03-01T22:05:42.841Z" }, - { url = "https://files.pythonhosted.org/packages/ae/50/06d511cc4b8e0360d3c94af051a768e84b755c5eb031b12adaaab6dec6e5/yarl-1.23.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:7c6b9461a2a8b47c65eef63bb1c76a4f1c119618ffa99ea79bc5bb1e46c5821b", size = 85854, upload-time = "2026-03-01T22:05:44.85Z" }, - { url = "https://files.pythonhosted.org/packages/c4/f4/4e30b250927ffdab4db70da08b9b8d2194d7c7b400167b8fbeca1e4701ca/yarl-1.23.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:2569b67d616eab450d262ca7cb9f9e19d2f718c70a8b88712859359d0ab17035", size = 98351, upload-time = "2026-03-01T22:05:46.836Z" }, - { url = "https://files.pythonhosted.org/packages/86/fc/4118c5671ea948208bdb1492d8b76bdf1453d3e73df051f939f563e7dcc5/yarl-1.23.0-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:e9d9a4d06d3481eab79803beb4d9bd6f6a8e781ec078ac70d7ef2dcc29d1bea5", size = 92711, upload-time = "2026-03-01T22:05:48.316Z" }, - { url = "https://files.pythonhosted.org/packages/56/11/1ed91d42bd9e73c13dc9e7eb0dd92298d75e7ac4dd7f046ad0c472e231cd/yarl-1.23.0-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f514f6474e04179d3d33175ed3f3e31434d3130d42ec153540d5b157deefd735", size = 106014, upload-time = "2026-03-01T22:05:50.028Z" }, - { url = "https://files.pythonhosted.org/packages/ce/c9/74e44e056a23fbc33aca71779ef450ca648a5bc472bdad7a82339918f818/yarl-1.23.0-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:fda207c815b253e34f7e1909840fd14299567b1c0eb4908f8c2ce01a41265401", size = 105557, upload-time = "2026-03-01T22:05:51.416Z" }, - { url = "https://files.pythonhosted.org/packages/66/fe/b1e10b08d287f518994f1e2ff9b6d26f0adeecd8dd7d533b01bab29a3eda/yarl-1.23.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:34b6cf500e61c90f305094911f9acc9c86da1a05a7a3f5be9f68817043f486e4", size = 101559, upload-time = "2026-03-01T22:05:52.872Z" }, - { url = "https://files.pythonhosted.org/packages/72/59/c5b8d94b14e3d3c2a9c20cb100119fd534ab5a14b93673ab4cc4a4141ea5/yarl-1.23.0-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:d7504f2b476d21653e4d143f44a175f7f751cd41233525312696c76aa3dbb23f", size = 100502, upload-time = "2026-03-01T22:05:54.954Z" }, - { url = "https://files.pythonhosted.org/packages/77/4f/96976cb54cbfc5c9fd73ed4c51804f92f209481d1fb190981c0f8a07a1d7/yarl-1.23.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:578110dd426f0d209d1509244e6d4a3f1a3e9077655d98c5f22583d63252a08a", size = 98027, upload-time = "2026-03-01T22:05:56.409Z" }, - { url = "https://files.pythonhosted.org/packages/63/6e/904c4f476471afdbad6b7e5b70362fb5810e35cd7466529a97322b6f5556/yarl-1.23.0-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:609d3614d78d74ebe35f54953c5bbd2ac647a7ddb9c30a5d877580f5e86b22f2", size = 95369, upload-time = "2026-03-01T22:05:58.141Z" }, - { url = "https://files.pythonhosted.org/packages/9d/40/acfcdb3b5f9d68ef499e39e04d25e141fe90661f9d54114556cf83be8353/yarl-1.23.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:4966242ec68afc74c122f8459abd597afd7d8a60dc93d695c1334c5fd25f762f", size = 105565, upload-time = "2026-03-01T22:06:00.286Z" }, - { url = "https://files.pythonhosted.org/packages/5e/c6/31e28f3a6ba2869c43d124f37ea5260cac9c9281df803c354b31f4dd1f3c/yarl-1.23.0-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:e0fd068364a6759bc794459f0a735ab151d11304346332489c7972bacbe9e72b", size = 99813, upload-time = "2026-03-01T22:06:01.712Z" }, - { url = "https://files.pythonhosted.org/packages/08/1f/6f65f59e72d54aa467119b63fc0b0b1762eff0232db1f4720cd89e2f4a17/yarl-1.23.0-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:39004f0ad156da43e86aa71f44e033de68a44e5a31fc53507b36dd253970054a", size = 105632, upload-time = "2026-03-01T22:06:03.188Z" }, - { url = "https://files.pythonhosted.org/packages/a3/c4/18b178a69935f9e7a338127d5b77d868fdc0f0e49becd286d51b3a18c61d/yarl-1.23.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:e5723c01a56c5028c807c701aa66722916d2747ad737a046853f6c46f4875543", size = 101895, upload-time = "2026-03-01T22:06:04.651Z" }, - { url = "https://files.pythonhosted.org/packages/8f/54/f5b870b5505663911dba950a8e4776a0dbd51c9c54c0ae88e823e4b874a0/yarl-1.23.0-cp313-cp313-win32.whl", hash = "sha256:1b6b572edd95b4fa8df75de10b04bc81acc87c1c7d16bcdd2035b09d30acc957", size = 82356, upload-time = "2026-03-01T22:06:06.04Z" }, - { url = "https://files.pythonhosted.org/packages/7a/84/266e8da36879c6edcd37b02b547e2d9ecdfea776be49598e75696e3316e1/yarl-1.23.0-cp313-cp313-win_amd64.whl", hash = "sha256:baaf55442359053c7d62f6f8413a62adba3205119bcb6f49594894d8be47e5e3", size = 87515, upload-time = "2026-03-01T22:06:08.107Z" }, - { url = "https://files.pythonhosted.org/packages/00/fd/7e1c66efad35e1649114fa13f17485f62881ad58edeeb7f49f8c5e748bf9/yarl-1.23.0-cp313-cp313-win_arm64.whl", hash = "sha256:fb4948814a2a98e3912505f09c9e7493b1506226afb1f881825368d6fb776ee3", size = 81785, upload-time = "2026-03-01T22:06:10.181Z" }, - { url = "https://files.pythonhosted.org/packages/9c/fc/119dd07004f17ea43bb91e3ece6587759edd7519d6b086d16bfbd3319982/yarl-1.23.0-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:aecfed0b41aa72b7881712c65cf764e39ce2ec352324f5e0837c7048d9e6daaa", size = 130719, upload-time = "2026-03-01T22:06:11.708Z" }, - { url = "https://files.pythonhosted.org/packages/e6/0d/9f2348502fbb3af409e8f47730282cd6bc80dec6630c1e06374d882d6eb2/yarl-1.23.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:a41bcf68efd19073376eb8cf948b8d9be0af26256403e512bb18f3966f1f9120", size = 89690, upload-time = "2026-03-01T22:06:13.429Z" }, - { url = "https://files.pythonhosted.org/packages/50/93/e88f3c80971b42cfc83f50a51b9d165a1dbf154b97005f2994a79f212a07/yarl-1.23.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:cde9a2ecd91668bcb7f077c4966d8ceddb60af01b52e6e3e2680e4cf00ad1a59", size = 89851, upload-time = "2026-03-01T22:06:15.53Z" }, - { url = "https://files.pythonhosted.org/packages/1c/07/61c9dd8ba8f86473263b4036f70fb594c09e99c0d9737a799dfd8bc85651/yarl-1.23.0-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5023346c4ee7992febc0068e7593de5fa2bf611848c08404b35ebbb76b1b0512", size = 95874, upload-time = "2026-03-01T22:06:17.553Z" }, - { url = "https://files.pythonhosted.org/packages/9e/e9/f9ff8ceefba599eac6abddcfb0b3bee9b9e636e96dbf54342a8577252379/yarl-1.23.0-cp313-cp313t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:d1009abedb49ae95b136a8904a3f71b342f849ffeced2d3747bf29caeda218c4", size = 88710, upload-time = "2026-03-01T22:06:19.004Z" }, - { url = "https://files.pythonhosted.org/packages/eb/78/0231bfcc5d4c8eec220bc2f9ef82cb4566192ea867a7c5b4148f44f6cbcd/yarl-1.23.0-cp313-cp313t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a8d00f29b42f534cc8aa3931cfe773b13b23e561e10d2b26f27a8d309b0e82a1", size = 101033, upload-time = "2026-03-01T22:06:21.203Z" }, - { url = "https://files.pythonhosted.org/packages/cd/9b/30ea5239a61786f18fd25797151a17fbb3be176977187a48d541b5447dd4/yarl-1.23.0-cp313-cp313t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:95451e6ce06c3e104556d73b559f5da6c34a069b6b62946d3ad66afcd51642ea", size = 100817, upload-time = "2026-03-01T22:06:22.738Z" }, - { url = "https://files.pythonhosted.org/packages/62/e2/a4980481071791bc83bce2b7a1a1f7adcabfa366007518b4b845e92eeee3/yarl-1.23.0-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:531ef597132086b6cf96faa7c6c1dcd0361dd5f1694e5cc30375907b9b7d3ea9", size = 97482, upload-time = "2026-03-01T22:06:24.21Z" }, - { url = "https://files.pythonhosted.org/packages/e5/1e/304a00cf5f6100414c4b5a01fc7ff9ee724b62158a08df2f8170dfc72a2d/yarl-1.23.0-cp313-cp313t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:88f9fb0116fbfcefcab70f85cf4b74a2b6ce5d199c41345296f49d974ddb4123", size = 95949, upload-time = "2026-03-01T22:06:25.697Z" }, - { url = "https://files.pythonhosted.org/packages/68/03/093f4055ed4cae649ac53bca3d180bd37102e9e11d048588e9ab0c0108d0/yarl-1.23.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:e7b0460976dc75cb87ad9cc1f9899a4b97751e7d4e77ab840fc9b6d377b8fd24", size = 95839, upload-time = "2026-03-01T22:06:27.309Z" }, - { url = "https://files.pythonhosted.org/packages/b9/28/4c75ebb108f322aa8f917ae10a8ffa4f07cae10a8a627b64e578617df6a0/yarl-1.23.0-cp313-cp313t-musllinux_1_2_armv7l.whl", hash = "sha256:115136c4a426f9da976187d238e84139ff6b51a20839aa6e3720cd1026d768de", size = 90696, upload-time = "2026-03-01T22:06:29.048Z" }, - { url = "https://files.pythonhosted.org/packages/23/9c/42c2e2dd91c1a570402f51bdf066bfdb1241c2240ba001967bad778e77b7/yarl-1.23.0-cp313-cp313t-musllinux_1_2_ppc64le.whl", hash = "sha256:ead11956716a940c1abc816b7df3fa2b84d06eaed8832ca32f5c5e058c65506b", size = 100865, upload-time = "2026-03-01T22:06:30.525Z" }, - { url = "https://files.pythonhosted.org/packages/74/05/1bcd60a8a0a914d462c305137246b6f9d167628d73568505fce3f1cb2e65/yarl-1.23.0-cp313-cp313t-musllinux_1_2_riscv64.whl", hash = "sha256:fe8f8f5e70e6dbdfca9882cd9deaac058729bcf323cf7a58660901e55c9c94f6", size = 96234, upload-time = "2026-03-01T22:06:32.692Z" }, - { url = "https://files.pythonhosted.org/packages/90/b2/f52381aac396d6778ce516b7bc149c79e65bfc068b5de2857ab69eeea3b7/yarl-1.23.0-cp313-cp313t-musllinux_1_2_s390x.whl", hash = "sha256:a0e317df055958a0c1e79e5d2aa5a5eaa4a6d05a20d4b0c9c3f48918139c9fc6", size = 100295, upload-time = "2026-03-01T22:06:34.268Z" }, - { url = "https://files.pythonhosted.org/packages/e5/e8/638bae5bbf1113a659b2435d8895474598afe38b4a837103764f603aba56/yarl-1.23.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:6f0fd84de0c957b2d280143522c4f91a73aada1923caee763e24a2b3fda9f8a5", size = 97784, upload-time = "2026-03-01T22:06:35.864Z" }, - { url = "https://files.pythonhosted.org/packages/80/25/a3892b46182c586c202629fc2159aa13975d3741d52ebd7347fd501d48d5/yarl-1.23.0-cp313-cp313t-win32.whl", hash = "sha256:93a784271881035ab4406a172edb0faecb6e7d00f4b53dc2f55919d6c9688595", size = 88313, upload-time = "2026-03-01T22:06:37.39Z" }, - { url = "https://files.pythonhosted.org/packages/43/68/8c5b36aa5178900b37387937bc2c2fe0e9505537f713495472dcf6f6fccc/yarl-1.23.0-cp313-cp313t-win_amd64.whl", hash = "sha256:dd00607bffbf30250fe108065f07453ec124dbf223420f57f5e749b04295e090", size = 94932, upload-time = "2026-03-01T22:06:39.579Z" }, - { url = "https://files.pythonhosted.org/packages/c6/cc/d79ba8292f51f81f4dc533a8ccfb9fc6992cabf0998ed3245de7589dc07c/yarl-1.23.0-cp313-cp313t-win_arm64.whl", hash = "sha256:ac09d42f48f80c9ee1635b2fcaa819496a44502737660d3c0f2ade7526d29144", size = 84786, upload-time = "2026-03-01T22:06:41.988Z" }, - { url = "https://files.pythonhosted.org/packages/90/98/b85a038d65d1b92c3903ab89444f48d3cee490a883477b716d7a24b1a78c/yarl-1.23.0-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:21d1b7305a71a15b4794b5ff22e8eef96ff4a6d7f9657155e5aa419444b28912", size = 124455, upload-time = "2026-03-01T22:06:43.615Z" }, - { url = "https://files.pythonhosted.org/packages/39/54/bc2b45559f86543d163b6e294417a107bb87557609007c007ad889afec18/yarl-1.23.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:85610b4f27f69984932a7abbe52703688de3724d9f72bceb1cca667deff27474", size = 86752, upload-time = "2026-03-01T22:06:45.425Z" }, - { url = "https://files.pythonhosted.org/packages/24/f9/e8242b68362bffe6fb536c8db5076861466fc780f0f1b479fc4ffbebb128/yarl-1.23.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:23f371bd662cf44a7630d4d113101eafc0cfa7518a2760d20760b26021454719", size = 86291, upload-time = "2026-03-01T22:06:46.974Z" }, - { url = "https://files.pythonhosted.org/packages/ea/d8/d1cb2378c81dd729e98c716582b1ccb08357e8488e4c24714658cc6630e8/yarl-1.23.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c4a80f77dc1acaaa61f0934176fccca7096d9b1ff08c8ba9cddf5ae034a24319", size = 99026, upload-time = "2026-03-01T22:06:48.459Z" }, - { url = "https://files.pythonhosted.org/packages/0a/ff/7196790538f31debe3341283b5b0707e7feb947620fc5e8236ef28d44f72/yarl-1.23.0-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:bd654fad46d8d9e823afbb4f87c79160b5a374ed1ff5bde24e542e6ba8f41434", size = 92355, upload-time = "2026-03-01T22:06:50.306Z" }, - { url = "https://files.pythonhosted.org/packages/c1/56/25d58c3eddde825890a5fe6aa1866228377354a3c39262235234ab5f616b/yarl-1.23.0-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:682bae25f0a0dd23a056739f23a134db9f52a63e2afd6bfb37ddc76292bbd723", size = 106417, upload-time = "2026-03-01T22:06:52.1Z" }, - { url = "https://files.pythonhosted.org/packages/51/8a/882c0e7bc8277eb895b31bce0138f51a1ba551fc2e1ec6753ffc1e7c1377/yarl-1.23.0-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:a82836cab5f197a0514235aaf7ffccdc886ccdaa2324bc0aafdd4ae898103039", size = 106422, upload-time = "2026-03-01T22:06:54.424Z" }, - { url = "https://files.pythonhosted.org/packages/42/2b/fef67d616931055bf3d6764885990a3ac647d68734a2d6a9e1d13de437a2/yarl-1.23.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1c57676bdedc94cd3bc37724cf6f8cd2779f02f6aba48de45feca073e714fe52", size = 101915, upload-time = "2026-03-01T22:06:55.895Z" }, - { url = "https://files.pythonhosted.org/packages/18/6a/530e16aebce27c5937920f3431c628a29a4b6b430fab3fd1c117b26ff3f6/yarl-1.23.0-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:c7f8dc16c498ff06497c015642333219871effba93e4a2e8604a06264aca5c5c", size = 100690, upload-time = "2026-03-01T22:06:58.21Z" }, - { url = "https://files.pythonhosted.org/packages/88/08/93749219179a45e27b036e03260fda05190b911de8e18225c294ac95bbc9/yarl-1.23.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:5ee586fb17ff8f90c91cf73c6108a434b02d69925f44f5f8e0d7f2f260607eae", size = 98750, upload-time = "2026-03-01T22:06:59.794Z" }, - { url = "https://files.pythonhosted.org/packages/d9/cf/ea424a004969f5d81a362110a6ac1496d79efdc6d50c2c4b2e3ea0fc2519/yarl-1.23.0-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:17235362f580149742739cc3828b80e24029d08cbb9c4bda0242c7b5bc610a8e", size = 94685, upload-time = "2026-03-01T22:07:01.375Z" }, - { url = "https://files.pythonhosted.org/packages/e2/b7/14341481fe568e2b0408bcf1484c652accafe06a0ade9387b5d3fd9df446/yarl-1.23.0-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:0793e2bd0cf14234983bbb371591e6bea9e876ddf6896cdcc93450996b0b5c85", size = 106009, upload-time = "2026-03-01T22:07:03.151Z" }, - { url = "https://files.pythonhosted.org/packages/0a/e6/5c744a9b54f4e8007ad35bce96fbc9218338e84812d36f3390cea616881a/yarl-1.23.0-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:3650dc2480f94f7116c364096bc84b1d602f44224ef7d5c7208425915c0475dd", size = 100033, upload-time = "2026-03-01T22:07:04.701Z" }, - { url = "https://files.pythonhosted.org/packages/0c/23/e3bfc188d0b400f025bc49d99793d02c9abe15752138dcc27e4eaf0c4a9e/yarl-1.23.0-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:f40e782d49630ad384db66d4d8b73ff4f1b8955dc12e26b09a3e3af064b3b9d6", size = 106483, upload-time = "2026-03-01T22:07:06.231Z" }, - { url = "https://files.pythonhosted.org/packages/72/42/f0505f949a90b3f8b7a363d6cbdf398f6e6c58946d85c6d3a3bc70595b26/yarl-1.23.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:94f8575fbdf81749008d980c17796097e645574a3b8c28ee313931068dad14fe", size = 102175, upload-time = "2026-03-01T22:07:08.4Z" }, - { url = "https://files.pythonhosted.org/packages/aa/65/b39290f1d892a9dd671d1c722014ca062a9c35d60885d57e5375db0404b5/yarl-1.23.0-cp314-cp314-win32.whl", hash = "sha256:c8aa34a5c864db1087d911a0b902d60d203ea3607d91f615acd3f3108ac32169", size = 83871, upload-time = "2026-03-01T22:07:09.968Z" }, - { url = "https://files.pythonhosted.org/packages/a9/5b/9b92f54c784c26e2a422e55a8d2607ab15b7ea3349e28359282f84f01d43/yarl-1.23.0-cp314-cp314-win_amd64.whl", hash = "sha256:63e92247f383c85ab00dd0091e8c3fa331a96e865459f5ee80353c70a4a42d70", size = 89093, upload-time = "2026-03-01T22:07:11.501Z" }, - { url = "https://files.pythonhosted.org/packages/e0/7d/8a84dc9381fd4412d5e7ff04926f9865f6372b4c2fd91e10092e65d29eb8/yarl-1.23.0-cp314-cp314-win_arm64.whl", hash = "sha256:70efd20be968c76ece7baa8dafe04c5be06abc57f754d6f36f3741f7aa7a208e", size = 83384, upload-time = "2026-03-01T22:07:13.069Z" }, - { url = "https://files.pythonhosted.org/packages/dd/8d/d2fad34b1c08aa161b74394183daa7d800141aaaee207317e82c790b418d/yarl-1.23.0-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:9a18d6f9359e45722c064c97464ec883eb0e0366d33eda61cb19a244bf222679", size = 131019, upload-time = "2026-03-01T22:07:14.903Z" }, - { url = "https://files.pythonhosted.org/packages/19/ff/33009a39d3ccf4b94d7d7880dfe17fb5816c5a4fe0096d9b56abceea9ac7/yarl-1.23.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:2803ed8b21ca47a43da80a6fd1ed3019d30061f7061daa35ac54f63933409412", size = 89894, upload-time = "2026-03-01T22:07:17.372Z" }, - { url = "https://files.pythonhosted.org/packages/0c/f1/dab7ac5e7306fb79c0190766a3c00b4cb8d09a1f390ded68c85a5934faf5/yarl-1.23.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:394906945aa8b19fc14a61cf69743a868bb8c465efe85eee687109cc540b98f4", size = 89979, upload-time = "2026-03-01T22:07:19.361Z" }, - { url = "https://files.pythonhosted.org/packages/aa/b1/08e95f3caee1fad6e65017b9f26c1d79877b502622d60e517de01e72f95d/yarl-1.23.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:71d006bee8397a4a89f469b8deb22469fe7508132d3c17fa6ed871e79832691c", size = 95943, upload-time = "2026-03-01T22:07:21.266Z" }, - { url = "https://files.pythonhosted.org/packages/c0/cc/6409f9018864a6aa186c61175b977131f373f1988e198e031236916e87e4/yarl-1.23.0-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:62694e275c93d54f7ccedcfef57d42761b2aad5234b6be1f3e3026cae4001cd4", size = 88786, upload-time = "2026-03-01T22:07:23.129Z" }, - { url = "https://files.pythonhosted.org/packages/76/40/cc22d1d7714b717fde2006fad2ced5efe5580606cb059ae42117542122f3/yarl-1.23.0-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a31de1613658308efdb21ada98cbc86a97c181aa050ba22a808120bb5be3ab94", size = 101307, upload-time = "2026-03-01T22:07:24.689Z" }, - { url = "https://files.pythonhosted.org/packages/8f/0d/476c38e85ddb4c6ec6b20b815bdd779aa386a013f3d8b85516feee55c8dc/yarl-1.23.0-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:fb1e8b8d66c278b21d13b0a7ca22c41dd757a7c209c6b12c313e445c31dd3b28", size = 100904, upload-time = "2026-03-01T22:07:26.287Z" }, - { url = "https://files.pythonhosted.org/packages/72/32/0abe4a76d59adf2081dcb0397168553ece4616ada1c54d1c49d8936c74f8/yarl-1.23.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:50f9d8d531dfb767c565f348f33dd5139a6c43f5cbdf3f67da40d54241df93f6", size = 97728, upload-time = "2026-03-01T22:07:27.906Z" }, - { url = "https://files.pythonhosted.org/packages/b7/35/7b30f4810fba112f60f5a43237545867504e15b1c7647a785fbaf588fac2/yarl-1.23.0-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:575aa4405a656e61a540f4a80eaa5260f2a38fff7bfdc4b5f611840d76e9e277", size = 95964, upload-time = "2026-03-01T22:07:30.198Z" }, - { url = "https://files.pythonhosted.org/packages/2d/86/ed7a73ab85ef00e8bb70b0cb5421d8a2a625b81a333941a469a6f4022828/yarl-1.23.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:041b1a4cefacf65840b4e295c6985f334ba83c30607441ae3cf206a0eed1a2e4", size = 95882, upload-time = "2026-03-01T22:07:32.132Z" }, - { url = "https://files.pythonhosted.org/packages/19/90/d56967f61a29d8498efb7afb651e0b2b422a1e9b47b0ab5f4e40a19b699b/yarl-1.23.0-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:d38c1e8231722c4ce40d7593f28d92b5fc72f3e9774fe73d7e800ec32299f63a", size = 90797, upload-time = "2026-03-01T22:07:34.404Z" }, - { url = "https://files.pythonhosted.org/packages/72/00/8b8f76909259f56647adb1011d7ed8b321bcf97e464515c65016a47ecdf0/yarl-1.23.0-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:d53834e23c015ee83a99377db6e5e37d8484f333edb03bd15b4bc312cc7254fb", size = 101023, upload-time = "2026-03-01T22:07:35.953Z" }, - { url = "https://files.pythonhosted.org/packages/ac/e2/cab11b126fb7d440281b7df8e9ddbe4851e70a4dde47a202b6642586b8d9/yarl-1.23.0-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:2e27c8841126e017dd2a054a95771569e6070b9ee1b133366d8b31beb5018a41", size = 96227, upload-time = "2026-03-01T22:07:37.594Z" }, - { url = "https://files.pythonhosted.org/packages/c2/9b/2c893e16bfc50e6b2edf76c1a9eb6cb0c744346197e74c65e99ad8d634d0/yarl-1.23.0-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:76855800ac56f878847a09ce6dba727c93ca2d89c9e9d63002d26b916810b0a2", size = 100302, upload-time = "2026-03-01T22:07:39.334Z" }, - { url = "https://files.pythonhosted.org/packages/28/ec/5498c4e3a6d5f1003beb23405671c2eb9cdbf3067d1c80f15eeafe301010/yarl-1.23.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:e09fd068c2e169a7070d83d3bde728a4d48de0549f975290be3c108c02e499b4", size = 98202, upload-time = "2026-03-01T22:07:41.717Z" }, - { url = "https://files.pythonhosted.org/packages/fe/c3/cd737e2d45e70717907f83e146f6949f20cc23cd4bf7b2688727763aa458/yarl-1.23.0-cp314-cp314t-win32.whl", hash = "sha256:73309162a6a571d4cbd3b6a1dcc703c7311843ae0d1578df6f09be4e98df38d4", size = 90558, upload-time = "2026-03-01T22:07:43.433Z" }, - { url = "https://files.pythonhosted.org/packages/e1/19/3774d162f6732d1cfb0b47b4140a942a35ca82bb19b6db1f80e9e7bdc8f8/yarl-1.23.0-cp314-cp314t-win_amd64.whl", hash = "sha256:4503053d296bc6e4cbd1fad61cf3b6e33b939886c4f249ba7c78b602214fabe2", size = 97610, upload-time = "2026-03-01T22:07:45.773Z" }, - { url = "https://files.pythonhosted.org/packages/51/47/3fa2286c3cb162c71cdb34c4224d5745a1ceceb391b2bd9b19b668a8d724/yarl-1.23.0-cp314-cp314t-win_arm64.whl", hash = "sha256:44bb7bef4ea409384e3f8bc36c063d77ea1b8d4a5b2706956c0d6695f07dcc25", size = 86041, upload-time = "2026-03-01T22:07:49.026Z" }, - { url = "https://files.pythonhosted.org/packages/69/68/c8739671f5699c7dc470580a4f821ef37c32c4cb0b047ce223a7f115757f/yarl-1.23.0-py3-none-any.whl", hash = "sha256:a2df6afe50dea8ae15fa34c9f824a3ee958d785fd5d089063d960bae1daa0a3f", size = 48288, upload-time = "2026-03-01T22:07:51.388Z" }, + { url = "https://files.pythonhosted.org/packages/85/92/55fa9ee84cb8ec9930a910b5753936a926f918d8cc8965bdac571479c095/yarl-1.25.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:142c06c4d6a35ee3ec5da08499805e879cb3ca7c1fbfbecb0140fe72403818d6", size = 144695, upload-time = "2026-09-15T19:29:53.114Z" }, + { url = "https://files.pythonhosted.org/packages/16/b4/9edc8e605b16b2eb5bd0c2ccc73e2b15aab583862460767fb43f91f11839/yarl-1.25.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:24ce942011a61953e7d313438038f4d32ff21387b775f58a957f7a07dd55ef95", size = 104332, upload-time = "2026-09-15T19:29:55.443Z" }, + { url = "https://files.pythonhosted.org/packages/ae/de/4204e6646e278b1cd4a9cf73ebe8b7cfcf16693f1249b324eb273d67602a/yarl-1.25.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9e23c82b63cd7652fc24d33ed6cc17099d607aa3b4fc4ddc75e95062f3d82df4", size = 104449, upload-time = "2026-09-15T19:29:57.239Z" }, + { url = "https://files.pythonhosted.org/packages/1d/fc/21d74789198ad68a23a209ab0d73fe5a52d39ebbd9945041e72827acdd77/yarl-1.25.1-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8ee202350cf57abf0e9502a41601841019c25d3db7ff52d980aaf31446254059", size = 116828, upload-time = "2026-09-15T19:29:59.031Z" }, + { url = "https://files.pythonhosted.org/packages/8f/31/90891ddb61848c067ebd1fb505ab5902a6e7d4707c2f3823f67ff37883d3/yarl-1.25.1-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:5df89f769cc8ff94c3d7e7603386fba309d25ce5240132d26c15baa8d0e96c4c", size = 107150, upload-time = "2026-09-15T19:30:00.868Z" }, + { url = "https://files.pythonhosted.org/packages/a1/15/f3d18743d3688b5f01aa83034b6c00665692ab20e1d0c89a29000d4979ea/yarl-1.25.1-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:83e9f4a25085bd4b7214701a0794ff1f50fc633ffb8bdfebf07abdd81c2db126", size = 124704, upload-time = "2026-09-15T19:30:03.128Z" }, + { url = "https://files.pythonhosted.org/packages/99/37/718789d8004775d6a2db86b2afc72b1d156e0590b88a1b8634ddd4bdb8ee/yarl-1.25.1-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:e636b64d24fd9c38053c5e389a1174c66361fa49dcfd220f4dd35b4abde7cb89", size = 129246, upload-time = "2026-09-15T19:30:05.014Z" }, + { url = "https://files.pythonhosted.org/packages/28/b9/7818ac6dec7fbcd16be2d19495807c01e2c38834e57d41c63356a75e786b/yarl-1.25.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e5637ca8d0bd7fb72648a6c7934af4baaccb697657f7438c9d264fc2abb8b0b1", size = 118071, upload-time = "2026-09-15T19:30:06.977Z" }, + { url = "https://files.pythonhosted.org/packages/b2/e3/8d098cafb30a64df7283b5a5dd0d32d22a71b18a1b9ec071d0776ffe5c2a/yarl-1.25.1-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:683e362b8ba453080f7489c66f4ea794e751c35b72e7eab3575ef784c2fbc7fb", size = 116180, upload-time = "2026-09-15T19:30:08.836Z" }, + { url = "https://files.pythonhosted.org/packages/20/9c/fbe9432478d87e00eef80242e15179639df162cb3d5d8d978fc56dcb6c51/yarl-1.25.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:df23df54b5114a17c2d0ef192433e2e5a9f0c5178c32375e90b7cfc965f349d0", size = 116578, upload-time = "2026-09-15T19:30:10.782Z" }, + { url = "https://files.pythonhosted.org/packages/b1/8e/b3dfd03732236b86b0bcf06a72a37de412ff6f82e719a947c3c651d4dece/yarl-1.25.1-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:f53dcd26694f148f738edc052b5a69234833e739f10f4c3287bdfd8ec0f7b326", size = 108886, upload-time = "2026-09-15T19:30:12.951Z" }, + { url = "https://files.pythonhosted.org/packages/83/e1/94dacb650d4963d5f844bc3df7ba70288cb7b68ed5a4d070da71acb19b14/yarl-1.25.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:b8075fe90bc08e40b8b8a1874fab42ee4c7b56af05c5886e9cc841397f916908", size = 124098, upload-time = "2026-09-15T19:30:14.963Z" }, + { url = "https://files.pythonhosted.org/packages/d6/3f/c93f76a218258c7bfc60dd27fd56e9102bdbc625517f4a6ee673295fe4e4/yarl-1.25.1-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:a8c2b841478068440d8b733005d13a5ef535b9928cbc05f17182d410f32ba449", size = 115768, upload-time = "2026-09-15T19:30:16.736Z" }, + { url = "https://files.pythonhosted.org/packages/a8/79/4d93f13c3b05cda3c962805dec28cbc255c50239b3457808abc5633a00c2/yarl-1.25.1-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:ca32926d7d77bcc8838425c4c95e040a3ace1cb7dfdae599013458dcda2607ca", size = 122461, upload-time = "2026-09-15T19:30:18.901Z" }, + { url = "https://files.pythonhosted.org/packages/c5/8e/e2ba83b3a9bfc1d3b882ad35fa8abc04a7af4d9356f2e329a23d0c8d889d/yarl-1.25.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:192a866877a49993949ef1975864ad8728bea28ee810f6abe1a0729c2b500426", size = 118295, upload-time = "2026-09-15T19:30:21.07Z" }, + { url = "https://files.pythonhosted.org/packages/42/67/cb5ea1baa0c0ac60bda44ce59f601133154af2a2e67722d3517f8793855d/yarl-1.25.1-cp310-cp310-win_amd64.whl", hash = "sha256:3f4d48a6112712973e676bd792121fee470e432d749177162d9949d5c9460a1b", size = 102929, upload-time = "2026-09-15T19:30:23.122Z" }, + { url = "https://files.pythonhosted.org/packages/2f/85/9a1e98de10fc0e738d517efd2a9984c3e7db6cf35fa72b2b373988a9e9b7/yarl-1.25.1-cp310-cp310-win_arm64.whl", hash = "sha256:48796ea00a303961507dc6c8437c4b325a6fc3f95f7c36c71b91ea9a8150963c", size = 98854, upload-time = "2026-09-15T19:30:25.102Z" }, + { url = "https://files.pythonhosted.org/packages/83/b3/2cea721d495ca57f8f414aa4867ee263f486b274e07463158cf52f02ba7f/yarl-1.25.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:9d693bf4bf534e9ba3ae2780cfd577f5135629f7b5ac653490859d0b77864865", size = 143794, upload-time = "2026-09-15T19:30:26.946Z" }, + { url = "https://files.pythonhosted.org/packages/55/e6/cd145cff8e5cf60b8b3c41fbecfa2a45028a8dec3fbc52bec03595ff3d3b/yarl-1.25.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ab2054c5531af2a9ba7b69b8ec91e4f884420e83a8c5e579b013084cb57e5e5d", size = 103993, upload-time = "2026-09-15T19:30:28.661Z" }, + { url = "https://files.pythonhosted.org/packages/ce/7c/fbb40fe2d53747c40aa36a9e2bd2178a202f942bda0b670f3306d4aefbce/yarl-1.25.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:564fdc7085d2245ab84f88882fdb1d6ac0723124bff6ded35bfb1c00f812630d", size = 104010, upload-time = "2026-09-15T19:30:31.069Z" }, + { url = "https://files.pythonhosted.org/packages/f0/0b/5a516f70641092283f57cf3670bdb75e7327bcc0dcb5038697e4dfbfd569/yarl-1.25.1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:acae6b45d1ace09b6ba3876da43b88366ef368f73b988c7f57e14231753d4420", size = 116444, upload-time = "2026-09-15T19:30:32.894Z" }, + { url = "https://files.pythonhosted.org/packages/b6/8a/d1a627f827b0a404ae0f5647cab0534959081cde13b0756a783469fb3b5e/yarl-1.25.1-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:1fb2a01ba8cd9c5d2c5dc1ec35e0fc951d04b4f037541d4ac090c993ce58b3d7", size = 107565, upload-time = "2026-09-15T19:30:35.188Z" }, + { url = "https://files.pythonhosted.org/packages/aa/cf/c8e0aaec886840a6c4480fe44eaec7cd4319f79a563b79321473be79c56f/yarl-1.25.1-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:e92b6bcc741b86d67606c40d3cb9c7cc8e6c737f81e31f4a94efc204456c92e3", size = 125006, upload-time = "2026-09-15T19:30:37.1Z" }, + { url = "https://files.pythonhosted.org/packages/50/26/0cce366d54a93cdc8342965dc7663385e4db161625cc1e8b18e786753d24/yarl-1.25.1-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:72c34ac7ad4314c19362d5ce27626dcc8429bd30bbf8c179f4234078851f9492", size = 128717, upload-time = "2026-09-15T19:30:38.904Z" }, + { url = "https://files.pythonhosted.org/packages/95/0c/a71501bbc1a674ff72c4d6c2b75f4d9a5af819f5244c3a7558080a8802c5/yarl-1.25.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d5add7b4ca7afeea91d52e4d4e4db3b1fe9885b71f07054560d8c4296b7441a2", size = 117728, upload-time = "2026-09-15T19:30:40.809Z" }, + { url = "https://files.pythonhosted.org/packages/e7/6f/c3267ca01defeed9ed9c4ff9b17bd54915432c405945233265b707475d1c/yarl-1.25.1-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:def538065f9e4d4cf1ae164bd59aba00dfa84f03923e0de4c3788f252d6bcd17", size = 116224, upload-time = "2026-09-15T19:30:42.818Z" }, + { url = "https://files.pythonhosted.org/packages/8f/69/fad57ee52d648431718ee0f1f68966a99c1352c3924688ffbdcc9d3fe51a/yarl-1.25.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:0a191bfdb30a79b98e5d175d75285f9fcb78bf0e46ba5efda042e1c72071a0de", size = 116299, upload-time = "2026-09-15T19:30:44.966Z" }, + { url = "https://files.pythonhosted.org/packages/2a/d4/6a8c1e29f33338687ca278cba0a8fbf6525a322c2c02a9a500ccbe041152/yarl-1.25.1-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:71f42c5b9a948c113bbdebfa544598321431d064ff959d32e99b1feb61d68345", size = 108625, upload-time = "2026-09-15T19:30:46.874Z" }, + { url = "https://files.pythonhosted.org/packages/e8/d2/3a35ae791c9cb6522c106923ff25c3230d999091e5e65511bca23bbd9914/yarl-1.25.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:72849d892954be4d09e569b8b831ac39ce58417fedc767d4308a0fe542018a40", size = 124515, upload-time = "2026-09-15T19:30:49.082Z" }, + { url = "https://files.pythonhosted.org/packages/be/fd/2b022109a6b4af0f7dc371cf7500af380b0d4f034010243e1b0ce218dc93/yarl-1.25.1-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:efb01a106f971cb3752856bca2318bbdf7f01bd8823779c461586cbe5ffd5258", size = 115711, upload-time = "2026-09-15T19:30:51.208Z" }, + { url = "https://files.pythonhosted.org/packages/18/59/f7586271136c3ddb0126bbfe661844699369b76b555fe38c4efe86870b2e/yarl-1.25.1-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:a1daf47cd95a7c3a63456336bc5aaa8c86dd3a47d07ed3d0e76132ae4666a5a1", size = 122751, upload-time = "2026-09-15T19:30:53.535Z" }, + { url = "https://files.pythonhosted.org/packages/a0/0b/07f7a2d881f7e16c385b47fc1753382600847cad305dcc7fa0c25828acf8/yarl-1.25.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:9489e6abf47ba37f332075a91444c7cfedb03e6ce99fbb2f116bfe1ce810da3b", size = 117983, upload-time = "2026-09-15T19:30:55.277Z" }, + { url = "https://files.pythonhosted.org/packages/aa/9d/8cdceec66a9b940700cb45931741403f045b162afd79bcb93c41cadd0972/yarl-1.25.1-cp311-cp311-win_amd64.whl", hash = "sha256:d7306dee25b8a0e737363f347362b875094b4dc4e367311470656ae420fdbf8e", size = 102894, upload-time = "2026-09-15T19:30:57.606Z" }, + { url = "https://files.pythonhosted.org/packages/17/f1/7ec357db1d3ad2863542d71e8fe64a126bbec17b134cd7d30951196809a5/yarl-1.25.1-cp311-cp311-win_arm64.whl", hash = "sha256:abb1384477f5901d436b5d2e5465954de46ea6098f59163d243660b5c4461d35", size = 98609, upload-time = "2026-09-15T19:30:59.705Z" }, + { url = "https://files.pythonhosted.org/packages/75/b3/cd32ac66ae622b854c2df0ac52106dda220d361b65a64fde7d5b3684aa3f/yarl-1.25.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:94d7aa6debf92a1dd14cb5280b083a764169a13cfb23a452111160274ed989f4", size = 144798, upload-time = "2026-09-15T19:31:01.821Z" }, + { url = "https://files.pythonhosted.org/packages/61/fb/a2c52a8007c2051ba74662afb112ecf3d00346af4c25e33df9d80fd14fb8/yarl-1.25.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:83d4a37e4b95da4d8bda930d6d35b75b4cdadbacbb4980cae290ea3100b5d51d", size = 104583, upload-time = "2026-09-15T19:31:04.05Z" }, + { url = "https://files.pythonhosted.org/packages/be/dd/ee38aec8e09fdf957e50d4085453fbe202f56c6c3b4cf07b81cdb4f09ee9/yarl-1.25.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:e029648f9c951db30e98a7d7ec90835db88ec4b32820efe2a9bdc2287e032eb6", size = 104325, upload-time = "2026-09-15T19:31:06.338Z" }, + { url = "https://files.pythonhosted.org/packages/1e/b3/058dbfb1857b484c9cf9cc135659f50b85ce66e03c99e44dc2f7b6161f55/yarl-1.25.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4d781294bb815ecb5ea57ff6bbf8038e0a31a95fdf3e1788f66e0dc100d64b58", size = 115358, upload-time = "2026-09-15T19:31:08.593Z" }, + { url = "https://files.pythonhosted.org/packages/db/39/29693446cf0cf6b15a0e2f75a5d40f93c56819b05b0622196f45e95b5cc0/yarl-1.25.1-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:e12c538e00e7c1b286a07061046b90e8124e6a9793efae2c70db6a4aad07faad", size = 107658, upload-time = "2026-09-15T19:31:10.802Z" }, + { url = "https://files.pythonhosted.org/packages/86/b3/3c4dd7e1af43b931fba95e0a722737f2ea94a6d199c802585282831d7abd/yarl-1.25.1-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:7e4de3ac4adbad3d0bc7c6f4360a7dbff5de2f15e3b723be3198074e17fd9c40", size = 122660, upload-time = "2026-09-15T19:31:12.84Z" }, + { url = "https://files.pythonhosted.org/packages/bd/b5/1b60dbc3cfc9c5712b15148c206748f2bc93953ffdbe25ea75b63dfc89c9/yarl-1.25.1-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:419f392a1da624877975709e3864dfe833af6cc7671b39318086d456e288380c", size = 126506, upload-time = "2026-09-15T19:31:15.088Z" }, + { url = "https://files.pythonhosted.org/packages/bc/7b/ca212cbe170ac8b96e45317ecbcf9c3c3ecf0cdec98d5b088a9c4088929b/yarl-1.25.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c6f117789d22dce188e5754e8bc65b7e6ebf8cb73963b9fa761f672a5883769d", size = 117050, upload-time = "2026-09-15T19:31:17.241Z" }, + { url = "https://files.pythonhosted.org/packages/cb/c3/72b4938cdbe619ad71ac156182faef4908846b84dc3ca4dbb4c4e6f84014/yarl-1.25.1-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:80e47012e730da131c9f059c80936783f9659aae22dc31c03c0595590d11ed54", size = 114174, upload-time = "2026-09-15T19:31:19.294Z" }, + { url = "https://files.pythonhosted.org/packages/e8/43/268717870f9ba0cc9701a95181587f6dc8c5f387aab4aeecc83158f38a79/yarl-1.25.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e80f557716fd765439577131e526b8942ffc2c07bdbc5e39fa62f660ba1e963f", size = 114944, upload-time = "2026-09-15T19:31:21.414Z" }, + { url = "https://files.pythonhosted.org/packages/da/84/baa5bf504d51fe062c4bcaf62936da97fffb43285978d0b39984824231fd/yarl-1.25.1-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:f61964f235a43738bfac50da46fc4254943a7eea3051aeb0b6fc7c992c29fadc", size = 108263, upload-time = "2026-09-15T19:31:23.388Z" }, + { url = "https://files.pythonhosted.org/packages/a4/28/779a2ed9e0152a601a27039bed9aead3f0b79797a67e2c44bfa444622dd8/yarl-1.25.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:e546fe1d4a93ebc2910f0d768baff19faa09843ab3f2036a67ed6e69fae4419d", size = 122184, upload-time = "2026-09-15T19:31:25.343Z" }, + { url = "https://files.pythonhosted.org/packages/f8/1f/118e9e5b8f07694d63fd3222e801d7782270003f1a222aa798df3f8d5933/yarl-1.25.1-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:cce0727fd5ac04d372fa9bbfde9febc2bcf209aadfcf0468e45dec72719895d1", size = 114001, upload-time = "2026-09-15T19:31:27.465Z" }, + { url = "https://files.pythonhosted.org/packages/0f/ae/a4cf1cf372313734b17996d4007f9f73596e7a178b9485802e5494ecf484/yarl-1.25.1-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:af4ea5b37403ef4e30f3927eaed540db942bde01d8d3ff083527c0704d1c9c68", size = 120565, upload-time = "2026-09-15T19:31:29.47Z" }, + { url = "https://files.pythonhosted.org/packages/05/79/ad94f93ca731bc9e44d321833ab96b82a4f9f5f63cf773f81a4aeea5ecc1/yarl-1.25.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:68782fdb4027b8d1eee25ec35e9a6db05e863b899eb0310b3a33b6c3fef55707", size = 117060, upload-time = "2026-09-15T19:31:31.367Z" }, + { url = "https://files.pythonhosted.org/packages/bb/cc/51a7b4abf4ac593b8e7eb3794b28e5a35ae26eed8bc04787628d215af82f/yarl-1.25.1-cp312-cp312-win_amd64.whl", hash = "sha256:7d575b54cb3863ef9bc290ea4b009999d55dc237326131e4853cf33e888fee03", size = 102593, upload-time = "2026-09-15T19:31:33.329Z" }, + { url = "https://files.pythonhosted.org/packages/9d/21/0941a6b93a58b59a1ec75e5333bf06929b671309c43c0cd201c172d9c39f/yarl-1.25.1-cp312-cp312-win_arm64.whl", hash = "sha256:bc3ac7bf569f6b64dad04dd7808c7872dae8a97df657856eac05e9b7e3614a85", size = 97697, upload-time = "2026-09-15T19:31:35.855Z" }, + { url = "https://files.pythonhosted.org/packages/7b/ed/2f3129bbcc9a5c8ba12cc2b29d8060a3bab9c8043c456cfd4b5ca3188890/yarl-1.25.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:25868beca8b6765f8f7d0e11fe6dd7c66dd4b0793b9500286d20cc92352126a5", size = 143623, upload-time = "2026-09-15T19:31:37.966Z" }, + { url = "https://files.pythonhosted.org/packages/17/e1/f1bc3390fdca352826676b531d0712736f156919090206700421d46b2c37/yarl-1.25.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:10b2fd95332f0d716d5eee3c9fb2ce8eada19082de7fee83d32e37992fd75c26", size = 104011, upload-time = "2026-09-15T19:31:40.25Z" }, + { url = "https://files.pythonhosted.org/packages/a8/aa/50acc5c3e5da04172ae3c281c75405af4d2ca911e16120ab0563f4dffb66/yarl-1.25.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:0f12afda4eea8c8994a76d4df1875c765194f5fbe8a9d197929ea303caee29ec", size = 103677, upload-time = "2026-09-15T19:31:42.46Z" }, + { url = "https://files.pythonhosted.org/packages/30/d2/7d1e0ab9f8390e1fbcede5a6dbf70d23c96ad09b8c5567f3a514d1ddb0e2/yarl-1.25.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:14b79a30a93a3ce2e8832603fd0ab780ada281b0ba5110b519a634f2d7d7d1fc", size = 115392, upload-time = "2026-09-15T19:31:44.371Z" }, + { url = "https://files.pythonhosted.org/packages/71/e1/5ba1e3a2a22139213655e760919038e8ed7e2d4a99826d0bbddb3beb96e5/yarl-1.25.1-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:4bd6340d20ae2c7ca719b87b426e808e90743b676d05d4c26c4fb5ca71f41184", size = 107493, upload-time = "2026-09-15T19:31:46.273Z" }, + { url = "https://files.pythonhosted.org/packages/f5/53/780653d5e0f73831f467cf13548912e5eec97f21dc49fc8daf21da027df4/yarl-1.25.1-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:126a2533570c554719ca40a1288fdee1700b6bc82e7131aa69fa85252d92e651", size = 122537, upload-time = "2026-09-15T19:31:48.654Z" }, + { url = "https://files.pythonhosted.org/packages/03/92/d54fa70236c6036271c9c9c09fd978df5cbe3ef49ef6c46e9b833476d215/yarl-1.25.1-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:a3faadac7d812ddac258feb57b9846b60c1b437c4f4b9ad42595c6f6fe4390df", size = 126170, upload-time = "2026-09-15T19:31:50.872Z" }, + { url = "https://files.pythonhosted.org/packages/0e/b7/a82a49bf88340b837ef6972b508a1604ae377b9e6904b46b10cf5f1cf925/yarl-1.25.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:be80550d9bfe83d9b62398a37081a90434e6df2d978ec345c3d2820de6beddab", size = 117012, upload-time = "2026-09-15T19:31:53.189Z" }, + { url = "https://files.pythonhosted.org/packages/ef/78/5d684b411e3f3602464ee9b538db48205038f8605872985f61efb809ced0/yarl-1.25.1-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:e07595c7d6f4db270ceede356a1bd1c07a34f1c26f958d1ed0cd7b48e0d2bba3", size = 114950, upload-time = "2026-09-15T19:31:55.694Z" }, + { url = "https://files.pythonhosted.org/packages/2f/11/51d82b852c64f7fad0fc7a7ff3031517204887e874c722bbca839c0b23ac/yarl-1.25.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:eb96ed1ae6c7d072d60840c0434aef07a2df611812810807fbc54263a6053e9a", size = 115428, upload-time = "2026-09-15T19:31:57.966Z" }, + { url = "https://files.pythonhosted.org/packages/e4/49/9d1978049bf646b9ea918313926453c6901b71c92f097467777d47d36a88/yarl-1.25.1-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:3feb99222553a8cbedfa52c2f59dd84c3f50d5b582c728d522caf8d72769a54b", size = 108428, upload-time = "2026-09-15T19:32:00.048Z" }, + { url = "https://files.pythonhosted.org/packages/43/35/7b8f1ebb45d7ec3dda7d1909bf44f458de41ef91e2937f107733582a5166/yarl-1.25.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:a2ed0ba415ccdf08f14bf544cb78346d0f76086707ffee24921a2c84dbf1305a", size = 121961, upload-time = "2026-09-15T19:32:02.436Z" }, + { url = "https://files.pythonhosted.org/packages/63/d6/d8b689ab7ca26edeb85f6ff28812aac7a25376eefc1780e303a7bfbaceff/yarl-1.25.1-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:2b49375d22299b0a834c2bca72f39aaecc270d96fb24c30424899676f487b22a", size = 114961, upload-time = "2026-09-15T19:32:04.456Z" }, + { url = "https://files.pythonhosted.org/packages/cf/d5/1a1798ea4dc6b7ee3260010a27907ebc697c95dae99817d817ed446d24aa/yarl-1.25.1-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:ef74070ac553c59eb4f04258722066d6c6135b7baa03b2e9f2da65c096e96d98", size = 120036, upload-time = "2026-09-15T19:32:06.5Z" }, + { url = "https://files.pythonhosted.org/packages/91/8d/b1b35ed7903da6669b1d367cb2c09436acd4ff508029b4f39a0c0c2058fc/yarl-1.25.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:0a66db89ea473abeac4b70523cafd94db3772380e565f9d28af7a179b7af71fa", size = 117276, upload-time = "2026-09-15T19:32:09.401Z" }, + { url = "https://files.pythonhosted.org/packages/3a/8f/4db01cef62caff0d7a4593ed694fb8a41a27a11158cab80d290221f13e57/yarl-1.25.1-cp313-cp313-win_amd64.whl", hash = "sha256:1f51020b2eb8a003c84925638ec63c21a750a4bddd3a22ec8eac6a742dadf1b9", size = 101945, upload-time = "2026-09-15T19:32:11.545Z" }, + { url = "https://files.pythonhosted.org/packages/c0/5e/3ce00497c5c0babb74d4130c10c3828ccd215b4819d12020c42429f991ac/yarl-1.25.1-cp313-cp313-win_arm64.whl", hash = "sha256:b10dd0557ba422715b5206b3743192135a6022acca8baec51aa127d0a75db8fe", size = 97270, upload-time = "2026-09-15T19:32:14.127Z" }, + { url = "https://files.pythonhosted.org/packages/80/cf/54023edfab7aa773b860503db0c56e962ccab0922803ee97988c176ea090/yarl-1.25.1-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:a9ca696eb02e5c02a8afd872ada510eba9b7fe6e68b9572c2e9a9b1941e31e2e", size = 143975, upload-time = "2026-09-15T19:32:16.416Z" }, + { url = "https://files.pythonhosted.org/packages/d7/a8/e6c1be0e6761d0f2d10bbf33a3e1e02b99dc83874d92945d7b461a72481e/yarl-1.25.1-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:a5877f2255aab518ebe528289037699201d5dc5f045f2396cb30aa02db22f57f", size = 104018, upload-time = "2026-09-15T19:32:18.364Z" }, + { url = "https://files.pythonhosted.org/packages/6e/bb/dda344765ffd3430afe1a1c66c866a57fae67786537d4f14607df6505ac1/yarl-1.25.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:7a5c3115595995779ee21f2567035793911c3802a43c74f3fbb0314929ec67ac", size = 104156, upload-time = "2026-09-15T19:32:20.459Z" }, + { url = "https://files.pythonhosted.org/packages/e5/5f/ed1538bcd06009fe990d6d283dd7667f639e62a81e35c6d8c6ef6c08fb3c/yarl-1.25.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:77e5099b99b37f3cf79c246998ca9f7313a78054cd1809ec46bc1afad47e1c4c", size = 116025, upload-time = "2026-09-15T19:32:22.766Z" }, + { url = "https://files.pythonhosted.org/packages/a2/af/2185daf56b99830d3356ecfada46faaa49945de6626e842b7728088d4980/yarl-1.25.1-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:6efaf45df6a849cef613a03a94c845647456662f85438c886bb67a9c027c8c2c", size = 106985, upload-time = "2026-09-15T19:32:24.749Z" }, + { url = "https://files.pythonhosted.org/packages/c1/65/bc1ae564fb4b04a30b6a8f250e787772581c57e4c3d5cf07ac3359de3103/yarl-1.25.1-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:d5f90e44653c4e0f78501ed9bb7d3fce835a8d62b7c6ed0cb16557534087e743", size = 123030, upload-time = "2026-09-15T19:32:27.084Z" }, + { url = "https://files.pythonhosted.org/packages/6a/3e/e2afcde10d74e53b3fa889960991efb3019beda2b1682a01de720a302056/yarl-1.25.1-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:632da579b2d879f6bad20f2cfa35ded1efe2f4f77f8abb26a6234a5b236acd2f", size = 126765, upload-time = "2026-09-15T19:32:29.332Z" }, + { url = "https://files.pythonhosted.org/packages/a2/be/415b00c0fe5a0615b062a456b26623d7ec91c2bee20faea1a14045aa0469/yarl-1.25.1-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:30eec96e8a91bd588ce897c9543f6d5d8d34b28fbcba28a4dedf20ebeae9fe57", size = 117199, upload-time = "2026-09-15T19:32:31.49Z" }, + { url = "https://files.pythonhosted.org/packages/97/27/3d8c63ddd3e8bcfd033748ab93876678ce59bacd66e4cb1ed851c9c5b37e/yarl-1.25.1-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:12b6bc4906e11f5e1a1cdcb12296e7afbd366c783cc8073403cd2fb74334e453", size = 115187, upload-time = "2026-09-15T19:32:34.137Z" }, + { url = "https://files.pythonhosted.org/packages/39/b7/7a81d0be1a502a26a0d4326c6f2ecb736c824f570ea1c6529f2b0b227b50/yarl-1.25.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:9d6ed3d17bccce4c05343e1ca8da13bc5c02c812a4e7282ddd05e8769322d3fc", size = 116085, upload-time = "2026-09-15T19:32:36.438Z" }, + { url = "https://files.pythonhosted.org/packages/f0/69/39fff459916aa0fab42215dc47b759586fd80f94aa56dfc4a7c15ba6e0dc/yarl-1.25.1-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:f38a70074041d3b7e138e452799f5174198bae5bd5ab2000917badf403908c5f", size = 107996, upload-time = "2026-09-15T19:32:38.959Z" }, + { url = "https://files.pythonhosted.org/packages/c0/39/80b9a55a3335590451d9ecf3eb593a8c635351f4c905ef056d7e8a8fd9e7/yarl-1.25.1-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:4ca89e4e21854ed27ec753297dde84b16c9f8e53b14a4866fb44457d643c19f8", size = 122549, upload-time = "2026-09-15T19:32:41.151Z" }, + { url = "https://files.pythonhosted.org/packages/42/7d/a179c6757818bb59372a4adafd09f7f26a3b4a0f04c3ae404b544c0b0c82/yarl-1.25.1-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:1ab7618921a93767387a4b83776f751588f5b5ae9bb5bc96620e2e2e00bca868", size = 115107, upload-time = "2026-09-15T19:32:43.072Z" }, + { url = "https://files.pythonhosted.org/packages/32/2b/a773ac867e4ab53a98ed98e5cefe3bae31e6f550252ca9d1de266f1a40c5/yarl-1.25.1-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:0ae12ff2b805fa02c4dab838005caef735e39986322698c48588d3beacb65c62", size = 120666, upload-time = "2026-09-15T19:32:45.061Z" }, + { url = "https://files.pythonhosted.org/packages/bc/41/52be6505e85b0f76b4f85b01b5de7e06a0512201abc2c95e14e099549174/yarl-1.25.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:90c30ed53546da833c700115c0064c22120d1b1560f474699fd31f22dd668233", size = 117505, upload-time = "2026-09-15T19:32:47.177Z" }, + { url = "https://files.pythonhosted.org/packages/f5/01/349c0386caedbbe488d519f252df54efac8a1459282d466c474bdd84a620/yarl-1.25.1-cp314-cp314-win_amd64.whl", hash = "sha256:acfa7e22aa6c6e7a5996a41d275bfa01efa7ea56ab890590280e9063e2cf5c1b", size = 103446, upload-time = "2026-09-15T19:32:49.615Z" }, + { url = "https://files.pythonhosted.org/packages/5c/f0/8ec63180f77912f0dc4e5a42760cb8c08d20da1d5ace3578a01b84d1f3d8/yarl-1.25.1-cp314-cp314-win_arm64.whl", hash = "sha256:8e7d98cdbb6d71e726f7d525952867096053d1f290dd4e3c50d7d313a136f414", size = 99159, upload-time = "2026-09-15T19:32:51.686Z" }, + { url = "https://files.pythonhosted.org/packages/47/7d/92d2220d6886b70ab1ed8579533ac2af2dfac716d5d929001daff7986df9/yarl-1.25.1-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:d21f0fa80a02d05299207eeaafef345d812ace96d5306e4ef265e1d419a615fa", size = 150071, upload-time = "2026-09-15T19:32:53.911Z" }, + { url = "https://files.pythonhosted.org/packages/64/fc/b245e448124bcda9340df38e3553fa222b50260fca027a84095e9bd8642d/yarl-1.25.1-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:17c9877a89fb6e2bca6f9087eb24cd7fb434653946ef5075e470d23d49b52287", size = 106780, upload-time = "2026-09-15T19:32:56.443Z" }, + { url = "https://files.pythonhosted.org/packages/51/e2/9a6ce2e334ebf218a30335ae76fb1696459430d42f733b8cb0d7d65b84d3/yarl-1.25.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:29273edf1530e397bd07cb784db1fbe0d2590b77569f2e24679a9c0a2d763b94", size = 107361, upload-time = "2026-09-15T19:32:58.827Z" }, + { url = "https://files.pythonhosted.org/packages/ed/70/66e8c76b569b450d16e190f15071c916c3df70b0e33927e415ac497cf0c2/yarl-1.25.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b7abffdf37af1cec6a2ad69b827aa84320db5894791bc8ed932dc93fb274b7e9", size = 114396, upload-time = "2026-09-15T19:33:02.24Z" }, + { url = "https://files.pythonhosted.org/packages/73/23/0d82838a05c57fdc05bc8b66e8c92dcc0df15e27463a5f163142d521c682/yarl-1.25.1-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:2239a02249d9326655419e0168a28ca9008938eaab31dc29fc875c217927a6c0", size = 104882, upload-time = "2026-09-15T19:33:04.494Z" }, + { url = "https://files.pythonhosted.org/packages/86/d4/ea08615c4edaa6049a13a2f1128944d068d1893abda7d708d4d7ea01599a/yarl-1.25.1-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:664ec6a520b74a1df2810666eb67695fcb77fa663e6ea0a25aaf2e529cb24dfa", size = 119485, upload-time = "2026-09-15T19:33:06.583Z" }, + { url = "https://files.pythonhosted.org/packages/1a/82/0898bdce9b1ae403b308b9c733d0d24af4a3464270c2c081f457b16c3e0d/yarl-1.25.1-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:4f1c91f5a5980a937ff8e238e98e6897e1ad74a4b1e2c0d68c73b5ffbb3f5c0b", size = 122490, upload-time = "2026-09-15T19:33:08.653Z" }, + { url = "https://files.pythonhosted.org/packages/d1/38/97d79b81c342b78246cfedb74809e68841f3198d21653e10d3232bd9c622/yarl-1.25.1-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7c88edaec8c349ad4c5ad4c486a3defcc4b80ceb2f074436ffa0a87caf5e76a6", size = 115336, upload-time = "2026-09-15T19:33:11.056Z" }, + { url = "https://files.pythonhosted.org/packages/8e/9d/2577896554cd310dc470adb6da0b7dd0b435cb63e2565204a7ac240e504c/yarl-1.25.1-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:35dcbea443fafb3eece757ad4e514560ddeb6c34cfae1582c620d7b293d7feee", size = 111825, upload-time = "2026-09-15T19:33:13.204Z" }, + { url = "https://files.pythonhosted.org/packages/29/6b/7ac49d8ba84a5c4bd73415a4c949d22c749cb3762579b3d50e48019a78aa/yarl-1.25.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:882569ff613758cac762a457a5d72d6e211b28d4bcfea89d1d71ea942b02eac0", size = 114655, upload-time = "2026-09-15T19:33:15.553Z" }, + { url = "https://files.pythonhosted.org/packages/e5/18/e5942a16723f5b72f9b1297fd5a85a54f6300cd15c0dcb5005b90cd89156/yarl-1.25.1-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:d0f1489233a254bb3643d2f05de7d59019254d81daeca6b9162fe9edef57e0c7", size = 106395, upload-time = "2026-09-15T19:33:17.599Z" }, + { url = "https://files.pythonhosted.org/packages/7b/2d/549fa46240781513ebc47ae7eb418df428a163a2a3d644cc9cbb3ecb7846/yarl-1.25.1-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:f41753a76f4f63927d03a0d8ba8f5ce0f2083bec29a8cfaccc55371b1564b96b", size = 119277, upload-time = "2026-09-15T19:33:19.973Z" }, + { url = "https://files.pythonhosted.org/packages/76/16/4763f78dcdc0b3b9fb3842b04afe72b9320857c6a69300c62a0eab03d119/yarl-1.25.1-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:8fb0eb4955adf0579001581f2f71a126e8781ba61bcd120f127b0401163c6c2d", size = 112504, upload-time = "2026-09-15T19:33:22.464Z" }, + { url = "https://files.pythonhosted.org/packages/ae/b4/974e3edfe0d188393ce1cb9de400111c63fe61f4eb3b772a500d84c970d1/yarl-1.25.1-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:a1e32763e641a1566507d90a8d3b19bfc3cc04a9d4e5ae3e32189874ed4b58a3", size = 116243, upload-time = "2026-09-15T19:33:24.788Z" }, + { url = "https://files.pythonhosted.org/packages/b0/aa/157b940428da80c104ca09666a740e51c94963df65d5b112e06b52e4d7a8/yarl-1.25.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:65b5b2066651b7432d389e9799d979c703bcc6ef44266bb8153ef54e91e4aab3", size = 115822, upload-time = "2026-09-15T19:33:26.886Z" }, + { url = "https://files.pythonhosted.org/packages/7e/af/19fbdce41412e1b96825544cc52cd7029d3724655d0988237972f078bd29/yarl-1.25.1-cp314-cp314t-win_amd64.whl", hash = "sha256:734f6e5400352ac4254456003d462866c684703570929cff7a7bde015d0cb371", size = 107386, upload-time = "2026-09-15T19:33:29.009Z" }, + { url = "https://files.pythonhosted.org/packages/2a/99/f6431c8968e89be608d74b28ae2d024521b2953f27dd44e0dece5e04f67a/yarl-1.25.1-cp314-cp314t-win_arm64.whl", hash = "sha256:287e99ff5aa4dc1c7630bfc683ded6f106d756c99dec432a2d7f197a784f51c6", size = 102094, upload-time = "2026-09-15T19:33:31.151Z" }, + { url = "https://files.pythonhosted.org/packages/54/22/318c7980066769c6bcd9221ed2248294f5698811da099013098c670565ed/yarl-1.25.1-py3-none-any.whl", hash = "sha256:681c758b0490f9e96b78e5fa8e8dc6e648e9185bb6eaebe73183c33ea0c445f3", size = 63617, upload-time = "2026-09-15T19:34:59.616Z" }, ] [[package]] From 7849ed2330362e5a3d06450e681f1fea7631a8e4 Mon Sep 17 00:00:00 2001 From: Mrinal Chanshetty Date: Tue, 20 Oct 2026 16:30:34 -0700 Subject: [PATCH 33/66] fix(pricing): port pricing helpers needed by #47419 Minimal port of helpers from #41523/#43890/#46647 needed by #47419; behavior changes of those PRs not included. Adds lookup_model_info_for_registration, model_info_with_pricing_overrides, runtime_model_cost_registrations (fields each register_model call set, tracked in a side table cleared on cost-map reload instead of on AliasedCostEntry), the flat-price variant helpers, Router._cost_map_backend_model, and Router._inherit_builtin_service_tier_pricing with the tier-suffixed threshold keys from #43890. --- .../litellm_core_utils/llm_cost_calc/utils.py | 9 +- litellm/router.py | 46 +++++++ litellm/utils.py | 130 +++++++++++++++++- 3 files changed, 183 insertions(+), 2 deletions(-) diff --git a/litellm/litellm_core_utils/llm_cost_calc/utils.py b/litellm/litellm_core_utils/llm_cost_calc/utils.py index 46bf2ec2960..d25b70e2450 100644 --- a/litellm/litellm_core_utils/llm_cost_calc/utils.py +++ b/litellm/litellm_core_utils/llm_cost_calc/utils.py @@ -75,6 +75,9 @@ _SERVICE_TIER_TO_COST_KEY_SUFFIX: Final[Mapping[str, str]] = MappingProxyType( ServiceTier.ULTRAFAST.value: ServiceTier.ULTRAFAST.value, } ) +SERVICE_TIER_COST_KEY_SUFFIXES: Final[tuple[str, ...]] = tuple( + sorted(frozenset(f"_{suffix}" for suffix in _SERVICE_TIER_TO_COST_KEY_SUFFIX.values())) +) _INCLUSIVE_THRESHOLD_PROVIDERS: Final = frozenset({"xai"}) _BATCH_KEY_SUFFIX: Final = "_batches" @@ -665,10 +668,14 @@ def _get_token_base_cost( # Exclude service_tier-specific variants (e.g. input_cost_per_token_above_200k_tokens_priority) # so that the threshold detection loop only processes standard keys. The # service_tier-specific above-threshold key is resolved later via _get_service_tier_cost_key. + tier_key_suffix: Final = _get_service_tier_cost_key("", service_tier) threshold_keys: Final = [ k for k in model_info - if k.startswith("input_cost_per_token_above_") and not k.endswith(_NON_STANDARD_THRESHOLD_SUFFIXES) + if k.startswith("input_cost_per_token_above_") + and ( + not k.endswith(_NON_STANDARD_THRESHOLD_SUFFIXES) or (tier_key_suffix != "" and k.endswith(tier_key_suffix)) + ) ] # Only sort the threshold keys (typically 1-2 keys instead of 66+) diff --git a/litellm/router.py b/litellm/router.py index d794311453c..aba87177a38 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -86,6 +86,7 @@ from litellm.litellm_core_utils.get_llm_provider_logic import ( is_registered_custom_provider, ) from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLogging +from litellm.litellm_core_utils.llm_cost_calc.utils import SERVICE_TIER_COST_KEY_SUFFIXES from litellm.litellm_core_utils.ptu_pricing import ( PTU_COST_ATTRIBUTION_ENV_VAR, declares_ptu, @@ -8838,6 +8839,11 @@ class Router: backend_model=deployment.litellm_params.model, custom_llm_provider=deployment.litellm_params.custom_llm_provider, ) + Router._inherit_builtin_service_tier_pricing( + model_info=_model_info, + backend_model=Router._cost_map_backend_model(deployment), + custom_llm_provider=deployment.litellm_params.custom_llm_provider, + ) Router._inherit_builtin_tiered_output_rate( model_info=_model_info, backend_model=deployment.litellm_params.model, @@ -9853,6 +9859,41 @@ class Router: return (backend_key, backend_key.replace("responses/", "")) return (backend_key,) + @staticmethod + def _inherit_builtin_service_tier_pricing( + model_info: dict, # mutable-ok: deployment cost-map entry filled in place + backend_model: str, + custom_llm_provider: str | None, + ) -> None: + """Inherit missing tier rates so a standalone entry does not fall back to custom standard rates.""" + if ptu_terms(model_info) is not None and is_ptu_cost_attribution_enabled(): + return + if all(model_info.get(field) is None for field in ("input_cost_per_token", "output_cost_per_token")): + return + try: + backend_info: Final = litellm.get_model_info(model=backend_model, custom_llm_provider=custom_llm_provider) + except Exception: # noqa: BLE001 # get_model_info raises plain Exception for an unmapped backend model + return + backend_entry: Final = litellm.model_cost.get(backend_info.get("key") or "") + if not isinstance(backend_entry, dict): + return + for field, backend_value in backend_entry.items(): + if not field.endswith(SERVICE_TIER_COST_KEY_SUFFIXES): + continue + if model_info.get(field) is not None or backend_value is None: + continue + model_info[field] = copy.deepcopy(backend_value) + + @staticmethod + def _cost_map_backend_model(deployment: Deployment) -> str: + model_info_base_model: Final = deployment.model_info.base_model + if isinstance(model_info_base_model, str) and model_info_base_model: + return model_info_base_model + params_base_model: Final = deployment.litellm_params.get("base_model") + if isinstance(params_base_model, str) and params_base_model: + return params_base_model + return deployment.litellm_params.model + @staticmethod def _deployment_model_cost_payload(deployment: Deployment) -> dict: # mutable-ok: cost-map entry """The ``model_info`` a deployment contributes to ``litellm.model_cost``. @@ -9878,6 +9919,11 @@ class Router: backend_model=deployment.litellm_params.model, custom_llm_provider=deployment.litellm_params.custom_llm_provider, ) + Router._inherit_builtin_service_tier_pricing( + model_info=model_info, + backend_model=Router._cost_map_backend_model(deployment), + custom_llm_provider=deployment.litellm_params.custom_llm_provider, + ) Router._inherit_builtin_tiered_output_rate( model_info=model_info, backend_model=deployment.litellm_params.model, diff --git a/litellm/utils.py b/litellm/utils.py index 64ecfcac98c..50e82b570fb 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -45,7 +45,7 @@ from httpx import Proxy from httpx._utils import get_environment_proxies from openai.lib import _parsing, _pydantic from openai.types.chat.completion_create_params import ResponseFormat -from pydantic import BaseModel +from pydantic import BaseModel, ConfigDict, TypeAdapter, ValidationError, with_config import litellm import litellm.litellm_core_utils @@ -3240,6 +3240,129 @@ def _get_builtin_model_info_for_registration(model: str) -> ModelInfo | None: _runtime_registered_model_cost: Final[dict[str, dict[str, object]]] = {} # mutable-ok: replayed on reload +_runtime_registered_fields: Final[dict[str, frozenset[str]]] = {} # mutable-ok: fields each registration set +_runtime_registered_fields_owner: list[int] = [0] # mutable-ok: id of the model_cost map the fields describe + + +def _registered_fields_for_current_map() -> dict[str, frozenset[str]]: + if _runtime_registered_fields_owner[0] != id(litellm.model_cost): + _runtime_registered_fields.clear() + _runtime_registered_fields_owner[0] = id(litellm.model_cost) + return _runtime_registered_fields + + +_RATE_TABLE: Final = TypeAdapter(Mapping[str, object]) +_RATE_TIERS: Final = TypeAdapter(tuple[Mapping[str, object], ...]) +_TOKEN_COST_FIELDS: Final = ("input_cost_per_token", "output_cost_per_token") +_DIRECTION_RATE_FIELDS: Final = MappingProxyType( + { + "input_cost_per_token": ("input_cost_per_token",), + "output_cost_per_token": ("output_cost_per_token", "output_cost_per_reasoning_token"), + } +) + + +def _is_overridden_rate(name: str, overridden_fields: tuple[str, ...]) -> bool: + is_variant: Final = name.startswith(tuple(f"{rate_field}_" for rate_field in overridden_fields)) + return name in overridden_fields or (is_variant and "_cache_" not in name) + + +def _without_overridden_rates(rates: Mapping[str, object], overridden_fields: tuple[str, ...]) -> Mapping[str, object]: + return MappingProxyType( + {name: rate for name, rate in rates.items() if not _is_overridden_rate(name, overridden_fields)} + ) + + +def _rate_table_with_flat_prices( + name: str, table: object, overridden_fields: tuple[str, ...], flat_prices: Mapping[str, object] +) -> object: + try: + if name == "tiered_pricing": + return [ + {**_without_overridden_rates(tier, overridden_fields), **flat_prices} + for tier in _RATE_TIERS.validate_python(table) + ] + if name == "off_peak_pricing": + return dict(_without_overridden_rates(_RATE_TABLE.validate_python(table), overridden_fields)) + except ValidationError: + return table + return table + + +def _without_overridden_price_variants( + entry: Mapping[str, object], value: Mapping[str, object] +) -> Mapping[str, object]: + flat_prices: Final = MappingProxyType( + {cost_field: value[cost_field] for cost_field in _TOKEN_COST_FIELDS if value.get(cost_field) is not None} + ) + overridden_fields: Final = tuple( + itertools.chain.from_iterable(_DIRECTION_RATE_FIELDS[cost_field] for cost_field in flat_prices) + ) + if not overridden_fields: + return entry + return MappingProxyType( + { + name: _rate_table_with_flat_prices(name, field_value, overridden_fields, flat_prices) + for name, field_value in entry.items() + if not _is_overridden_rate(name, overridden_fields) + } + ) + + +@with_config(ConfigDict(extra="allow")) +class _PricingModelInfo(ModelInfo): + pass + + +_PRICING_MODEL_INFO: Final = TypeAdapter(_PricingModelInfo) + + +def model_info_with_pricing_overrides(model_info: ModelInfo, registration: Mapping[str, object]) -> ModelInfo: + from litellm.types.utils import is_server_derived_pricing_key + + overrides: Final = { + name: value for name, value in registration.items() if value is not None and is_server_derived_pricing_key(name) + } + return _PRICING_MODEL_INFO.validate_python( + _update_dictionary(dict(_without_overridden_price_variants(model_info, overrides)), overrides) + ) + + +def runtime_model_cost_registrations( + model: str, custom_llm_provider: str +) -> tuple[tuple[str, Mapping[str, object]], ...]: + names: Final = _get_potential_model_names(model, custom_llm_provider) + candidates: Final = ( + model, + names["combined_model_name"], + f"{custom_llm_provider}/{names['split_model']}", + names["split_model"], + names["stripped_model_name"], + ) + registered: Final = ( + (key, litellm.model_cost.get(key), _registered_fields_for_current_map().get(key, frozenset())) + for key in dict.fromkeys(candidates) + ) + return tuple( + (key, MappingProxyType({name: value for name, value in entry.items() if name in fields})) + for key, entry, fields in registered + if isinstance(entry, Mapping) and fields + ) + + +@dataclass(frozen=True, slots=True) +class ModelInfoLookupMiss: + tripped: bool + + +def lookup_model_info_for_registration(model: str, custom_llm_provider: str | None) -> ModelInfo | ModelInfoLookupMiss: + try: + info: Final = get_model_info(model=model, custom_llm_provider=custom_llm_provider) + except ModelNotMappedError: + return ModelInfoLookupMiss(tripped=False) + except Exception: + return ModelInfoLookupMiss(tripped=True) + return ModelInfoLookupMiss(tripped=False) if is_generalized_model_info(info) else info class _LiveDeploymentReplay: @@ -3281,6 +3404,7 @@ def reapply_runtime_model_cost_registrations() -> None: have no such owner are recorded and replayed, and a registration describing a single request opts out of even that. """ + _runtime_registered_fields.clear() if _LiveDeploymentReplay.callback is not None: _LiveDeploymentReplay.callback() if _runtime_registered_model_cost: @@ -3410,6 +3534,10 @@ def register_model( ## override / add new keys to the existing model cost dictionary updated_dictionary = _update_dictionary(existing_model, value) litellm.model_cost.setdefault(model_cost_key, {}).update(updated_dictionary) + registered_fields = _registered_fields_for_current_map() + registered_fields[str(model_cost_key)] = registered_fields.get(str(model_cost_key), frozenset()) | frozenset( + name for name, field_value in value.items() if field_value is not None + ) # Invalidate case-insensitive lookup map since model_cost was modified _invalidate_model_cost_lowercase_map() From f5049dba86016ca173da4eb5bb132c773a2e1be8 Mon Sep 17 00:00:00 2001 From: joshua-berri Date: Tue, 20 Oct 2026 16:39:37 -0700 Subject: [PATCH 34/66] fix(bedrock): resolve profile pricing before applying custom rates (#47419) Backport of #47419 to stable/1.104.x. Cherry-picked from 312479739914ad46d37696308ec26bcdb652b7a8 (main). Ported onto the line's register_model and router startup path without #41523's aliased-entry rewrite: registered fields come from the side table added in the previous commit. Tests adapted to the line: private names (_replay_model_cost_registrations, _response_cost_calculator), the custom-pricing test helpers from main's test_cost_calculator.py, CONVERSE_ANSWER inlined, and the alias-propagation and bedrock gpt-6.1-sol/ARN cases removed since those depend on #41523 and #46128, which are not on this line. --- litellm/cost_calculator.py | 99 ++- .../litellm_core_utils/llm_cost_calc/utils.py | 25 +- litellm/main.py | 1 + litellm/router.py | 85 +-- litellm/utils.py | 5 +- .../llm_cost_calc/test_llm_cost_calc_utils.py | 82 +++ .../chat/test_bedrock_converse_handler.py | 43 ++ tests/unit/test_cost_calculator.py | 620 ++++++++++++++++++ tests/unit/test_main.py | 95 +++ .../unit/test_router_model_cost_isolation.py | 181 ++++- tests/unit/test_utils.py | 48 +- 11 files changed, 1220 insertions(+), 64 deletions(-) diff --git a/litellm/cost_calculator.py b/litellm/cost_calculator.py index 845c62d91d6..55aeaaa10ff 100644 --- a/litellm/cost_calculator.py +++ b/litellm/cost_calculator.py @@ -8,7 +8,7 @@ from types import MappingProxyType from typing import TYPE_CHECKING, Any, Final, Literal, cast from httpx import Response -from pydantic import BaseModel +from pydantic import BaseModel, TypeAdapter from typing_extensions import ReadOnly, TypedDict, assert_never import litellm @@ -125,6 +125,7 @@ from litellm.types.utils import ( TranscriptionUsageTokensObject, Usage, VectorStoreSearchResponse, + is_server_derived_pricing_key, ) from litellm.utils import ( CallTypes, @@ -137,6 +138,8 @@ from litellm.utils import ( TextCompletionResponse, TranscriptionResponse, _cached_get_model_info_helper, + model_info_with_pricing_overrides, + runtime_model_cost_registrations, token_counter, ) @@ -402,6 +405,7 @@ def cost_per_token( ### REQUEST MODEL ### request_model: str | None = None, # original request model for router detection custom_model_info: OCRPricing | None = None, + bedrock_model_info: ModelInfo | None = None, ) -> tuple[float, float]: """ Calculates the cost per token for a given model, prompt tokens, and completion tokens. @@ -688,6 +692,15 @@ def cost_per_token( elif custom_llm_provider == "anthropic": return anthropic_cost_per_token(model=model, usage=usage_block, service_tier=service_tier) elif custom_llm_provider == "bedrock": + resolved_bedrock_info: Final = bedrock_model_info or _bedrock_pricing_info(model, None, "bedrock", False) + if resolved_bedrock_info is not None: + return generic_cost_per_token( + model=model, + usage=usage_block, + custom_llm_provider="bedrock", + service_tier=service_tier, + model_info=resolved_bedrock_info, + ) return bedrock_cost_per_token(model=model, usage=usage_block, service_tier=service_tier) elif custom_llm_provider == "openai": return openai_cost_per_token( @@ -801,6 +814,55 @@ def _cost_map_entry_prices_anything(entry: Mapping[str, object]) -> bool: ) +_LOGGED_LITELLM_PARAMS: Final = TypeAdapter(Mapping[str, object]) + + +def _bedrock_registration_has_prices(entry: Mapping[str, object]) -> bool: + return _cost_map_entry_prices_anything(entry) or any( + value is not None and field.startswith("cache_") and is_server_derived_pricing_key(field) + for field, value in entry.items() + ) + + +def _bedrock_pricing_info( + model: str | None, + invoked_model_id: str | None, + custom_llm_provider: str | None, + explicit_pricing: bool, +) -> ModelInfo | None: + if explicit_pricing or custom_llm_provider != "bedrock" or not model: + return None + registration: Final = next( + ( + (key, entry) + for key, entry in runtime_model_cost_registrations(model, "bedrock") + if _bedrock_registration_has_prices(entry) + ), + None, + ) + profile: Final = _cost_map_model_info(invoked_model_id, "bedrock") if invoked_model_id else None + if profile is None or not _declares_rates(profile): + return _cost_map_model_info(registration[0], None) if registration is not None else None + if registration is None or registration[0] == profile["key"]: + return profile + return model_info_with_pricing_overrides(profile, registration[1]) + + +def _declares_rates(model_info: ModelInfo | None) -> bool: + entry: Final = _raw_cost_map_entry(model_info["key"]) if model_info is not None else None + return entry is not None and _cost_map_entry_prices_anything(entry) + + +def _invoked_model_id_for_cost( + optional_params: object, + logging_obj: LitellmLoggingObject | None, +) -> str | None: + recorded: Final[object] = getattr(logging_obj, "model_call_details", None) + return _get_hidden_str_for_cost_calc(optional_params, "model_id") or _get_hidden_str_for_cost_calc( + recorded, "model_id" + ) + + def _select_model_name_for_cost_calc( model: str | None, completion_response: object | None, @@ -809,6 +871,7 @@ def _select_model_name_for_cost_calc( custom_llm_provider: str | None = None, router_model_id: str | None = None, region_name: str | None = None, + invoked_model_id: str | None = None, ) -> str | None: """ 1. If custom pricing is true, return received model name @@ -829,6 +892,13 @@ def _select_model_name_for_cost_calc( hidden_params: Final[dict | None] = getattr(completion_response, "_hidden_params", None) provider_response_model: Final = _get_hidden_str_for_cost_calc(hidden_params, "provider_response_model") explicit_pricing: Final = custom_pricing is True or base_model is not None + configured_model: Final = model or ( + completion_response_model if isinstance(completion_response_model, str) else None + ) + bedrock_model_info: Final = _bedrock_pricing_info( + configured_model, invoked_model_id, custom_llm_provider, explicit_pricing + ) + bedrock_pricing_model: Final = bedrock_model_info["key"] if bedrock_model_info is not None else None priced_from_response: Final = provider_response_model is not None or completion_response_model is not None priced_region: Final = ( _get_hidden_str_for_cost_calc(hidden_params, "region_name") or region_name @@ -846,8 +916,8 @@ def _select_model_name_for_cost_calc( else: return_model = model - elif base_model is not None or provider_response_model is not None: - return_model = base_model if base_model is not None else provider_response_model + elif base_model is not None or bedrock_pricing_model is not None or provider_response_model is not None: + return_model = base_model if base_model is not None else bedrock_pricing_model or provider_response_model elif completion_response_model is None and hidden_params is not None: if hidden_params.get("model", None) is not None and len(hidden_params["model"]) > 0: @@ -1426,6 +1496,10 @@ def completion_cost( service_tier = _normalize_service_tier(service_tier) explicit_pricing: Final = custom_pricing is True or base_model is not None + invoked_model_id: Final = _invoked_model_id_for_cost( + _LOGGED_LITELLM_PARAMS.validate_python(optional_params) if optional_params is not None else None, + litellm_logging_obj, + ) selected_model: Final = _select_model_name_for_cost_calc( model=model, completion_response=completion_response, @@ -1434,6 +1508,14 @@ def completion_cost( base_model=base_model, router_model_id=router_model_id, region_name=region_name, + invoked_model_id=invoked_model_id, + ) + + bedrock_model_info: Final = _bedrock_pricing_info( + model or _get_response_model(completion_response), + invoked_model_id, + _get_provider_for_cost_calc(model, custom_llm_provider), + explicit_pricing, ) potential_model_names: Final = [ @@ -1808,6 +1890,7 @@ def completion_cost( vertex_location=vertex_location, response=completion_response, custom_model_info=_ocr_model_info(litellm_logging_obj, custom_pricing, router_model_id), + bedrock_model_info=bedrock_model_info, ) # Get additional costs from provider (e.g., routing fees, infrastructure costs) @@ -1896,6 +1979,7 @@ def completion_cost( data_residency=data_residency, vertex_location=vertex_location, custom_cost_per_token=custom_cost_per_token, + model_info=bedrock_model_info, ) _reasoning_cost = _token_type_breakdown.reasoning_cost _cache_read_cost = _token_type_breakdown.cache_read_cost @@ -2137,7 +2221,16 @@ def pricing_entry_for_cost_calc( custom_llm_provider=custom_llm_provider, router_model_id=router_model_id, region_name=region_name, + invoked_model_id=_invoked_model_id_for_cost(None, litellm_logging_obj), ) + bedrock_model_info: Final = _bedrock_pricing_info( + model or _get_response_model(completion_response), + _invoked_model_id_for_cost(None, litellm_logging_obj), + _get_provider_for_cost_calc(model, custom_llm_provider), + custom_pricing is True or base_model is not None, + ) + if bedrock_model_info is not None: + return bedrock_model_info["key"], bedrock_model_info candidates: Final = (selected_model, _get_response_model(completion_response), model) resolved: Final = next( (info for info in (_cost_map_model_info(name, custom_llm_provider) for name in candidates if name) if info), diff --git a/litellm/litellm_core_utils/llm_cost_calc/utils.py b/litellm/litellm_core_utils/llm_cost_calc/utils.py index d25b70e2450..8ca79874564 100644 --- a/litellm/litellm_core_utils/llm_cost_calc/utils.py +++ b/litellm/litellm_core_utils/llm_cost_calc/utils.py @@ -275,7 +275,7 @@ def _parse_token_threshold(threshold: str) -> float: def _parse_above_token_threshold(key: str) -> float: - return _parse_token_threshold(key.split("_above_")[1].split("_tokens")[0]) + return _parse_token_threshold(key.rsplit("_above_", 1)[1].split("_tokens")[0]) def _prompt_exceeds_threshold(prompt_tokens: int, threshold: float, inclusive: bool) -> bool: @@ -669,10 +669,12 @@ def _get_token_base_cost( # so that the threshold detection loop only processes standard keys. The # service_tier-specific above-threshold key is resolved later via _get_service_tier_cost_key. tier_key_suffix: Final = _get_service_tier_cost_key("", service_tier) + threshold_prefixes: Final = tuple(f"{prefix}_above_" for prefix in _BATCH_RATE_PREFIXES) threshold_keys: Final = [ k for k in model_info - if k.startswith("input_cost_per_token_above_") + if k.startswith(threshold_prefixes) + and "_tokens" in k and ( not k.endswith(_NON_STANDARD_THRESHOLD_SUFFIXES) or (tier_key_suffix != "" and k.endswith(tier_key_suffix)) ) @@ -680,12 +682,12 @@ def _get_token_base_cost( # Only sort the threshold keys (typically 1-2 keys instead of 66+) threshold: float | None = None - for key in sorted(threshold_keys, key=_parse_above_token_threshold, reverse=True): + for key in sorted(threshold_keys, key=_parse_above_token_threshold): value = model_info.get(key) if value is not None: try: # Handle both formats: _above_128k_tokens and _above_128_tokens - threshold_str = key.split("_above_")[1].split("_tokens")[0] + threshold_str = key.rsplit("_above_", 1)[1].split("_tokens")[0] threshold = _parse_above_token_threshold(key) if _prompt_exceeds_threshold(usage.prompt_tokens, threshold, threshold_is_inclusive): # Prefer a service_tier-specific above-threshold key when available, @@ -698,7 +700,7 @@ def _get_token_base_cost( service_tier, ) if service_tier - else key + else f"input_cost_per_token_above_{threshold_str}_tokens" ) prompt_base_cost = cast( float, @@ -754,8 +756,6 @@ def _get_token_base_cost( ) cache_read_cost = _get_cost_per_unit(model_info, cache_read_tiered_key, cache_read_cost) - - break except (IndexError, ValueError): continue except Exception: @@ -1636,20 +1636,23 @@ def get_billed_token_rates( vertex_location: str | None = None, current_time: datetime | None = None, custom_cost_per_token: CostPerToken | None = None, + model_info: ModelInfo | None = None, ) -> BilledTokenRates | None: """Rates the cost calculator bills ``usage`` at, resolved exactly as the totals and the token-type breakdown resolve them. None when the model's pricing cannot be resolved.""" if custom_cost_per_token is not None: return _custom_pricing_rates(custom_cost_per_token) try: - model_info: Final = apply_provider_cache_read_default( - get_model_info(model=model, custom_llm_provider=custom_llm_provider), + resolved_model_info: Final = apply_provider_cache_read_default( + model_info + if model_info is not None + else get_model_info(model=model, custom_llm_provider=custom_llm_provider), custom_llm_provider, ) except Exception: # noqa: BLE001 # get_model_info raises a bare Exception for an unmapped model: no rates return None return _cost_map_billed_rates( - model_info=model_info, + model_info=resolved_model_info, usage=usage, custom_llm_provider=custom_llm_provider, service_tier=service_tier, @@ -1668,6 +1671,7 @@ def get_token_type_cost_breakdown( vertex_location: str | None = None, current_time: datetime | None = None, custom_cost_per_token: CostPerToken | None = None, + model_info: ModelInfo | None = None, ) -> TokenTypeCostBreakdown: """ Provider-agnostic cost of reasoning and cache tokens, derived from the usage @@ -1692,6 +1696,7 @@ def get_token_type_cost_breakdown( vertex_location=vertex_location, current_time=current_time, custom_cost_per_token=custom_cost_per_token, + model_info=model_info, ) if rates is None: return TokenTypeCostBreakdown(0.0, 0.0, 0.0) diff --git a/litellm/main.py b/litellm/main.py index c3cf278633b..4aa4159d771 100644 --- a/litellm/main.py +++ b/litellm/main.py @@ -5722,6 +5722,7 @@ def completion( optional_params=processed_non_default_params, # [IMPORTANT] - using processed_non_default_params ensures consistent params logged to langfuse for finetuning / eval datasets. litellm_params=litellm_params, custom_llm_provider=custom_llm_provider, + model_id=optional_params.get("model_id"), ) if mock_response or mock_tool_calls or mock_timeout: kwargs.pop("mock_timeout", None) # remove for any fallbacks triggered diff --git a/litellm/router.py b/litellm/router.py index aba87177a38..5e84f54c65d 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -318,12 +318,14 @@ from litellm.types.utils import ( StandardLoggingRoutingDecision, Usage, all_litellm_params, + is_server_derived_pricing_key, shared_backend_model_info, ) from litellm.types.utils import ModelInfo as ModelMapInfo from litellm.utils import ( CustomStreamWrapper, EmbeddingResponse, + ModelInfoLookupMiss, ModelResponse, Rules, function_setup, @@ -332,6 +334,8 @@ from litellm.utils import ( get_secret, get_utc_datetime, is_region_allowed, + lookup_model_info_for_registration, + model_info_with_pricing_overrides, provider_rejectable_params, set_live_deployment_replay, ) @@ -471,6 +475,8 @@ def _stream_chunks_have_generated_content(chunks: Sequence[ModelResponseStream]) _NO_SESSION_KWARGS: Final[Mapping[str, Mapping[str, object]]] = MappingProxyType({}) _SESSION_ADAPTER: Final = TypeAdapter(Mapping[str, object]) _SILENT_MODEL_ADAPTER: Final = TypeAdapter(str | list[str]) +_MODEL_INFO_ADAPTER: Final = TypeAdapter(Mapping[str, object]) +_LITELLM_PARAMS_ADAPTER: Final = TypeAdapter(Mapping[str, object]) def _as_retry_skipped_deployment_ids(value: object) -> tuple[str, ...]: @@ -8824,39 +8830,7 @@ class Router: litellm_params=litellm_params, model_info=_model_info, ) - for field in CustomPricingLiteLLMParams.model_fields: - if deployment.litellm_params.get(field) is not None: - _model_info[field] = deployment.litellm_params[field] - - Router._inherit_builtin_base_rates_for_off_peak( - model_info=_model_info, - backend_model=deployment.litellm_params.model, - custom_llm_provider=deployment.litellm_params.custom_llm_provider, - ) - if _model_info.get("input_cost_per_token") is not None: - Router._inherit_builtin_cache_pricing( - model_info=_model_info, - backend_model=deployment.litellm_params.model, - custom_llm_provider=deployment.litellm_params.custom_llm_provider, - ) - Router._inherit_builtin_service_tier_pricing( - model_info=_model_info, - backend_model=Router._cost_map_backend_model(deployment), - custom_llm_provider=deployment.litellm_params.custom_llm_provider, - ) - Router._inherit_builtin_tiered_output_rate( - model_info=_model_info, - backend_model=deployment.litellm_params.model, - custom_llm_provider=deployment.litellm_params.custom_llm_provider, - ) - - ## REGISTER MODEL INFO IN LITELLM MODEL COST MAP - Router._register_deployment_in_model_cost( - model_id=deployment.model_info.id, - model_info=_model_info, - model=deployment.litellm_params.model, - custom_llm_provider=deployment.litellm_params.custom_llm_provider, - ) + Router._register_deployment_pricing(deployment) ## Check if LLM Deployment is allowed for this deployment if self.deployment_is_active_for_environment(deployment=deployment) is not True: @@ -9892,10 +9866,24 @@ class Router: params_base_model: Final = deployment.litellm_params.get("base_model") if isinstance(params_base_model, str) and params_base_model: return params_base_model + params: Final = _LITELLM_PARAMS_ADAPTER.validate_python(deployment.litellm_params.model_dump(exclude_none=True)) + invoked_model: Final = params.get("model_id") + if ( + isinstance(invoked_model, str) + and invoked_model + and ( + deployment.litellm_params.custom_llm_provider == "bedrock" + or deployment.litellm_params.model.startswith("bedrock/") + ) + ): + profile_model: Final = invoked_model if invoked_model.startswith("bedrock/") else f"bedrock/{invoked_model}" + profile_info: Final = lookup_model_info_for_registration(model=profile_model, custom_llm_provider="bedrock") + if not isinstance(profile_info, ModelInfoLookupMiss): + return profile_model return deployment.litellm_params.model @staticmethod - def _deployment_model_cost_payload(deployment: Deployment) -> dict: # mutable-ok: cost-map entry + def _deployment_model_cost_payload(deployment: Deployment) -> dict[str, object]: # mutable-ok: cost-map entry """The ``model_info`` a deployment contributes to ``litellm.model_cost``. Custom pricing lives on ``litellm_params`` rather than ``model_info``, and @@ -9903,30 +9891,49 @@ class Router: both are folded back in here. That keeps this reproducible from a deployment alone, which is what lets a refresh rebuild the same entries. """ - model_info: Final[dict] = deployment.model_info.model_dump(exclude_none=True) # mutable-ok: built in place + model_info: Final = dict( + _MODEL_INFO_ADAPTER.validate_python(deployment.model_info.model_dump(exclude_none=True)) + ) for field in CustomPricingLiteLLMParams.model_fields: field_value = deployment.litellm_params.get(field) if field_value is not None: model_info[field] = field_value + backend_model: Final = Router._cost_map_backend_model(deployment) + params: Final = _LITELLM_PARAMS_ADAPTER.validate_python(deployment.litellm_params.model_dump(exclude_none=True)) + if ( + params.get("model_id") + and backend_model != deployment.litellm_params.model + and ( + deployment.litellm_params.custom_llm_provider == "bedrock" + or deployment.litellm_params.model.startswith("bedrock/") + ) + ): + profile_info: Final = lookup_model_info_for_registration(model=backend_model, custom_llm_provider="bedrock") + if not isinstance(profile_info, ModelInfoLookupMiss): + explicit_info: Final = _MODEL_INFO_ADAPTER.validate_python(model_info) + priced_info: Final = model_info_with_pricing_overrides(profile_info, explicit_info) + model_info.update( + {key: value for key, value in priced_info.items() if is_server_derived_pricing_key(key)} + ) Router._inherit_builtin_base_rates_for_off_peak( model_info=model_info, - backend_model=deployment.litellm_params.model, + backend_model=backend_model, custom_llm_provider=deployment.litellm_params.custom_llm_provider, ) if model_info.get("input_cost_per_token") is not None: Router._inherit_builtin_cache_pricing( model_info=model_info, - backend_model=deployment.litellm_params.model, + backend_model=backend_model, custom_llm_provider=deployment.litellm_params.custom_llm_provider, ) Router._inherit_builtin_service_tier_pricing( model_info=model_info, - backend_model=Router._cost_map_backend_model(deployment), + backend_model=backend_model, custom_llm_provider=deployment.litellm_params.custom_llm_provider, ) Router._inherit_builtin_tiered_output_rate( model_info=model_info, - backend_model=deployment.litellm_params.model, + backend_model=backend_model, custom_llm_provider=deployment.litellm_params.custom_llm_provider, ) return model_info diff --git a/litellm/utils.py b/litellm/utils.py index 50e82b570fb..5f32820df5e 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -3468,7 +3468,10 @@ def register_model( if persist_across_reloads: _registrations: Final[Mapping[str, Mapping[str, object]]] = loaded_model_cost for _registered_key, _registered_value in _registrations.items(): - _runtime_registered_model_cost[_registered_key] = dict(_registered_value) # mutable-ok: caller-owned + _runtime_registered_model_cost[_registered_key] = _update_dictionary( + dict(_runtime_registered_model_cost.get(_registered_key, {})), + dict(_RATE_TABLE.validate_python(_registered_value)), + ) _skip_get_model_info_providers: Final = PROVIDERS_THAT_AUTHENTICATE_ON_PROVIDER_INFO diff --git a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index e599a4b6353..3fc70ffec5c 100644 --- a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -3936,3 +3936,85 @@ def test_get_batch_cost_rates_claude_haiku_5_5_prompt_length_tiers( ) assert (rates.input, rates.output, rates.cache_read, rates.cache_creation) == expected + + +@pytest.mark.parametrize( + "field", ("output_cost_per_token", "cache_read_input_token_cost", "cache_creation_input_token_cost") +) +def test_flat_input_price_keeps_other_token_thresholds(field: str) -> None: + from typing import Final, cast + from litellm.litellm_core_utils.llm_cost_calc.utils import _get_token_base_cost + + info: Final = cast( + ModelInfo, + { + "input_cost_per_token": 0.001, + "output_cost_per_token": 0.002, + "cache_read_input_token_cost": 0.003, + "cache_creation_input_token_cost": 0.004, + f"{field}_above_300k_tokens": 0.005, + }, + ) + rates: Final = _get_token_base_cost( + model_info=info, + usage=Usage(prompt_tokens=300_001, completion_tokens=3, total_tokens=300_004), + ) + assert rates[0] == 0.001 + assert rates[1] == (0.005 if field == "output_cost_per_token" else 0.002) + assert rates[2] == (0.005 if field == "cache_creation_input_token_cost" else 0.004) + assert rates[4] == (0.005 if field == "cache_read_input_token_cost" else 0.003) + + +@pytest.mark.parametrize("prompt_tokens", (200_000, 200_001, 512_000, 512_001)) +@pytest.mark.parametrize("higher_rate", (0.0, 0.009)) +def test_mixed_token_thresholds_preserve_each_crossed_rate(prompt_tokens: int, higher_rate: float) -> None: + from typing import Final, cast + from litellm.litellm_core_utils.llm_cost_calc.utils import _get_token_base_cost + + info: Final = cast( + ModelInfo, + { + "input_cost_per_token": 0.001, + "output_cost_per_token": 0.002, + "cache_read_input_token_cost": 0.003, + "cache_creation_input_token_cost": 0.004, + "input_cost_per_token_above_200k_tokens": 0.005, + "output_cost_per_token_above_200k_tokens": 0.006, + "cache_creation_input_token_cost_above_200k_tokens": 0.007, + "cache_read_input_token_cost_above_512k_tokens": higher_rate, + "output_cost_per_token_above_512k_tokens": higher_rate, + }, + ) + rates: Final = _get_token_base_cost( + model_info=info, + usage=Usage(prompt_tokens=prompt_tokens, completion_tokens=3, total_tokens=prompt_tokens + 3), + ) + assert rates[0] == (0.005 if prompt_tokens > 200_000 else 0.001) + assert rates[1] == (higher_rate if prompt_tokens > 512_000 else 0.006 if prompt_tokens > 200_000 else 0.002) + assert rates[2] == (0.007 if prompt_tokens > 200_000 else 0.004) + assert rates[4] == (higher_rate if prompt_tokens > 512_000 else 0.003) + + +@pytest.mark.parametrize("rate", (0.0, 0.001)) +def test_token_breakdown_uses_supplied_pricing_without_catalog_lookup(rate: float) -> None: + model_info: Final[ModelInfo] = { + "input_cost_per_token": 0.01, + "output_cost_per_token": 0.02, + "cache_read_input_token_cost": rate, + "cache_creation_input_token_cost": rate, + } + usage: Final = Usage( + prompt_tokens=20, completion_tokens=3, total_tokens=23, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=5), cache_creation_input_tokens=5, + ) + prompt_cost, output_cost = generic_cost_per_token( + model="supplied-pricing-test", usage=usage, custom_llm_provider="bedrock", model_info=model_info, + ) + breakdown: Final = get_token_type_cost_breakdown( + model="supplied-pricing-test", usage=usage, custom_llm_provider="bedrock", model_info=model_info, + ) + assert breakdown.cache_read_cost == pytest.approx(5 * rate) + assert breakdown.cache_creation_cost == pytest.approx(5 * rate) + assert breakdown.rates is not None + assert prompt_cost == pytest.approx(10 * breakdown.rates.input_cost_per_token + breakdown.cache_read_cost + breakdown.cache_creation_cost) + assert output_cost == pytest.approx(3 * breakdown.rates.output_cost_per_token) diff --git a/tests/unit/llms/bedrock/chat/test_bedrock_converse_handler.py b/tests/unit/llms/bedrock/chat/test_bedrock_converse_handler.py index 08bcac33a35..93320b62083 100644 --- a/tests/unit/llms/bedrock/chat/test_bedrock_converse_handler.py +++ b/tests/unit/llms/bedrock/chat/test_bedrock_converse_handler.py @@ -16,6 +16,8 @@ import pytest from botocore.credentials import Credentials from botocore.exceptions import ClientError +import litellm + from litellm.llms.bedrock.chat.converse_handler import BedrockConverseLLM from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler from litellm.rust_bridge import configuration @@ -273,3 +275,44 @@ def test_session_tags_sign_the_request_and_stay_out_of_the_body(monkeypatch): sent = client.post.call_args.kwargs assert "Credential=ASIACONVERSETAGGED/" in sent["headers"]["Authorization"] assert "aws_session_tags" not in sent["data"] + + +@pytest.mark.parametrize("stream", (False, True)) +def test_converse_profile_override_records_cost_without_changing_response_model( + monkeypatch: pytest.MonkeyPatch, stream: bool +) -> None: + monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") + monkeypatch.setenv("LITELLM_RUST", "0") + configuration.rust(False) + model: Final = "openai.gpt-5.6-sol" + profile: Final = f"us.{model}" + prices: Final = litellm.get_model_info(profile, custom_llm_provider="bedrock") + + def respond(request: httpx.Request) -> httpx.Response: + assert request.url.path == f"/model/{profile}/converse" + return httpx.Response(200, json=CONVERSE_RESPONSE) + + with httpx.Client(transport=httpx.MockTransport(respond)) as transport: + response: Final = litellm.completion( + model=f"bedrock/converse/{model}", + model_id=profile, + messages=[{"role": "user", "content": "hi"}], + api_key="test-bearer", + aws_region_name="us-east-1", + client=HTTPHandler(client=transport), + stream=stream, + fake_stream=stream, + max_tokens=16, + ) + result: Final = litellm.stream_chunk_builder(list(response)) if stream else response + + assert result is not None + assert result.model == model + assert result.choices[0].message.content == "hi" + cost: Final = ( + response.logging_obj._response_cost_calculator(result) if stream else result._hidden_params.get("response_cost") + ) + assert cost == pytest.approx( + CONVERSE_RESPONSE["usage"]["inputTokens"] * prices["input_cost_per_token"] + + CONVERSE_RESPONSE["usage"]["outputTokens"] * prices["output_cost_per_token"] + ) diff --git a/tests/unit/test_cost_calculator.py b/tests/unit/test_cost_calculator.py index 99dea6366f9..1e9b7f596bf 100644 --- a/tests/unit/test_cost_calculator.py +++ b/tests/unit/test_cost_calculator.py @@ -1,10 +1,13 @@ import datetime +import json import time from pathlib import Path from types import MappingProxyType, SimpleNamespace from typing import Final, cast +import httpx import pytest +import respx from pydantic import BaseModel import litellm @@ -5319,3 +5322,620 @@ def test_completion_cost_is_zero_when_explicit_rates_are_zero(monkeypatch: pytes ) assert cost == 0.0 + + +@pytest.fixture +def isolated_pricing_registry(local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch) -> None: + monkeypatch.setattr(litellm, "disable_aiohttp_transport", True) + monkeypatch.setattr(litellm, "open_ai_chat_completion_models", set(litellm.open_ai_chat_completion_models)) + monkeypatch.setattr(litellm, "models_by_provider", dict(litellm.models_by_provider)) + + +_CUSTOM_PRICING_MODEL: Final = "migration-custom-pricing-chat" + + +_CUSTOM_PRICING_RATES: Final = MappingProxyType( + {"input_cost_per_token": 0.0000008, "output_cost_per_token": 0.0000032} +) + + +_CUSTOM_PRICING_EXPECTED_COST: Final = 7 * 0.0000008 + 4 * 0.0000032 + + +def _custom_pricing_chunk(choices: list[dict[str, object]], usage: dict[str, int] | None = None) -> str: + chunk: Final = { + "id": "chatcmpl-custom-pricing", + "object": "chat.completion.chunk", + "created": 1, + "model": _CUSTOM_PRICING_MODEL, + "choices": choices, + **({"usage": usage} if usage is not None else {}), + } + return f"data: {json.dumps(chunk)}\n\n" + + +def _custom_pricing_upstream(request: httpx.Request) -> httpx.Response: + if json.loads(request.content).get("stream") is True: + body: Final = "".join( + ( + _custom_pricing_chunk( + [{"index": 0, "delta": {"role": "assistant", "content": "I am ready to help."}, "finish_reason": None}] + ), + _custom_pricing_chunk([{"index": 0, "delta": {}, "finish_reason": "stop"}]), + _custom_pricing_chunk([], {"prompt_tokens": 7, "completion_tokens": 4, "total_tokens": 11}), + "data: [DONE]\n\n", + ) + ) + return httpx.Response(200, text=body, headers={"content-type": "text/event-stream"}) + return httpx.Response( + 200, + json={ + "id": "chatcmpl-custom-pricing", + "object": "chat.completion", + "created": 1, + "model": _CUSTOM_PRICING_MODEL, + "choices": [ + {"index": 0, "message": {"role": "assistant", "content": "I am ready to help."}, "finish_reason": "stop"} + ], + "usage": {"prompt_tokens": 7, "completion_tokens": 4, "total_tokens": 11}, + }, + ) + + +@pytest.mark.parametrize("rate", (0.0, 0.001)) +@pytest.mark.parametrize("cache_field", ("cache_read_input_token_cost", "cache_creation_input_token_cost")) +@pytest.mark.usefixtures("isolated_pricing_registry") +@respx.mock +def test_router_cache_only_pricing_preserves_uncached_token_charges(rate: float, cache_field: str) -> None: + litellm.register_model( + {_CUSTOM_PRICING_MODEL: {**_CUSTOM_PRICING_RATES, "litellm_provider": "openai", "mode": "chat"}}, + persist_across_reloads=False, + ) + respx.post("https://api.openai.com/v1/chat/completions").mock(side_effect=_custom_pricing_upstream) + router: Final = litellm.Router( + model_list=[ + { + "model_name": "cache-priced-deployment", + "litellm_params": { + "model": f"openai/{_CUSTOM_PRICING_MODEL}", + "api_key": "sk-test", + cache_field: rate, + }, + "model_info": {"id": "cache-only-deployment"}, + } + ] + ) + + response: Final = router.completion( + model="cache-priced-deployment", messages=[{"role": "user", "content": "How are you?"}] + ) + + assert response._hidden_params["response_cost"] == pytest.approx(_CUSTOM_PRICING_EXPECTED_COST) + + +@pytest.mark.parametrize("profile_prefix", ("us", "global")) +@pytest.mark.parametrize( + "model_name", + ("gpt-5.6-sol", "gpt-5.6-luna", "gpt-5.6-terra", "gpt-6-sol", "gpt-6-luna", "gpt-6-astra"), +) +@pytest.mark.parametrize("arn", (False,)) +def test_bedrock_converse_cost_uses_invoked_profile( + _local_model_cost_map: None, model_name: str, profile_prefix: str, arn: bool +) -> None: + model: Final = f"openai.{model_name}" + profile: Final = f"{profile_prefix}.{model}" + invoked: Final = f"arn:aws:bedrock:us-east-1:123456789012:inference-profile/{profile}" if arn else profile + response: Final = ModelResponse(model=model, usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15)) + prices: Final = litellm.get_model_info(profile, custom_llm_provider="bedrock") + + cost: Final = completion_cost( + completion_response=response, + model=f"bedrock/converse/{model}", + custom_llm_provider="bedrock", + optional_params={"model_id": invoked}, + ) + + assert cost == pytest.approx(10 * prices["input_cost_per_token"] + 5 * prices["output_cost_per_token"]) + assert response.model == model + + +@pytest.mark.parametrize("custom_pricing", (False, True)) +def test_bedrock_converse_profile_preserves_explicit_base_and_custom_pricing( + _local_model_cost_map: None, custom_pricing: bool +) -> None: + model: Final = "openai.gpt-6-sol" + response: Final = ModelResponse(model=model, usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15)) + prices: Final = litellm.get_model_info(model, custom_llm_provider="bedrock") + + cost: Final = completion_cost( + completion_response=response, + model=model, + custom_llm_provider="bedrock", + optional_params={"model_id": f"us.{model}"}, + custom_pricing=custom_pricing, + base_model=None if custom_pricing else model, + ) + + assert cost == pytest.approx(10 * prices["input_cost_per_token"] + 5 * prices["output_cost_per_token"]) + + +@pytest.mark.parametrize("stream", (False, True)) +def test_bedrock_converse_cost_retains_profile_after_dispatch_consumes_optional_params( + _local_model_cost_map: None, stream: bool +) -> None: + from litellm.cost_calculator import pricing_entry_for_cost_calc + + model: Final = "openai.gpt-5.6-sol" + profile: Final = f"us.{model}" + logging_obj: Final = Logging( + model=model, + messages=[{"role": "user", "content": "hi"}], + stream=stream, + call_type="completion", + start_time=datetime.datetime(2026, 1, 1), + litellm_call_id="bedrock-profile-cost", + function_id="bedrock-profile-cost", + ) + logging_obj.update_environment_variables( + litellm_params={}, optional_params={"model_id": profile}, custom_llm_provider="bedrock" + ) + logging_obj.optional_params.pop("model_id") + response: Final = ModelResponse(model=model, usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15)) + prices: Final = litellm.get_model_info(profile, custom_llm_provider="bedrock") + + assert logging_obj._response_cost_calculator(response) == pytest.approx( + 10 * prices["input_cost_per_token"] + 5 * prices["output_cost_per_token"] + ) + entry: Final = pricing_entry_for_cost_calc(model, response, "bedrock", False, None, None, None, logging_obj) + assert entry is not None + assert entry[0] == prices["key"] + + +@pytest.mark.parametrize( + "invoked_model_id", + (None, "", 123, "unmapped-profile", "arn:aws:bedrock:us-east-1:123456789012:application-inference-profile/opaque"), +) +def test_bedrock_converse_cost_keeps_configured_rates_when_target_has_no_prices( + _local_model_cost_map: None, invoked_model_id: object +) -> None: + model: Final = "openai.gpt-6-sol" + response: Final = ModelResponse(model=model, usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15)) + expected: Final = completion_cost(completion_response=response, model=model, custom_llm_provider="bedrock") + + assert ( + completion_cost( + completion_response=response, + model=model, + custom_llm_provider="bedrock", + optional_params={"model_id": invoked_model_id}, + ) + == expected + ) + + +def test_non_bedrock_cost_ignores_bedrock_model_id(_local_model_cost_map: None) -> None: + response: Final = ModelResponse( + model="gpt-6-sol", usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15) + ) + expected: Final = completion_cost(completion_response=response, custom_llm_provider="openai") + + assert ( + completion_cost( + completion_response=response, + custom_llm_provider="openai", + optional_params={"model_id": "us.openai.gpt-6-sol"}, + ) + == expected + ) + + +@pytest.mark.parametrize("rate", (0.0, 0.001)) +@pytest.mark.parametrize("persist_across_reloads", (True, False)) +@pytest.mark.parametrize("routed_response", (True, False)) +@pytest.mark.parametrize("metadata_prefix", ("bedrock/", "bedrock/converse/")) +def test_bedrock_converse_profile_preserves_registered_price_override( + _local_model_cost_map: None, + monkeypatch: pytest.MonkeyPatch, + rate: float, + persist_across_reloads: bool, + routed_response: bool, + metadata_prefix: str, +) -> None: + import litellm.utils as model_utils + from litellm.cost_calculator import pricing_entry_for_cost_calc + + monkeypatch.setattr(model_utils, "_runtime_registered_model_cost", {}) + catalog: Final = dict(litellm.model_cost) + model: Final = "openai.gpt-5.6-sol" + litellm.register_model( + {f"{metadata_prefix}{model}": {"supports_function_calling": True}}, + persist_across_reloads=persist_across_reloads, + ) + litellm.register_model( + { + model: { + "input_cost_per_token": rate, + "output_cost_per_token": rate, + "litellm_provider": "bedrock_converse", + "mode": "chat", + } + }, + persist_across_reloads=persist_across_reloads, + ) + litellm.register_model( + {model: {"supports_function_calling": True, "input_cost_per_token": None}}, + persist_across_reloads=persist_across_reloads, + ) + response: Final = ModelResponse( + model=f"bedrock/converse/{model}" if routed_response else model, + usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15), + ) + + logging_obj: Final = Logging( + model=model, + messages=[], + stream=False, + call_type="completion", + start_time=datetime.datetime(2026, 1, 1), + litellm_call_id="registered-pricing", + function_id="registered-pricing", + ) + assert completion_cost( + completion_response=response, + model=f"bedrock/converse/{model}", + custom_llm_provider="bedrock", + optional_params={"model_id": f"us.{model}"}, + litellm_logging_obj=logging_obj, + ) == pytest.approx(15 * rate) + + assert logging_obj.billed_token_rates is not None + assert logging_obj.billed_token_rates.input_cost_per_token == rate + assert logging_obj.billed_token_rates.output_cost_per_token == rate + entry: Final = pricing_entry_for_cost_calc(model, response, "bedrock", False, None, None, None, None) + assert entry is not None + assert entry[0] == model + assert entry[1]["input_cost_per_token"] == rate + assert entry[1]["output_cost_per_token"] == rate + + updated_rate: Final = rate + 0.002 + litellm.register_model( + {model: {"input_cost_per_token": str(updated_rate)}}, persist_across_reloads=persist_across_reloads + ) + assert completion_cost( + completion_response=response, + model=f"bedrock/converse/{model}", + custom_llm_provider="bedrock", + optional_params={"model_id": f"us.{model}"}, + ) == pytest.approx(10 * updated_rate + 5 * rate) + + monkeypatch.setattr(litellm, "model_cost", catalog) + model_utils._invalidate_model_cost_lowercase_map() + model_utils.reapply_runtime_model_cost_registrations() + profile_prices: Final = litellm.get_model_info(f"us.{model}", custom_llm_provider="bedrock") + expected_after_reload: Final = ( + 10 * updated_rate + 5 * rate + if persist_across_reloads + else 10 * profile_prices["input_cost_per_token"] + 5 * profile_prices["output_cost_per_token"] + ) + assert completion_cost( + completion_response=response, + model=f"bedrock/converse/{model}", + custom_llm_provider="bedrock", + optional_params={"model_id": f"us.{model}"}, + ) == pytest.approx(expected_after_reload) + + +def test_bedrock_converse_profile_ignores_registered_capabilities_without_prices( + _local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch +) -> None: + import litellm.utils as model_utils + + monkeypatch.setattr(model_utils, "_runtime_registered_model_cost", {}) + model: Final = "openai.gpt-6-sol" + litellm.register_model({model: {"supports_function_calling": True}}) + response: Final = ModelResponse(model=model, usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15)) + prices: Final = litellm.get_model_info(f"us.{model}", custom_llm_provider="bedrock") + + assert completion_cost( + completion_response=response, + model=model, + custom_llm_provider="bedrock", + optional_params={"model_id": f"us.{model}"}, + ) == pytest.approx(10 * prices["input_cost_per_token"] + 5 * prices["output_cost_per_token"]) + + +@pytest.mark.parametrize("rate", (0.0, 0.001)) +@pytest.mark.parametrize("cache_field", ("cache_read_input_token_cost", "cache_creation_input_token_cost")) +@pytest.mark.parametrize("has_base_rates", (False, True)) +@pytest.mark.parametrize("persist_across_reloads", (False, True)) +@pytest.mark.parametrize("profile_prefix", ("us", "global")) +@pytest.mark.parametrize("provider", (None, "bedrock")) +def test_bedrock_converse_profile_preserves_cache_only_registered_prices( + _local_model_cost_map: None, + monkeypatch: pytest.MonkeyPatch, + rate: float, + cache_field: str, + has_base_rates: bool, + persist_across_reloads: bool, + profile_prefix: str, + provider: str | None, +) -> None: + import litellm.utils as model_utils + from litellm.cost_calculator import pricing_entry_for_cost_calc + + monkeypatch.setattr(model_utils, "_runtime_registered_model_cost", {}) + model: Final = "openai.cache-overlay-test" + profile: Final = f"{profile_prefix}.{model}" + catalog: Final = { + **litellm.model_cost, + model: { + "litellm_provider": "bedrock", + "mode": "chat", + **({"input_cost_per_token": 0.01, "output_cost_per_token": 0.02} if has_base_rates else {}), + }, + profile: { + "litellm_provider": "bedrock", + "mode": "chat", + "input_cost_per_token": 0.02, + "output_cost_per_token": 0.04, + "cache_read_input_token_cost": 0.005, + "cache_creation_input_token_cost": 0.025, + }, + } + profile_before: Final = dict(catalog[profile]) + monkeypatch.setattr(litellm, "model_cost", dict(catalog)) + model_utils._invalidate_model_cost_lowercase_map() + litellm.register_model({model: {cache_field: rate}}, persist_across_reloads=persist_across_reloads) + response: Final = ModelResponse( + model=model, + usage=Usage( + prompt_tokens=15, + completion_tokens=3, + total_tokens=18, + prompt_tokens_details=PromptTokensDetailsWrapper( + cached_tokens=5 if cache_field == "cache_read_input_token_cost" else 0 + ), + cache_creation_input_tokens=5 if cache_field == "cache_creation_input_token_cost" else 0, + ), + ) + logging_obj: Final = Logging( + model=model, + messages=[], + stream=False, + call_type="completion", + start_time=datetime.datetime(2026, 1, 1), + litellm_call_id="cache-overlay", + function_id="cache-overlay", + ) + logging_obj.model_call_details["model_id"] = profile + expected: Final = 10 * 0.02 + 3 * 0.04 + 5 * rate + assert completion_cost( + completion_response=response, + model=f"bedrock/converse/{model}", + custom_llm_provider=provider, + optional_params={"model_id": profile}, + litellm_logging_obj=logging_obj, + ) == pytest.approx(expected) + breakdown_key: Final = "cache_read_cost" if cache_field == "cache_read_input_token_cost" else "cache_creation_cost" + assert logging_obj.cost_breakdown is not None + assert logging_obj.cost_breakdown.get(breakdown_key, 0.0) == pytest.approx(5 * rate) + assert logging_obj.billed_token_rates is not None + assert ( + logging_obj.billed_token_rates.cache_read_input_token_cost + if cache_field == "cache_read_input_token_cost" + else logging_obj.billed_token_rates.cache_creation_input_token_cost + ) == rate + entry: Final = pricing_entry_for_cost_calc( + f"bedrock/converse/{model}", response, provider, False, None, None, None, logging_obj + ) + assert entry is not None + assert entry[1]["input_cost_per_token"] == 0.02 + assert entry[1]["output_cost_per_token"] == 0.04 + assert entry[1][cache_field] == rate + assert litellm.model_cost[profile] == profile_before + + monkeypatch.setattr(litellm, "model_cost", dict(catalog)) + model_utils._invalidate_model_cost_lowercase_map() + model_utils.reapply_runtime_model_cost_registrations() + expected_after_reload: Final = ( + 10 * 0.02 + 3 * 0.04 + 5 * (rate if persist_across_reloads else catalog[profile][cache_field]) + ) + assert completion_cost( + completion_response=response, + model=f"bedrock/converse/{model}", + custom_llm_provider=provider, + optional_params={"model_id": profile}, + litellm_logging_obj=logging_obj, + ) == pytest.approx(expected_after_reload) + + +@pytest.mark.parametrize("profile", ("us.openai.missing-profile-test", "us.openai.unpriced-profile-test")) +def test_bedrock_cache_registration_with_unpriced_profile_keeps_registered_rates( + _local_model_cost_map: None, monkeypatch: pytest.MonkeyPatch, profile: str +) -> None: + import litellm.utils as model_utils + + model: Final = "openai.registered-cache-test" + monkeypatch.setattr( + litellm, + "model_cost", + { + **litellm.model_cost, + model: { + "litellm_provider": "bedrock", + "mode": "chat", + "input_cost_per_token": 0.01, + "output_cost_per_token": 0.02, + }, + "us.openai.unpriced-profile-test": {"litellm_provider": "bedrock", "mode": "chat"}, + }, + ) + model_utils._invalidate_model_cost_lowercase_map() + litellm.register_model({model: {"cache_read_input_token_cost": 0.001}}, persist_across_reloads=False) + response: Final = ModelResponse( + model=model, + usage=Usage( + prompt_tokens=15, + completion_tokens=3, + total_tokens=18, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=5), + ), + ) + assert completion_cost( + completion_response=response, + model=f"bedrock/converse/{model}", + custom_llm_provider="bedrock", + optional_params={"model_id": profile}, + ) == pytest.approx(10 * 0.01 + 3 * 0.02 + 5 * 0.001) + + +@pytest.mark.parametrize("direction", ("input", "output")) +@pytest.mark.parametrize("rate", (0.0, 0.004)) +@pytest.mark.parametrize("prompt_tokens", (100, 300_001)) +def test_bedrock_partial_registration_overrides_only_its_profile_direction( + _local_model_cost_map: None, + monkeypatch: pytest.MonkeyPatch, + direction: str, + rate: float, + prompt_tokens: int, +) -> None: + from litellm.cost_calculator import pricing_entry_for_cost_calc + + model: Final = "openai.partial-pricing-test" + profile: Final = f"us.{model}" + profile_entry: Final = { + "litellm_provider": "bedrock", + "mode": "chat", + "input_cost_per_token": 0.01, + "output_cost_per_token": 0.02, + "input_cost_per_token_above_300k_tokens": 0.03, + "output_cost_per_token_above_300k_tokens": 0.06, + "cache_read_input_token_cost": 0.001, + } + monkeypatch.setattr(litellm, "model_cost", {**litellm.model_cost, profile: dict(profile_entry)}) + litellm.register_model({model: {f"{direction}_cost_per_token": rate}}, persist_across_reloads=False) + response: Final = ModelResponse( + model=model, + usage=Usage( + prompt_tokens=prompt_tokens, + completion_tokens=3, + total_tokens=prompt_tokens + 3, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=5), + ), + ) + logging_obj: Final = Logging( + model=model, + messages=[], + stream=False, + call_type="completion", + start_time=datetime.datetime(2026, 1, 1), + litellm_call_id="partial-pricing", + function_id="partial-pricing", + ) + logging_obj.model_call_details["model_id"] = profile + input_rate: Final = rate if direction == "input" else (0.03 if prompt_tokens > 300_000 else 0.01) + output_rate: Final = rate if direction == "output" else (0.06 if prompt_tokens > 300_000 else 0.02) + assert completion_cost( + completion_response=response, + model=model, + custom_llm_provider="bedrock", + litellm_logging_obj=logging_obj, + ) == pytest.approx((prompt_tokens - 5) * input_rate + 3 * output_rate + 5 * 0.001) + assert logging_obj.billed_token_rates is not None + assert logging_obj.billed_token_rates.input_cost_per_token == input_rate + assert logging_obj.billed_token_rates.output_cost_per_token == output_rate + assert logging_obj.cost_breakdown is not None + assert logging_obj.cost_breakdown["cache_read_cost"] == pytest.approx(5 * 0.001) + entry: Final = pricing_entry_for_cost_calc(model, response, "bedrock", False, None, None, None, logging_obj) + assert entry is not None + assert entry[1][f"{direction}_cost_per_token"] == rate + assert litellm.model_cost[profile] == profile_entry + + +@pytest.mark.parametrize("prompt_tokens", (299_999, 300_000, 300_001)) +@pytest.mark.parametrize("cache_field", ("cache_read_input_token_cost", "cache_creation_input_token_cost")) +@pytest.mark.parametrize("tier_override", (None, 0.0, 0.003)) +def test_bedrock_registered_cache_prices_preserve_dynamic_threshold_rates( + _local_model_cost_map: None, + monkeypatch: pytest.MonkeyPatch, + prompt_tokens: int, + cache_field: str, + tier_override: float | None, +) -> None: + import litellm.utils as model_utils + from litellm.cost_calculator import pricing_entry_for_cost_calc + + model: Final = "openai.threshold-overlay-test" + profile: Final = f"us.{model}" + tier_field: Final = f"{cache_field}_above_300k_tokens" + monkeypatch.setattr( + litellm, + "model_cost", + { + **litellm.model_cost, + profile: { + "litellm_provider": "bedrock", + "mode": "chat", + "input_cost_per_token": 0.01, + "output_cost_per_token": 0.02, + "input_cost_per_token_above_300k_tokens": 0.03, + "output_cost_per_token_above_300k_tokens": 0.06, + tier_field: 0.007, + }, + }, + ) + model_utils._invalidate_model_cost_lowercase_map() + litellm.register_model( + { + model: { + cache_field: 0.001, + **({tier_field: tier_override} if tier_override is not None else {}), + } + }, + persist_across_reloads=False, + ) + usage: Final = Usage( + prompt_tokens=prompt_tokens, + completion_tokens=3, + total_tokens=prompt_tokens + 3, + prompt_tokens_details=PromptTokensDetailsWrapper( + cached_tokens=5 if cache_field == "cache_read_input_token_cost" else 0 + ), + cache_creation_input_tokens=5 if cache_field == "cache_creation_input_token_cost" else 0, + ) + response: Final = ModelResponse(model=model, usage=usage) + logging_obj: Final = Logging( + model=model, + messages=[], + stream=False, + call_type="completion", + start_time=datetime.datetime(2026, 1, 1), + litellm_call_id="threshold-overlay", + function_id="threshold-overlay", + ) + logging_obj.model_call_details["model_id"] = profile + expected_input_rate: Final = 0.03 if prompt_tokens > 300_000 else 0.01 + expected_output_rate: Final = 0.06 if prompt_tokens > 300_000 else 0.02 + expected_cache_rate: Final = ( + (tier_override if tier_override is not None else 0.007) if prompt_tokens > 300_000 else 0.001 + ) + total: Final = completion_cost( + completion_response=response, + model=f"bedrock/converse/{model}", + custom_llm_provider="bedrock", + optional_params={"model_id": profile}, + litellm_logging_obj=logging_obj, + ) + assert total == pytest.approx( + (prompt_tokens - 5) * expected_input_rate + 3 * expected_output_rate + 5 * expected_cache_rate + ) + breakdown_key: Final = "cache_read_cost" if cache_field == "cache_read_input_token_cost" else "cache_creation_cost" + assert logging_obj.cost_breakdown is not None + assert logging_obj.cost_breakdown.get(breakdown_key, 0.0) == pytest.approx(5 * expected_cache_rate) + assert logging_obj.billed_token_rates is not None + assert logging_obj.billed_token_rates.input_cost_per_token == expected_input_rate + assert logging_obj.billed_token_rates.output_cost_per_token == expected_output_rate + entry: Final = pricing_entry_for_cost_calc(model, response, "bedrock", False, None, None, None, logging_obj) + assert entry is not None + assert entry[1]["input_cost_per_token_above_300k_tokens"] == 0.03 + assert entry[1][tier_field] == (tier_override if tier_override is not None else 0.007) diff --git a/tests/unit/test_main.py b/tests/unit/test_main.py index 2c99228013e..0302c3d648b 100644 --- a/tests/unit/test_main.py +++ b/tests/unit/test_main.py @@ -4269,3 +4269,98 @@ def test_completion_rejects_untranslatable_tool_choice_with_a_400(tool_choice): ) assert exc_info.value.status_code == 400 assert f"tool_choice={tool_choice}" in str(exc_info.value) + + +@pytest.mark.parametrize("stream", (False, True)) +@pytest.mark.parametrize("asynchronous", (False, True)) +@pytest.mark.parametrize("profile,custom_price", ((None, False), ("us.openai.gpt-6-sol", False), (None, True))) +@pytest.mark.asyncio +async def test_converse_fallback_prices_the_current_attempt( + monkeypatch: pytest.MonkeyPatch, stream: bool, asynchronous: bool, profile: str | None, custom_price: bool +) -> None: + from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler + from litellm.rust_bridge import configuration + + CONVERSE_ANSWER: Final = json.dumps( + { + "output": {"message": {"role": "assistant", "content": [{"text": "hi"}]}}, + "stopReason": "end_turn", + "usage": {"inputTokens": 1, "outputTokens": 1, "totalTokens": 2}, + "metrics": {"latencyMs": 1}, + } + ).encode() + + monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") + monkeypatch.setenv("LITELLM_RUST", "0") + configuration.rust(False) + monkeypatch.setattr(litellm, "model_cost", dict(litellm.model_cost)) + failed_profile: Final = "us.amazon.nova-micro-v1:0" + model: Final = "openai.gpt-6-sol" + logging_obj: Final = LiteLLMLogging( + model="amazon.nova-micro-v1:0", + messages=[{"role": "user", "content": "hi"}], + stream=stream, + call_type="acompletion" if asynchronous else "completion", + start_time=datetime(2026, 1, 1), + litellm_call_id="bedrock-fallback-pricing", + function_id="bedrock-fallback-pricing", + ) + + def respond(request: httpx.Request) -> httpx.Response: + if failed_profile in request.url.path: + return httpx.Response(400, json={"message": "Input is too long for requested model."}) + assert request.url.path == f"/model/{profile or model}/converse" + return httpx.Response(200, content=CONVERSE_ANSWER) + + client: Final = ( + AsyncHTTPHandler(transport=httpx.MockTransport(respond)) + if asynchronous + else HTTPHandler(client=httpx.Client(transport=httpx.MockTransport(respond))) + ) + kwargs: Final = { + "messages": [{"role": "user", "content": "hi"}], + "api_key": "test-bearer", + "aws_region_name": "us-east-1", + "client": client, + "litellm_logging_obj": logging_obj, + "num_retries": 0, + "stream": stream, + "fake_stream": stream, + } + if asynchronous: + with pytest.raises(litellm.BadRequestError): + await litellm.acompletion(model="bedrock/converse/amazon.nova-micro-v1:0", model_id=failed_profile, **kwargs) + else: + with pytest.raises(litellm.BadRequestError): + litellm.completion(model="bedrock/converse/amazon.nova-micro-v1:0", model_id=failed_profile, **kwargs) + + overrides: Final = { + **({"model_id": profile} if profile is not None else {}), + **({"input_cost_per_token": 0.001, "output_cost_per_token": 0.002} if custom_price else {}), + } + response: Final = ( + await litellm.acompletion(model=f"bedrock/converse/{model}", **kwargs, **overrides) + if asynchronous + else litellm.completion(model=f"bedrock/converse/{model}", **kwargs, **overrides) + ) + result: Final = ( + litellm.stream_chunk_builder( + [chunk async for chunk in response] if asynchronous else list(response), logging_obj=response.logging_obj + ) + if stream + else response + ) + assert result is not None + prices: Final = litellm.get_model_info(profile or model, custom_llm_provider="bedrock") + expected: Final = ( + 0.001 + 0.002 + if custom_price + else prices["input_cost_per_token"] + prices["output_cost_per_token"] + ) + active_logging: Final = response.logging_obj if stream else logging_obj + assert active_logging._response_cost_calculator(result) == pytest.approx(expected) + if asynchronous: + await client.close() + else: + client.close() + configuration.reset_rust_configuration() diff --git a/tests/unit/test_router_model_cost_isolation.py b/tests/unit/test_router_model_cost_isolation.py index 6a6e4c5b4d4..2a7d9813925 100644 --- a/tests/unit/test_router_model_cost_isolation.py +++ b/tests/unit/test_router_model_cost_isolation.py @@ -761,6 +761,178 @@ def test_should_not_downgrade_chatgpt_shared_key_mode_with_alias_override(): _restore_model_cost_entries(model_keys) +@pytest.mark.parametrize("service_tier", ("default", "priority", "flex")) +@pytest.mark.parametrize( + "field", + ("input_cost_per_token", "output_cost_per_token", "cache_read_input_token_cost", "input_cost_per_token_priority"), +) +@pytest.mark.parametrize("rate", (0.0, 0.004)) +@pytest.mark.parametrize("explicit_base", (False, True)) +@pytest.mark.parametrize("provider", (None, "bedrock")) +@pytest.mark.parametrize("registration_path", ("direct", "startup", "reload")) +def test_bedrock_deployment_inherits_invoked_profile_around_custom_prices( + monkeypatch: pytest.MonkeyPatch, + field: str, + rate: float, + explicit_base: bool, + provider: str | None, + registration_path: str, + service_tier: str, +) -> None: + from litellm.cost_calculator import completion_cost + from litellm.types.utils import ModelResponse, Usage, PromptTokensDetailsWrapper + + model: Final = "openai.gpt-5.6-sol" + profile: Final = f"us.{model}" + base_model: Final = f"global.{model}" + profile_prices: Final = { + "litellm_provider": "bedrock", + "mode": "chat", + "input_cost_per_token": 0.01, + "output_cost_per_token": 0.02, + "cache_read_input_token_cost": 0.001, + "input_cost_per_token_priority": 0.05, + "output_cost_per_token_priority": 0.06, + "input_cost_per_token_flex": 0.007, + "output_cost_per_token_flex": 0.008, + } + base_prices: Final = {**profile_prices, "input_cost_per_token": 0.03, "output_cost_per_token": 0.04} + monkeypatch.setattr( + litellm, "model_cost", {**litellm.model_cost, profile: dict(profile_prices), base_model: dict(base_prices)} + ) + deployment: Final = Deployment( + model_name="profile-priced", + litellm_params=LiteLLM_Params( + model=f"converse/{model}" if provider else f"bedrock/converse/{model}", + model_id=profile, + custom_llm_provider=provider, + ), + model_info=ModelInfo( + **{ + "id": "profile-priced-deployment", + field: rate, + **({"base_model": f"bedrock/{base_model}"} if explicit_base else {}), + } + ), + ) + if registration_path == "direct": + Router._register_deployment_pricing(deployment) + else: + router: Final = Router(model_list=[deployment.to_json(exclude_none=True)]) + if registration_path == "reload": + router._replay_model_cost_registrations() + response: Final = ModelResponse( + model=model, + usage=Usage( + prompt_tokens=100, + completion_tokens=3, + total_tokens=103, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=5), + ), + ) + catalog: Final = base_prices if explicit_base else profile_prices + input_field: Final = "input_cost_per_token" + (f"_{service_tier}" if service_tier != "default" else "") + output_field: Final = "output_cost_per_token" + (f"_{service_tier}" if service_tier != "default" else "") + input_rate: Final = rate if field == input_field else catalog[input_field] + output_rate: Final = rate if field == output_field else catalog[output_field] + cache_rate: Final = rate if field == "cache_read_input_token_cost" else 0.001 + assert completion_cost( + model=model, + completion_response=response, + custom_llm_provider="bedrock", + custom_pricing=True, + router_model_id="profile-priced-deployment", + service_tier=service_tier, + ) == pytest.approx(95 * input_rate + 3 * output_rate + 5 * cache_rate) + assert litellm.model_cost[profile] == profile_prices + + +@pytest.mark.parametrize("catalog_entry", (None, {"litellm_provider": 1, "mode": "chat"})) +@pytest.mark.parametrize("known_model", (False, True)) +@pytest.mark.parametrize("explicit_base", (False, True)) +@pytest.mark.parametrize("service_tier", ("default", "priority", "flex")) +@pytest.mark.parametrize("override", (None, "cache_read_input_token_cost", "input_cost_per_token_priority")) +@pytest.mark.parametrize("reload", (False, True)) +def test_bedrock_deployment_keeps_custom_prices_when_profile_lookup_fails( + monkeypatch: pytest.MonkeyPatch, + catalog_entry: dict[str, object] | None, + known_model: bool, + explicit_base: bool, + service_tier: str, + override: str | None, + reload: bool, +) -> None: + from litellm.cost_calculator import completion_cost + from litellm.types.utils import ModelResponse, Usage, PromptTokensDetailsWrapper + + model: Final = "anthropic.unmapped-profile-pricing-test" + profile: Final = ( + "us.anthropic.invalid-profile-pricing-test" + if catalog_entry is not None + else "arn:aws:bedrock:us-east-1:123456789012:application-inference-profile/opaque-test" + ) + configured_prices: Final = { + "litellm_provider": "bedrock", + "mode": "chat", + "input_cost_per_token": 0.03, + "output_cost_per_token": 0.04, + "cache_read_input_token_cost": 0.001, + "input_cost_per_token_priority": 0.05, + "output_cost_per_token_priority": 0.06, + "input_cost_per_token_flex": 0.007, + "output_cost_per_token_flex": 0.008, + } + monkeypatch.setattr( + litellm, + "model_cost", + { + **litellm.model_cost, + **({model: dict(configured_prices)} if known_model else {}), + **({profile: catalog_entry} if catalog_entry is not None else {}), + }, + ) + deployment: Final = Deployment( + model_name="custom-priced", + litellm_params=LiteLLM_Params(model=f"bedrock/converse/{model}", model_id=profile), + model_info=ModelInfo( + id="unmapped-profile-deployment", + input_cost_per_token=0.01, + output_cost_per_token=0.02, + **({override: 0.0} if override else {}), + **({"base_model": f"bedrock/{profile}"} if explicit_base else {}), + ), + ) + router: Final = Router(model_list=[deployment.to_json(exclude_none=True)]) + if reload: + router._replay_model_cost_registrations() + inherit_configured: Final = known_model and not explicit_base + tier_rates: Final = inherit_configured and service_tier != "default" + input_rate: Final = configured_prices[f"input_cost_per_token_{service_tier}"] if tier_rates else 0.01 + output_rate: Final = configured_prices[f"output_cost_per_token_{service_tier}"] if tier_rates else 0.02 + effective_input: Final = 0.0 if override == "input_cost_per_token_priority" and service_tier == "priority" else input_rate + cache_rate: Final = 0.0 if override == "cache_read_input_token_cost" else (0.001 if inherit_configured else effective_input) + assert completion_cost( + model=model, + completion_response=ModelResponse( + model=model, + usage=Usage( + prompt_tokens=100, + completion_tokens=3, + total_tokens=103, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=80), + ), + ), + custom_llm_provider="bedrock", + custom_pricing=True, + router_model_id="unmapped-profile-deployment", + service_tier=service_tier, + ) == pytest.approx(20 * effective_input + 80 * cache_rate + 3 * output_rate) + if known_model: + assert { + key: value for key, value in litellm.model_cost[model].items() if key in configured_prices + } == configured_prices + + def test_partial_custom_pricing_inherits_builtin_cache_pricing(): """A deployment that overrides only input/output cost on a cache-supporting model must still bill cache_read and cache_creation tokens. Before the @@ -1771,14 +1943,7 @@ def test_a_reload_rebuilds_exactly_what_a_fresh_boot_registered() -> None: ) rebuilt = litellm.model_cost["priced-id"] - assert at_boot.items() <= rebuilt.items(), ( - f"the rebuild changed or dropped a field the boot registration wrote: " - f"{ {k: (v, rebuilt.get(k)) for k, v in at_boot.items() if rebuilt.get(k) != v} }" - ) - assert {field: rebuilt[field] for field in set(rebuilt) - set(at_boot)} == { - "db_model": False, - "member_auto_router": False, - } + assert at_boot == rebuilt assert "member_auto_router" not in litellm.model_cost["gpt-4o"] assert router.model_list finally: diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py index c40121e284f..b9cf6abd360 100644 --- a/tests/unit/test_utils.py +++ b/tests/unit/test_utils.py @@ -4205,7 +4205,11 @@ async def test_builtin_string_callback_registers_when_subclass_already_active( assert any(type(cb) is S3Logger for cb in litellm._async_success_callback) -def test_reapply_runtime_registrations_replays_register_model_overrides(monkeypatch): +@pytest.mark.parametrize("rate", (0.0, 0.000123)) +@pytest.mark.parametrize("updated_rate", (None, 0.0, 0.000456)) +def test_reapply_runtime_registrations_replays_register_model_overrides( + monkeypatch: pytest.MonkeyPatch, rate: float, updated_rate: float | None +) -> None: """ register_model is the documented way to override pricing for a model. A price-data reload swaps litellm.model_cost for a freshly fetched catalog, @@ -4236,11 +4240,17 @@ def test_reapply_runtime_registrations_replays_register_model_overrides(monkeypa "openai/gpt-4o": { "litellm_provider": "openai", "mode": "chat", - "input_cost_per_token": 0.000123, + "input_cost_per_token": rate, } } ) + litellm.register_model({"openai/gpt-4o": {"supports_function_calling": True, "input_cost_per_token": None}}) + litellm.register_model( + {"openai/gpt-4o": {"input_cost_per_token": str(updated_rate) if updated_rate is not None else None}} + ) + litellm.register_model({"openai/gpt-4o": {"supports_function_calling": False}}) + litellm.model_cost = { "openai/gpt-4o": { "litellm_provider": "openai", @@ -4252,7 +4262,9 @@ def test_reapply_runtime_registrations_replays_register_model_overrides(monkeypa _invalidate_model_cost_lowercase_map() reapply_runtime_model_cost_registrations() - assert litellm.model_cost["openai/gpt-4o"]["input_cost_per_token"] == 0.000123 + expected_rate: Final = rate if updated_rate is None else updated_rate + assert litellm.model_cost["openai/gpt-4o"]["input_cost_per_token"] == expected_rate + assert litellm.model_cost["openai/gpt-4o"]["supports_function_calling"] is False assert litellm.model_cost["openai/gpt-4o"]["max_input_tokens"] == 4242 finally: litellm.model_cost = saved_model_cost @@ -6362,3 +6374,33 @@ def test_function_setup_never_logs_the_ocr_data_uri_payload() -> None: assert logged == [{"role": "user", "content": f"data:application/pdf;base64 ({len(payload)} chars)"}] assert payload not in str(logged) + + +@pytest.mark.parametrize( + "key", ("openai.test-converse", "bedrock/openai.test-converse", "bedrock/converse/openai.test-converse") +) +def test_runtime_model_cost_registrations_resolve_bedrock_routing(monkeypatch: pytest.MonkeyPatch, key: str) -> None: + from litellm import utils as model_utils + + rates: Final = {"input_cost_per_token": 0.001, "output_cost_per_token": 0.002} + monkeypatch.setattr( + litellm, "model_cost", {**litellm.model_cost, key: {"litellm_provider": "bedrock_converse", "mode": "chat"}} + ) + monkeypatch.setattr(model_utils, "_runtime_registered_fields", {}) + litellm.register_model({key: rates}, persist_across_reloads=False) + + registrations: Final = dict( + model_utils.runtime_model_cost_registrations("bedrock/converse/openai.test-converse", "bedrock") + ) + assert registrations[key] == rates + assert model_utils.runtime_model_cost_registrations("bedrock/converse/openai.other-converse", "bedrock") == () + + +def test_registered_fields_reset_when_model_cost_is_replaced(monkeypatch: pytest.MonkeyPatch) -> None: + monkeypatch.setattr(litellm, "model_cost", {}) + litellm.register_model({"registered-fields-probe": {"input_cost_per_token": 1e-06, "litellm_provider": "openai"}}) + assert "registered-fields-probe" in litellm.utils._registered_fields_for_current_map() + + monkeypatch.setattr(litellm, "model_cost", {}) + + assert litellm.utils._registered_fields_for_current_map() == {} From ec25d80617c2bef7bfe5dfb4c180cbbaecd33172 Mon Sep 17 00:00:00 2001 From: daqiangganjun <93830914+daqiangganjun@users.noreply.github.com> Date: Tue, 20 Oct 2026 16:35:01 -0700 Subject: [PATCH 35/66] fix(router): count provider budget spend on every API surface (#38172) Backport of #38172 to stable/1.104.x. Cherry-picked from 8327cd6d4724b6218f85562ba164f0cb2cb71ef6 (main). Prerequisite for #47625: RouterBudgetLimiting reads the provider from the logging payload, so the batch poller's aretrieve_batch events reach router budgets at all. Test file placed at tests/unit/router_strategy/ on this line. --- litellm/router_strategy/budget_limiter.py | 10 +- .../router_strategy/test_budget_limiter.py | 137 ++++++++++++++++++ 2 files changed, 142 insertions(+), 5 deletions(-) create mode 100644 tests/unit/router_strategy/test_budget_limiter.py diff --git a/litellm/router_strategy/budget_limiter.py b/litellm/router_strategy/budget_limiter.py index 4e84bded9de..64252cbbfb3 100644 --- a/litellm/router_strategy/budget_limiter.py +++ b/litellm/router_strategy/budget_limiter.py @@ -502,12 +502,12 @@ class RouterBudgetLimiting(CustomLogger): response_cost: Final[float] = standard_logging_payload.get("response_cost", 0) model_id: Final[str] = str(standard_logging_payload.get("model_id", "")) - custom_llm_provider: Final[str] = kwargs.get("litellm_params", {}).get("custom_llm_provider", None) - if custom_llm_provider is None: - raise ValueError("custom_llm_provider is required") + custom_llm_provider: Final[str | None] = standard_logging_payload.get("custom_llm_provider") - budget_config: Final = self._get_budget_config_for_provider(custom_llm_provider) - if budget_config: + budget_config: Final = ( + self._get_budget_config_for_provider(custom_llm_provider) if custom_llm_provider is not None else None + ) + if custom_llm_provider is not None and budget_config is not None: # increment spend for provider spend_key: Final = f"provider_spend:{custom_llm_provider}:{budget_config.budget_duration}" start_time_key: Final = f"provider_budget_start_time:{custom_llm_provider}" diff --git a/tests/unit/router_strategy/test_budget_limiter.py b/tests/unit/router_strategy/test_budget_limiter.py new file mode 100644 index 00000000000..62de1586fdd --- /dev/null +++ b/tests/unit/router_strategy/test_budget_limiter.py @@ -0,0 +1,137 @@ +""" +Spend tracking in RouterBudgetLimiting.async_log_success_event. + +Only chat completions puts custom_llm_provider into litellm_params. The responses, +anthropic_messages, embedding and rerank surfaces leave it unset, which used to make +the callback raise before any spend was recorded, so those budgets never moved. +""" + +from typing import Final + +import pytest + +from litellm.caching.caching import DualCache +from litellm.router_strategy.budget_limiter import RouterBudgetLimiting + + +@pytest.fixture +def disable_budget_sync(monkeypatch): + async def noop(*args, **kwargs): + return None + + monkeypatch.setattr( + "litellm.router_strategy.budget_limiter.RouterBudgetLimiting.periodic_sync_in_memory_spend_with_redis", + noop, + ) + + +def _success_kwargs( + *, + provider_in_litellm_params: str | None, + provider_in_payload: str | None, + call_type: str = "aresponses", + response_cost: float = 0.25, + model_id: str = "deployment-1", +) -> dict[str, object]: + provider_params: Final[dict[str, str]] = ( + {} if provider_in_litellm_params is None else {"custom_llm_provider": provider_in_litellm_params} + ) + litellm_params: Final[dict[str, str]] = {"model": "openai/gpt-4o", **provider_params} + + return { + "call_type": call_type, + "litellm_params": litellm_params, + "standard_logging_object": { + "response_cost": response_cost, + "model_id": model_id, + "custom_llm_provider": provider_in_payload, + }, + } + + +async def _log_success(limiter: RouterBudgetLimiting, kwargs: dict[str, object]) -> None: + await limiter.async_log_success_event(kwargs=kwargs, response_obj=None, start_time=None, end_time=None) + + +@pytest.mark.asyncio +@pytest.mark.parametrize("call_type", ["aresponses", "anthropic_messages", "aembedding", "arerank"]) +async def test_provider_spend_tracked_when_litellm_params_omits_provider(disable_budget_sync, call_type): + """Non-chat surfaces carry the provider only on the standard logging payload.""" + limiter = RouterBudgetLimiting( + dual_cache=DualCache(), + provider_budget_config={"openai": {"budget_limit": 10.0, "time_period": "1d"}}, + ) + + await _log_success( + limiter, + _success_kwargs( + provider_in_litellm_params=None, + provider_in_payload="openai", + call_type=call_type, + ), + ) + + assert await limiter.dual_cache.async_get_cache("provider_spend:openai:1d") == 0.25 + + +@pytest.mark.asyncio +async def test_chat_completions_spend_still_tracked(disable_budget_sync): + """Chat completions fills in both sources and must keep accumulating.""" + limiter = RouterBudgetLimiting( + dual_cache=DualCache(), + provider_budget_config={"openai": {"budget_limit": 10.0, "time_period": "1d"}}, + ) + + await _log_success( + limiter, + _success_kwargs( + provider_in_litellm_params="openai", + provider_in_payload="openai", + call_type="acompletion", + ), + ) + + assert await limiter.dual_cache.async_get_cache("provider_spend:openai:1d") == 0.25 + + +@pytest.mark.asyncio +async def test_budget_of_other_provider_is_untouched(disable_budget_sync): + """A provider without its own budget must not bleed into a configured one.""" + limiter = RouterBudgetLimiting( + dual_cache=DualCache(), + provider_budget_config={"openai": {"budget_limit": 10.0, "time_period": "1d"}}, + ) + + await _log_success( + limiter, + _success_kwargs(provider_in_litellm_params=None, provider_in_payload="anthropic"), + ) + + assert await limiter.dual_cache.async_get_cache("provider_spend:openai:1d") in (None, 0.0) + + +@pytest.mark.asyncio +async def test_deployment_budget_tracked_when_provider_is_unresolvable(disable_budget_sync): + """An unresolvable provider must not abort the deployment and tag budgets that follow it.""" + limiter = RouterBudgetLimiting( + dual_cache=DualCache(), + provider_budget_config=None, + model_list=[ + { + "model_name": "some-model", + "litellm_params": { + "model": "openai/gpt-4o", + "max_budget": 10.0, + "budget_duration": "1d", + }, + "model_info": {"id": "deployment-1"}, + } + ], + ) + + await _log_success( + limiter, + _success_kwargs(provider_in_litellm_params=None, provider_in_payload=None), + ) + + assert await limiter.dual_cache.async_get_cache("deployment_spend:deployment-1:1d") == 0.25 From 712dc21192ad7318186018067336f9d674b5d07f Mon Sep 17 00:00:00 2001 From: joshua-berri Date: Tue, 20 Oct 2026 16:49:21 -0700 Subject: [PATCH 36/66] fix(batches): retry confirmed pre-accounting failures (#47625) Backport of #47625 to stable/1.104.x. Cherry-picked from 6564a490f40fba668201fa60d378cb6c165bb03c (main). Ported by hand onto the line's spend and budget code: the charge-once helpers move from model_max_budget_limiter into router_utils.batch_utils as on main; RouterBudgetLimiting keeps the line's websocket skip and uses the line's duration_in_seconds window for the batch marker TTL; the write_started mark covers budget reservations only, since the search free-tier allowance (#47494) is not on this line. Tests adapted to the line's _ProxyDBLogger name; the search-allowance test is dropped for the same reason. --- .../proxy/common_utils/check_batch_cost.py | 36 ++-- .../proxy/hooks/model_max_budget_limiter.py | 15 +- .../proxy/hooks/proxy_track_cost_callback.py | 56 +++++- litellm/router_strategy/budget_limiter.py | 28 ++- litellm/router_utils/batch_utils.py | 13 ++ .../test_router_batch_utils.py | 30 +++- .../hooks/test_proxy_track_cost_callback.py | 73 ++++++++ .../common_utils/test_check_batch_cost.py | 170 ++++++++++++++++-- .../router_strategy/test_budget_limiter.py | 90 ++++++++++ 9 files changed, 462 insertions(+), 49 deletions(-) diff --git a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py index 92c4aa3b89a..a58798835d7 100644 --- a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py +++ b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py @@ -963,20 +963,26 @@ class CheckBatchCost: ) return None - try: - await logging_obj.async_success_handler( - result=response, - batch_cost=batch_result.cost, - batch_usage=batch_result.usage, - batch_models=batch_result.models, - batch_successful_requests=batch_result.successful_requests, - batch_failed_requests=batch_result.failed_requests, - batch_prompt_cost=batch_result.prompt_cost, - batch_completion_cost=batch_result.completion_cost, - ) - except Exception: - await self._release_job_claim(job, original_status, original_file_object) - raise + from litellm.proxy.hooks.proxy_track_cost_callback import track_batch_accounting + + with track_batch_accounting(logging_obj.litellm_call_id) as accounting: + try: + await logging_obj.async_success_handler( + result=response, + batch_cost=batch_result.cost, + batch_usage=batch_result.usage, + batch_models=batch_result.models, + batch_successful_requests=batch_result.successful_requests, + batch_failed_requests=batch_result.failed_requests, + batch_prompt_cost=batch_result.prompt_cost, + batch_completion_cost=batch_result.completion_cost, + ) + finally: + if accounting.retryable_failure: + await self._release_job_claim(job, original_status, original_file_object) + + if accounting.retryable_failure: + return None # Record batch duration (completed_at - created_at) if prom_logger and response.completed_at and response.created_at: @@ -1106,7 +1112,7 @@ class CheckBatchCost: continue verbose_proxy_logger.error( f"CheckBatchCost: failed to track cost for batch {batch_id} " - f"(job {job.id}); leaving it unprocessed so the next poll retries: {tracking_err}" + f"(job {job.id}): {tracking_err}" ) self._record_error(prom_logger, "cost_tracking_error") continue diff --git a/litellm/proxy/hooks/model_max_budget_limiter.py b/litellm/proxy/hooks/model_max_budget_limiter.py index 7ce50bf5ead..20f7c0f3a02 100644 --- a/litellm/proxy/hooks/model_max_budget_limiter.py +++ b/litellm/proxy/hooks/model_max_budget_limiter.py @@ -6,8 +6,6 @@ from dataclasses import dataclass from types import MappingProxyType from typing import Final -from openai.types import Batch - import litellm from litellm._logging import verbose_proxy_logger from litellm.caching.caching import DualCache @@ -16,7 +14,7 @@ from litellm.litellm_core_utils.duration_parser import duration_in_seconds from litellm.llms.bedrock.common_utils import get_bedrock_base_model from litellm.proxy._types import Litellm_EntityType, UserAPIKeyAuth from litellm.router_strategy.budget_limiter import RouterBudgetLimiting -from litellm.router_utils.batch_utils import is_batch_retrieve_call_type +from litellm.router_utils.batch_utils import batch_charged_once_marker_key, batch_id_to_charge_once from litellm.types.llms.openai import AllMessageValues from litellm.types.utils import BudgetConfig, StandardLoggingPayload @@ -121,17 +119,6 @@ def model_budget_start_time_cache_key( return f"{_BUDGET_START_TIME_KEY_PREFIXES[entity_type]}:{entity_id}:{budget_model}:{budget_duration}" -def batch_charged_once_marker_key(spend_key: str, batch_id: str) -> str: - return f"{spend_key}:batch:{batch_id}" - - -def batch_id_to_charge_once(call_type: object, response_obj: object, response_cost: float) -> str | None: - """A finished batch reports its whole cost on every poll, so its id is charged once per counter.""" - if response_cost <= 0 or not is_batch_retrieve_call_type(call_type): - return None - return response_obj.id if isinstance(response_obj, Batch) else None - - def resolve_model_budget(model: str, model_max_budget: Mapping[str, object]) -> ResolvedModelBudget | None: """Find the `model_max_budget` entry that governs `model`, or None.""" for candidate in _budget_model_candidates(model): diff --git a/litellm/proxy/hooks/proxy_track_cost_callback.py b/litellm/proxy/hooks/proxy_track_cost_callback.py index e097debde77..92cda0d61e2 100644 --- a/litellm/proxy/hooks/proxy_track_cost_callback.py +++ b/litellm/proxy/hooks/proxy_track_cost_callback.py @@ -1,9 +1,13 @@ import asyncio import traceback -from collections.abc import Callable, Mapping, Sequence +from collections.abc import Callable, Generator, Mapping, Sequence +from contextlib import contextmanager +from contextvars import ContextVar from datetime import datetime from typing import TYPE_CHECKING, Any, Final, Protocol, cast +from pydantic import TypeAdapter + import litellm from litellm._logging import verbose_proxy_logger from litellm.batches.batch_utils import batch_cost_is_final @@ -61,6 +65,37 @@ from litellm.utils import get_end_user_id_for_cost_tracking if TYPE_CHECKING: from litellm.proxy.utils import ProxyLogging + +class BatchAccountingOutcome: + def __init__(self, call_id: str) -> None: + self.call_id: Final = call_id + self.write_started = False + self.failed = False + + @property + def retryable_failure(self) -> bool: + return self.failed and not self.write_started + + +_BATCH_ACCOUNTING: Final[ContextVar[BatchAccountingOutcome | None]] = ContextVar("batch_accounting", default=None) +_BATCH_CALLBACK_FIELDS: Final = TypeAdapter(dict[str, object]) + + +@contextmanager +def track_batch_accounting(call_id: str) -> Generator[BatchAccountingOutcome, None, None]: + outcome: Final = BatchAccountingOutcome(call_id) + token: Final = _BATCH_ACCOUNTING.set(outcome) + try: + yield outcome + finally: + _BATCH_ACCOUNTING.reset(token) + + +def _batch_accounting_for(call_id: object) -> BatchAccountingOutcome | None: + outcome: Final = _BATCH_ACCOUNTING.get() + return outcome if outcome is not None and call_id == outcome.call_id else None + + _UNATTRIBUTED_TRACKABLE_CALL_TYPES: Final[frozenset[str]] = frozenset( { CallTypes.pass_through.value, @@ -286,6 +321,11 @@ class _ProxyDBLogger(CustomLogger): update_cache, ) + accounting: Final = ( + _batch_accounting_for(_BATCH_CALLBACK_FIELDS.validate_python(kwargs).get("litellm_call_id")) + if _BATCH_ACCOUNTING.get() is not None + else None + ) verbose_proxy_logger.debug("INSIDE _PROXY_track_cost_callback") try: verbose_proxy_logger.debug( @@ -306,6 +346,8 @@ class _ProxyDBLogger(CustomLogger): ) _write_spend_metadata_to_kwargs(kwargs=kwargs, metadata=metadata) budget_reservation: Final = _get_budget_reservation_from_metadata(metadata=metadata) + if accounting is not None and budget_reservation is not None: + accounting.write_started = True if ( isinstance(completion_response, LiteLLMBatch) and kwargs.get("call_type") == CallTypes.aretrieve_batch.value @@ -448,6 +490,8 @@ class _ProxyDBLogger(CustomLogger): f"Cost tracking failed for model={model}.\nDebug info - {cost_tracking_failure_debug_info}\nAdd custom pricing - https://docs.litellm.ai/docs/proxy/custom_pricing" ) except Exception as e: + if accounting is not None: + accounting.failed = True failing_model: Final = kwargs.get("model", "") failing_call_type: Final = kwargs.get("call_type", "") error_msg: Final = ( @@ -698,7 +742,15 @@ async def _update_database_and_spend_counters( budget_reservation=budget_reservation, response_cost=response_cost ) try: - charged: Final = await proxy_logging_obj.db_spend_update_writer.update_database( + writer: Final = proxy_logging_obj.db_spend_update_writer + accounting: Final = ( + _batch_accounting_for(_BATCH_CALLBACK_FIELDS.validate_python(kwargs).get("litellm_call_id")) + if _BATCH_ACCOUNTING.get() is not None + else None + ) + if accounting is not None: + accounting.write_started = True + charged: Final = await writer.update_database( token=user_api_key, response_cost=response_cost, user_id=user_id, diff --git a/litellm/router_strategy/budget_limiter.py b/litellm/router_strategy/budget_limiter.py index 64252cbbfb3..f68af6b21b7 100644 --- a/litellm/router_strategy/budget_limiter.py +++ b/litellm/router_strategy/budget_limiter.py @@ -27,6 +27,8 @@ from itertools import groupby from types import MappingProxyType from typing import Any, Final +from pydantic import TypeAdapter + import litellm from litellm._logging import verbose_router_logger from litellm.caching.caching import DualCache @@ -37,6 +39,7 @@ from litellm.litellm_core_utils.core_helpers import ( ) from litellm.litellm_core_utils.duration_parser import duration_in_seconds from litellm.router_strategy.tag_based_routing import _get_tags_from_request_kwargs +from litellm.router_utils.batch_utils import batch_charged_once_marker_key, batch_id_to_charge_once from litellm.router_utils.cooldown_callbacks import ( _get_prometheus_logger_from_callbacks, ) @@ -46,6 +49,8 @@ from litellm.types.utils import BudgetConfig, GenericBudgetConfigType, StandardL from litellm.types.utils import BudgetConfig as GenericBudgetInfo DEFAULT_REDIS_SYNC_INTERVAL: Final = 1 +_CALLBACK_FIELDS: Final = TypeAdapter(dict[str, object]) +_BATCH_CHARGE_VALUES: Final = TypeAdapter(tuple[object, float]) class _LiteLLMParamsDictView: @@ -500,10 +505,14 @@ class RouterBudgetLimiting(CustomLogger): if standard_logging_payload is None: raise ValueError("standard_logging_payload is required") - response_cost: Final[float] = standard_logging_payload.get("response_cost", 0) + batch_response, response_cost = _BATCH_CHARGE_VALUES.validate_python( + (response_obj, _CALLBACK_FIELDS.validate_python(standard_logging_payload).get("response_cost", 0)) + ) model_id: Final[str] = str(standard_logging_payload.get("model_id", "")) custom_llm_provider: Final[str | None] = standard_logging_payload.get("custom_llm_provider") + batch_id: Final = batch_id_to_charge_once(kwargs.get("call_type"), batch_response, response_cost) + budget_config: Final = ( self._get_budget_config_for_provider(custom_llm_provider) if custom_llm_provider is not None else None ) @@ -516,6 +525,7 @@ class RouterBudgetLimiting(CustomLogger): spend_key=spend_key, start_time_key=start_time_key, response_cost=response_cost, + batch_id=batch_id, ) deployment_budget_config: Final = self._get_budget_config_for_deployment(model_id) @@ -528,6 +538,7 @@ class RouterBudgetLimiting(CustomLogger): spend_key=deployment_spend_key, start_time_key=deployment_start_time_key, response_cost=response_cost, + batch_id=batch_id, ) request_tags: Final = _get_tags_from_request_kwargs( @@ -545,6 +556,7 @@ class RouterBudgetLimiting(CustomLogger): spend_key=_tag_spend_key, start_time_key=_tag_start_time_key, response_cost=response_cost, + batch_id=batch_id, ) async def _increment_spend_for_key( @@ -553,12 +565,15 @@ class RouterBudgetLimiting(CustomLogger): spend_key: str, start_time_key: str, response_cost: float, + batch_id: str | None = None, ): if budget_config.budget_duration is None: return current_time: Final = datetime.now(timezone.utc).timestamp() ttl_seconds: Final = duration_in_seconds(budget_config.budget_duration) + if batch_id is not None and not await self._claim_batch_charge(spend_key, batch_id, ttl_seconds): + return budget_start = await self._get_or_set_budget_start_time( start_time_key=start_time_key, @@ -596,6 +611,17 @@ class RouterBudgetLimiting(CustomLogger): verbose_router_logger.debug("Incremented spend for %s by %s", spend_key, response_cost) + async def _claim_batch_charge(self, spend_key: str, batch_id: str, ttl_seconds: int) -> bool: + marker_key: Final = batch_charged_once_marker_key(spend_key=spend_key, batch_id=batch_id) + redis_cache: Final = self.dual_cache.redis_cache + if redis_cache is not None: + polls: Final = await redis_cache.async_increment(key=marker_key, value=1, ttl=ttl_seconds, refresh_ttl=True) + return polls == 1 + local_polls: Final = await self.dual_cache.in_memory_cache.async_increment( + key=marker_key, value=1, ttl=ttl_seconds, refresh_ttl=True + ) + return local_polls == 1 + async def periodic_sync_in_memory_spend_with_redis(self): """ Handler that triggers sync_in_memory_spend_with_redis every DEFAULT_REDIS_SYNC_INTERVAL seconds diff --git a/litellm/router_utils/batch_utils.py b/litellm/router_utils/batch_utils.py index 386a2135239..50085a055b2 100644 --- a/litellm/router_utils/batch_utils.py +++ b/litellm/router_utils/batch_utils.py @@ -3,6 +3,8 @@ import json from os import PathLike from typing import Final +from openai.types import Batch + from litellm._logging import verbose_logger from litellm.types.llms.openai import FileTypes, OpenAIFilesPurpose from litellm.types.utils import CallTypes @@ -189,3 +191,14 @@ def is_batch_retrieve_call_type(call_type: object) -> bool: routing strategies' own state, must not be fed from it. """ return isinstance(call_type, str) and call_type in BATCH_RETRIEVE_CALL_TYPES + + +def batch_charged_once_marker_key(spend_key: str, batch_id: str) -> str: + return f"{spend_key}:batch:{batch_id}" + + +def batch_id_to_charge_once(call_type: object, response_obj: object, response_cost: float) -> str | None: + """A finished batch reports its whole cost on every poll, so its id is charged once per counter.""" + if response_cost <= 0 or not is_batch_retrieve_call_type(call_type): + return None + return response_obj.id if isinstance(response_obj, Batch) else None diff --git a/tests/router_unit_tests/test_router_batch_utils.py b/tests/router_unit_tests/test_router_batch_utils.py index 4336185a07f..c29205059a3 100644 --- a/tests/router_unit_tests/test_router_batch_utils.py +++ b/tests/router_unit_tests/test_router_batch_utils.py @@ -3,7 +3,7 @@ import pytest import json from io import BytesIO -from typing import Dict, List +from typing import Dict, List, Final from litellm.router_utils.batch_utils import ( replace_model_in_jsonl, _get_router_metadata_variable_name, @@ -333,3 +333,31 @@ def test_is_batch_retrieve_call_type_matches_only_batch_retrieves(): assert is_batch_retrieve_call_type(call_type.value) is False assert is_batch_retrieve_call_type(None) is False + + +@pytest.mark.parametrize( + ("call_type", "cost", "eligible"), + (("aretrieve_batch", 0.25, True), ("retrieve_batch", 0.25, True), ("acompletion", 0.25, False), + ("aretrieve_batch", 0, False), ("aretrieve_batch", -0.25, False)), +) +def test_batch_charge_identity_requires_a_cost_bearing_retrieval(call_type: str, cost: float, eligible: bool) -> None: + from openai.types import Batch + from litellm.router_utils.batch_utils import batch_id_to_charge_once + + batch: Final = Batch( + id="batch-budget", completion_window="24h", created_at=1, endpoint="/v1/chat/completions", + input_file_id="file-budget", object="batch", status="completed", + ) + assert batch_id_to_charge_once(call_type, batch, cost) == (batch.id if eligible else None) + assert batch_id_to_charge_once(call_type, {"id": batch.id}, cost) is None + + +def test_batch_charge_markers_keep_counters_and_batches_independent() -> None: + from litellm.caching.in_memory_cache import InMemoryCache + from litellm.router_utils.batch_utils import batch_charged_once_marker_key + + cache: Final = InMemoryCache() + cache.set_cache(batch_charged_once_marker_key("provider-spend", "first-batch"), 1) + assert cache.get_cache(batch_charged_once_marker_key("provider-spend", "first-batch")) == 1 + assert cache.get_cache(batch_charged_once_marker_key("deployment-spend", "first-batch")) is None + assert cache.get_cache(batch_charged_once_marker_key("provider-spend", "second-batch")) is None diff --git a/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py b/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py index b5e594db701..68f0b78172c 100644 --- a/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py +++ b/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py @@ -2,6 +2,7 @@ import asyncio import json import logging from datetime import datetime +from types import SimpleNamespace from typing import Final from unittest.mock import AsyncMock, MagicMock, patch @@ -2712,3 +2713,75 @@ async def test_track_cost_callback_failure_alert_never_carries_request_metadata_ assert "headers" in failure_debug_lines[0] else: assert failure_debug_lines == [] + + +_BATCH_CALL_START: Final = datetime(2026, 1, 1) + + +@pytest.mark.asyncio +async def test_batch_accounting_failures_stay_with_their_originating_call() -> None: + from litellm.proxy.hooks.proxy_track_cost_callback import track_batch_accounting + + logger: Final = _ProxyDBLogger() + dependency: Final = SimpleNamespace(failed_tracking_alert=AsyncMock()) + + async def fail_before_accounting(call_id: str) -> None: + await logger.async_log_success_event( + kwargs={ + "litellm_call_id": call_id, + "call_type": "aretrieve_batch", + "model": "batch-model", + "stream": False, + "response_cost": None, + }, + response_obj=None, + start_time=_BATCH_CALL_START, + end_time=_BATCH_CALL_START, + ) + + async def independent_batch() -> bool: + with track_batch_accounting("independent") as outcome: + await fail_before_accounting("independent") + return outcome.retryable_failure + + with patch("litellm.proxy.proxy_server.proxy_logging_obj", dependency): + with track_batch_accounting("outer") as outer: + await fail_before_accounting("unrelated") + assert outer.retryable_failure is False + with track_batch_accounting("inner") as inner: + await fail_before_accounting("inner") + assert inner.retryable_failure is True + assert outer.retryable_failure is False + independent, _ = await asyncio.gather(independent_batch(), fail_before_accounting("outer")) + assert independent is True + assert outer.retryable_failure is True + with pytest.raises(asyncio.CancelledError): + with track_batch_accounting("cancelled") as cancelled: + raise asyncio.CancelledError + await fail_before_accounting("cancelled") + assert cancelled.retryable_failure is False + + +@pytest.mark.asyncio +async def test_batch_accounting_does_not_retry_after_settling_a_budget_reservation() -> None: + from litellm.proxy.hooks.proxy_track_cost_callback import track_batch_accounting + + reservation: Final[dict[str, object]] = {"reserved_cost": 0.5, "entries": ()} + dependency: Final = SimpleNamespace(failed_tracking_alert=AsyncMock()) + with patch("litellm.proxy.proxy_server.proxy_logging_obj", dependency): + with track_batch_accounting("reserved") as outcome: + await _ProxyDBLogger().async_log_success_event( + kwargs={ + "litellm_call_id": "reserved", + "call_type": "aretrieve_batch", + "model": "batch-model", + "stream": False, + "response_cost": None, + "litellm_params": {"metadata": {"user_api_key_budget_reservation": reservation}}, + }, + response_obj=None, + start_time=_BATCH_CALL_START, + end_time=_BATCH_CALL_START, + ) + assert reservation["finalized"] is True + assert outcome.retryable_failure is False diff --git a/tests/unit/proxy/common_utils/test_check_batch_cost.py b/tests/unit/proxy/common_utils/test_check_batch_cost.py index 198e20d1c02..46dbde82ded 100644 --- a/tests/unit/proxy/common_utils/test_check_batch_cost.py +++ b/tests/unit/proxy/common_utils/test_check_batch_cost.py @@ -3217,6 +3217,151 @@ class TestMultiPodBatchCostClaim: ): yield logging_obj + @pytest.mark.asyncio + @pytest.mark.parametrize("failure_phase", ("before_write", "after_write", "external")) + @pytest.mark.parametrize("collector_enabled", (False, True)) + async def test_builtin_accounting_retries_only_before_a_possible_charge( + self, failure_phase: str, collector_enabled: bool + ) -> None: + import base64 + from datetime import datetime + + import httpx + import litellm + import respx + + from litellm.caching.caching import DualCache + from litellm.integrations.custom_logger import CustomLogger + from litellm.router_strategy.budget_limiter import RouterBudgetLimiting + from litellm.proxy.db.db_spend_update_writer import DBSpendUpdateWriter + from litellm.proxy.hooks.proxy_track_cost_callback import _ProxyDBLogger as ProxyDBLogger + from litellm.proxy.utils import PrismaClient + from litellm.types.router import Deployment, LiteLLM_Params, ModelInfo + from litellm.types.utils import SpecialEnums + + class AccountingDependency: + def __init__(self) -> None: + self.failure_phase = failure_phase + self.writer: Final = DBSpendUpdateWriter() + self.failed_tracking_alert = AsyncMock() + self.slack_alerting_instance = MagicMock() + self.slack_alerting_instance.customer_spend_alert = AsyncMock( + side_effect=ConnectionError("Alert destination unavailable after charge") + if failure_phase == "after_write" + else None + ) + + @property + def db_spend_update_writer(self) -> DBSpendUpdateWriter: + if self.failure_phase == "before_write": + raise ConnectionError("Accounting dependency temporarily unavailable") + return self.writer + + class ExternalCallback(CustomLogger): + async def async_log_success_event( + self, kwargs: dict[str, object], response_obj: object, start_time: datetime, end_time: datetime + ) -> None: + if failure_phase == "external": + raise ConnectionError("External destination unavailable") + + budget_cache: Final = DualCache() + RouterBudgetLimiting( + dual_cache=budget_cache, + provider_budget_config={"openai": {"budget_limit": 100, "time_period": "1d"}}, + model_list=[ + { + "model_name": "batch-alias", + "litellm_params": {"model": "openai/batch-test-model", "max_budget": 100, "budget_duration": "1d"}, + "model_info": {"id": "model-123"}, + } + ], + ) + dependency: Final = AccountingDependency() + spend_prisma: Final = PrismaClient( + database_url="postgresql://unused:unused@localhost:5432/unused", proxy_logging_obj=dependency + ) + create_spend_rows: Final = AsyncMock(return_value=1) + input_rate: Final = 0.000002 + litellm.register_model( + { + "batch-test-model": { + "litellm_provider": "openai", + "mode": "chat", + "input_cost_per_token_batches": input_rate, + "output_cost_per_token_batches": 0.000006, + } + } + ) + content: Final = json.dumps( + { + "response": { + "status_code": 200, + "body": { + "model": "batch-test-model", + "usage": {"prompt_tokens": 100, "completion_tokens": 0, "total_tokens": 100}, + }, + }, + "error": None, + } + ).encode() + row: Final = _FakeManagedObjectRow() + original_status: Final = row.status + original_file_object: Final = row.file_object + row.unified_object_id = ( + base64.urlsafe_b64encode( + SpecialEnums.LITELLM_MANAGED_BATCH_COMPLETE_STR.value.format("model-123", "batch-456").encode() + ) + .decode() + .rstrip("=") + ) + prisma: Final = self._prisma(row, []) + router: Final = self._router() + router.get_deployment.return_value = Deployment( + model_name="batch-alias", + litellm_params=LiteLLM_Params(model="openai/batch-test-model"), + model_info=ModelInfo(id="model-123"), + ) + from litellm.proxy.spend_tracking.spend_event_producer import SpendEventProducer + + producer: Final = MagicMock(spec=SpendEventProducer) if collector_enabled else None + litellm.logging_callback_manager.add_litellm_async_success_callback( + ProxyDBLogger(spend_event_producer=producer) + ) + litellm.logging_callback_manager.add_litellm_async_success_callback(ExternalCallback()) + with ( + respx.mock, + patch("litellm.proxy.proxy_server.proxy_logging_obj", dependency), + patch("litellm.proxy.proxy_server.prisma_client", spend_prisma), + patch.object( + spend_prisma.writer_db._original_prisma, + "litellm_spendlogs", + MagicMock(create_many=create_spend_rows), + ), + ): + respx.get(f"https://api.openai.com/v1/files/{_CLAIM_OUTPUT_FILE_ID}/content").mock( + return_value=httpx.Response(200, content=content) + ) + worker: Final = self._instance(prisma, router) + await worker.check_batch_cost() + assert row.batch_processed is (failure_phase != "before_write") + if failure_phase == "before_write": + assert row.status == original_status + assert json.loads(row.file_object) == original_file_object + assert create_spend_rows.await_count == (0 if failure_phase == "before_write" else 1) + dependency.failure_phase = "recovered" + await worker.check_batch_cost() + await worker.check_batch_cost() + + assert row.batch_processed is True + assert await budget_cache.async_get_cache("provider_spend:openai:1d") == pytest.approx(100 * input_rate) + assert await budget_cache.async_get_cache("deployment_spend:model-123:1d") == pytest.approx(100 * input_rate) + create_spend_rows.assert_awaited_once() + assert create_spend_rows.call_args.kwargs["data"][0]["spend"] == pytest.approx(100 * input_rate) + if producer is not None: + assert all( + json.loads(call.args[0])["call_type"] != "aretrieve_batch" for call in producer.publish.call_args_list + ) + @pytest.mark.asyncio @pytest.mark.parametrize( ("deployment_model", "successes", "failures", "expected_model"), @@ -3502,30 +3647,23 @@ class TestMultiPodBatchCostClaim: @pytest.mark.asyncio @pytest.mark.parametrize("stored_as_json_string", (True, False)) - async def test_a_failed_spend_log_write_releases_the_claim(self, stored_as_json_string: bool) -> None: - """A transient failure while billing a claimed batch must hand the row back, or its - spend is silently lost instead of being retried on the next cycle.""" - row = _FakeManagedObjectRow() - original_file_object: Final = row.file_object if stored_as_json_string else json.loads(row.file_object) - row.file_object = original_file_object - journal = [] - prisma = self._prisma(row, journal) + async def test_an_unclassified_logging_failure_keeps_the_claim(self, stored_as_json_string: bool) -> None: + row: Final = _FakeManagedObjectRow() + row.file_object = row.file_object if stored_as_json_string else json.loads(row.file_object) + journal: Final = [] + prisma: Final = self._prisma(row, journal) - with self._billing_patches(journal, bill_error=Exception("spend log write failed")): + with self._billing_patches(journal, bill_error=Exception("Accounting outcome unknown")): await self._instance(prisma, self._router()).check_batch_cost() - assert journal == ["fetch", "claim", "bill", "release"] - assert row.batch_processed is False - assert row.status == "in_progress" - assert json.loads(row.file_object) == original_file_object + assert journal == ["fetch", "claim", "bill"] + assert row.batch_processed is True with self._billing_patches(journal) as logging_obj: await self._instance(prisma, self._router()).check_batch_cost() await self._instance(prisma, self._router()).check_batch_cost() - assert row.batch_processed is True - assert row.status == "complete" - logging_obj.async_success_handler.assert_awaited_once() + logging_obj.async_success_handler.assert_not_awaited() @pytest.mark.asyncio async def test_a_worker_interrupted_mid_costing_leaves_the_batch_billable(self): diff --git a/tests/unit/router_strategy/test_budget_limiter.py b/tests/unit/router_strategy/test_budget_limiter.py index 62de1586fdd..3b1fa2ac577 100644 --- a/tests/unit/router_strategy/test_budget_limiter.py +++ b/tests/unit/router_strategy/test_budget_limiter.py @@ -6,10 +6,12 @@ anthropic_messages, embedding and rerank surfaces leave it unset, which used to the callback raise before any spend was recorded, so those budgets never moved. """ +import asyncio from typing import Final import pytest +import litellm from litellm.caching.caching import DualCache from litellm.router_strategy.budget_limiter import RouterBudgetLimiting @@ -135,3 +137,91 @@ async def test_deployment_budget_tracked_when_provider_is_unresolvable(disable_b ) assert await limiter.dual_cache.async_get_cache("deployment_spend:deployment-1:1d") == 0.25 + + +def _completed_budget_batch(batch_id: str): + from litellm.types.utils import LiteLLMBatch + + return LiteLLMBatch( + id=batch_id, + completion_window="24h", + created_at=1, + endpoint="/v1/chat/completions", + input_file_id="file-budget", + object="batch", + status="completed", + ) + + +@pytest.mark.asyncio +@pytest.mark.parametrize("call_type", ("aretrieve_batch", "retrieve_batch")) +async def test_batch_polls_charge_each_router_budget_once(monkeypatch, call_type): + monkeypatch.setattr(litellm, "tag_budget_config", {"release": {"budget_limit": 100, "time_period": "1d"}}) + monkeypatch.setattr("litellm.proxy.proxy_server.premium_user", True) + cache: Final = DualCache() + limiter: Final = RouterBudgetLimiting( + dual_cache=cache, + provider_budget_config={"openai": {"budget_limit": 100, "time_period": "1d"}}, + model_list=[ + { + "model_name": "batch-budget", + "litellm_params": {"model": "openai/batch-budget", "max_budget": 100, "budget_duration": "1d"}, + "model_info": {"id": "deployment-1"}, + } + ], + ) + kwargs: Final = { + **_success_kwargs(provider_in_litellm_params=None, provider_in_payload="openai", call_type=call_type), + "metadata": {"tags": ["release"]}, + } + response: Final = _completed_budget_batch("batch-first") + await asyncio.gather(*(limiter.async_log_success_event(kwargs, response, None, None) for _ in range(10))) + keys: Final = ("provider_spend:openai:1d", "deployment_spend:deployment-1:1d", "tag_spend:release:1d") + assert tuple([await cache.async_get_cache(key) for key in keys]) == (0.25, 0.25, 0.25) + await limiter.async_log_success_event(kwargs, _completed_budget_batch("batch-second"), None, None) + await limiter.async_log_success_event({**kwargs, "call_type": "acompletion"}, response, None, None) + await limiter.async_log_success_event({**kwargs, "call_type": "acompletion"}, response, None, None) + assert tuple([await cache.async_get_cache(key) for key in keys]) == (1.0, 1.0, 1.0) + await limiter.async_log_success_event({**kwargs, "call_type": "_arealtime"}, response, None, None) + assert tuple([await cache.async_get_cache(key) for key in keys]) == (1.0, 1.0, 1.0) + + +@pytest.mark.asyncio +async def test_batch_charge_is_shared_across_workers_and_requires_redis_confirmation(): + from fakeredis import FakeServer, FakeRedis as FakeSyncRedis + from redis.exceptions import ConnectionError as RedisConnectionError + from fakeredis.aioredis import FakeRedis + from litellm.caching.redis_cache import RedisCache + + server: Final = FakeServer() + client: Final = FakeRedis(server=server) + sync_client: Final = FakeSyncRedis(server=server) + redis_cache: Final = RedisCache(host="router-batch-fixture", connection_pool=sync_client.connection_pool) + litellm.in_memory_llm_clients_cache.set_cache(key=redis_cache._get_async_client_cache_key(), value=client) + first: Final = RouterBudgetLimiting( + dual_cache=DualCache(redis_cache=redis_cache), + provider_budget_config={"openai": {"budget_limit": 100, "time_period": "1d"}}, + ) + second: Final = RouterBudgetLimiting( + dual_cache=DualCache(redis_cache=redis_cache), + provider_budget_config={"openai": {"budget_limit": 100, "time_period": "1d"}}, + ) + kwargs: Final = _success_kwargs( + provider_in_litellm_params=None, provider_in_payload="openai", call_type="aretrieve_batch" + ) + response: Final = _completed_budget_batch("batch-shared") + await asyncio.gather( + first.async_log_success_event(kwargs, response, None, None), + second.async_log_success_event(kwargs, response, None, None), + ) + await first._push_in_memory_increments_to_redis() + await second._push_in_memory_increments_to_redis() + assert float(await client.get("provider_spend:openai:1d")) == 0.25 + server.connected = False + with pytest.raises(RedisConnectionError): + await second.async_log_success_event(kwargs, _completed_budget_batch("batch-unconfirmed"), None, None) + server.connected = True + await second.async_log_success_event(kwargs, _completed_budget_batch("batch-unconfirmed"), None, None) + await second._push_in_memory_increments_to_redis() + assert float(await client.get("provider_spend:openai:1d")) == 0.5 + await client.aclose() From f585b558e95fae00b18cf7cd0058a508b98cecc7 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Mon, 19 Oct 2026 18:51:51 -0700 Subject: [PATCH 37/66] fix(batches): apply the Vertex regional endpoint uplift to batch cost (#47466) * fix(batches): apply the Vertex regional endpoint uplift to batch cost batch_cost_calculator takes vertex_location and multiplies by the model's regional_endpoint_uplift_multiplier through get_vertex_regional_endpoint_uplift, and every batch cost path (aretrieve_batch pricing, completed-batch logging, native Vertex batch rows, the proxy batch cost poll and its per-line items) resolves the deployment's location and passes it down Co-authored-by: Mrun25 <165297479+Mrun25@users.noreply.github.com> * test(logging): point the resolver tests at resolve_vertex_location_for_cost --------- Backport of #47466 to stable/1.104.x Cherry-picked from c6c303a6181bf0b59f6b30beb708deade0d955d0 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Mrun25 <165297479+Mrun25@users.noreply.github.com> --- .../proxy/common_utils/check_batch_cost.py | 12 ++++- litellm/batches/batch_utils.py | 34 ++++++++++-- litellm/cost_calculator.py | 7 ++- litellm/litellm_core_utils/litellm_logging.py | 10 +++- .../llms/vertex_ai/batches/transformation.py | 9 +++- tests/unit/batches/test_batch_utils.py | 36 +++++++++++-- .../test_litellm_logging.py | 54 ++++++++++++++++++- .../custom_httpx/test_llm_http_handler.py | 4 +- tests/unit/test_cost_calculator.py | 24 +++++++++ 9 files changed, 173 insertions(+), 17 deletions(-) diff --git a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py index 35fc3510414..7ae03992007 100644 --- a/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py +++ b/enterprise/litellm_enterprise/proxy/common_utils/check_batch_cost.py @@ -712,7 +712,11 @@ class CheckBatchCost: from litellm.files.main import afile_content from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLogging - from litellm.litellm_core_utils.litellm_logging import deployment_pricing_model_info, mask_api_base_credentials + from litellm.litellm_core_utils.litellm_logging import ( + deployment_pricing_model_info, + mask_api_base_credentials, + resolve_vertex_location_for_cost, + ) from litellm.proxy.openai_files_endpoints.common_utils import ( _is_base64_encoded_unified_file_id, ) @@ -849,6 +853,12 @@ class CheckBatchCost: custom_llm_provider=batch_file_provider, model_name=model_name, model_info=deployment_model_info, + vertex_location=resolve_vertex_location_for_cost( + custom_llm_provider=llm_provider, + litellm_params=deployment_info.litellm_params.model_dump(exclude_none=True), + optional_params=None, + model=model_name, + ), ) error_file_failed_requests: Final = await count_error_file_failed_requests( response, diff --git a/litellm/batches/batch_utils.py b/litellm/batches/batch_utils.py index 819a279a43c..cdc2625239f 100644 --- a/litellm/batches/batch_utils.py +++ b/litellm/batches/batch_utils.py @@ -73,6 +73,7 @@ async def calculate_batch_cost_and_usage( custom_llm_provider: Literal["openai", "azure", "vertex_ai", "hosted_vllm", "anthropic", "mistral"], model_name: str | None = None, model_info: ModelInfo | None = None, + vertex_location: str | None = None, ) -> BatchCostUsageResult: """ Calculate the cost and usage of a batch. @@ -82,16 +83,21 @@ async def calculate_batch_cost_and_usage( pricing. Threaded through to batch_cost_calculator so that deployment-specific pricing (e.g. input_cost_per_token_batches) is used instead of the global cost map. + vertex_location: The Vertex AI location the batch ran on; non-global + locations apply the model's regional-endpoint uplift multiplier. """ first_row: Final = file_content_dictionary[0] if file_content_dictionary else None if _uses_native_vertex_output(custom_llm_provider, model_name, first_row): - return calculate_vertex_ai_batch_cost_and_usage(file_content_dictionary, model_name, model_info=model_info) + return calculate_vertex_ai_batch_cost_and_usage( + file_content_dictionary, model_name, model_info=model_info, vertex_location=vertex_location + ) return _aggregate_batch_cost_usage_models( entries=file_content_dictionary, custom_llm_provider=custom_llm_provider, model_name=model_name, model_info=model_info, + vertex_location=vertex_location, ) @@ -101,6 +107,7 @@ async def _handle_completed_batch( model_name: str | None = None, litellm_params: dict | None = None, model_info: ModelInfo | None = None, + vertex_location: str | None = None, ) -> BatchCostUsageResult: """Fetch a completed batch's output file and aggregate its cost, usage, and models in a single pass over the JSONL lines, so the parsed file content is @@ -114,6 +121,8 @@ async def _handle_completed_batch( model_info: Optional deployment-level model info with custom pricing, threaded through so a deployment's configured rates win over the global cost map. + vertex_location: The Vertex AI location the batch ran on; non-global + locations apply the model's regional-endpoint uplift multiplier. """ # A completed batch whose request lines all failed has no output file - the # results are written to a separate error_file_id and output_file_id is None. @@ -141,7 +150,10 @@ async def _handle_completed_batch( output_file_result: Final = ( calculate_vertex_ai_batch_cost_and_usage( - _iter_batch_output_entries(file_content), model_name, model_info=model_info + _iter_batch_output_entries(file_content), + model_name, + model_info=model_info, + vertex_location=vertex_location, ) if _uses_native_vertex_output( custom_llm_provider, model_name, next(_iter_batch_output_entries(file_content), None) @@ -151,6 +163,7 @@ async def _handle_completed_batch( custom_llm_provider=custom_llm_provider, model_name=model_name, model_info=model_info, + vertex_location=vertex_location, ) ) @@ -186,6 +199,7 @@ def _classify_output_line_stats( custom_llm_provider: Literal["openai", "azure", "vertex_ai", "hosted_vllm", "anthropic", "bedrock", "mistral"], model_name: str | None, model_info: ModelInfo | None, + vertex_location: str | None = None, ) -> Iterator[_BatchOutputLineStats | _LineOutcome]: """Classify every output line in a single pass, so counting failures never needs a second read of a potentially huge output file. A line the provider reported as @@ -196,7 +210,7 @@ def _classify_output_line_stats( if not _batch_response_was_successful(entry, custom_llm_provider): yield _LineOutcome.PROVIDER_FAILED continue - stats = _safe_output_line_stats(entry, custom_llm_provider, model_name, model_info) + stats = _safe_output_line_stats(entry, custom_llm_provider, model_name, model_info, vertex_location) yield stats if stats is not None else _LineOutcome.UNCOSTABLE @@ -205,13 +219,14 @@ def _safe_output_line_stats( custom_llm_provider: Literal["openai", "azure", "vertex_ai", "hosted_vllm", "anthropic", "bedrock", "mistral"], model_name: str | None, model_info: ModelInfo | None, + vertex_location: str | None = None, ) -> _BatchOutputLineStats | None: """Return the stats for one provider-successful batch output line, or None when it cannot be costed, so a single bad line never aborts the whole batch's cost accounting.""" custom_id: Final = entry.get("custom_id") if isinstance(entry, dict) else None try: - return _compute_output_line_stats(entry, custom_llm_provider, model_name, model_info) + return _compute_output_line_stats(entry, custom_llm_provider, model_name, model_info, vertex_location) except Exception as e: # noqa: BLE001 # any single line's costing failure must not abort the whole batch verbose_logger.warning( "batch output line could not be costed, so it is billed at $0 and the rest of the batch " @@ -227,6 +242,7 @@ def _compute_output_line_stats( custom_llm_provider: Literal["openai", "azure", "vertex_ai", "hosted_vllm", "anthropic", "bedrock", "mistral"], model_name: str | None, model_info: ModelInfo | None, + vertex_location: str | None = None, ) -> _BatchOutputLineStats: response_body: Final = _get_response_from_batch_job_output_file(entry, custom_llm_provider) usage: Final = _get_batch_job_usage_from_response_body(response_body, custom_llm_provider) @@ -241,6 +257,7 @@ def _compute_output_line_stats( model_name=model_name, response_model=response_model, model_info=model_info, + vertex_location=vertex_location, ) return _BatchOutputLineStats( prompt_cost=line_prompt_cost, @@ -270,6 +287,7 @@ def _output_line_cost( model_name: str | None, response_model: str | None, model_info: ModelInfo | None, + vertex_location: str | None = None, ) -> tuple[float, float]: """(prompt_cost, completion_cost) for one output line, priced at batch rates.""" from litellm.cost_calculator import batch_cost_calculator, ocr_batch_cost @@ -290,6 +308,7 @@ def _output_line_cost( model=cost_model, custom_llm_provider=custom_llm_provider, model_info=model_info, + vertex_location=vertex_location, ) @@ -298,11 +317,14 @@ def _aggregate_batch_cost_usage_models( custom_llm_provider: Literal["openai", "azure", "vertex_ai", "hosted_vllm", "anthropic", "bedrock", "mistral"], model_name: str | None = None, model_info: ModelInfo | None = None, + vertex_location: str | None = None, ) -> BatchCostUsageResult: """Aggregate cost, usage, models, and pass/fail counts from batch output entries in a single pass, holding one small stats record per line instead of the parsed file.""" - all_results: Final = tuple(_classify_output_line_stats(entries, custom_llm_provider, model_name, model_info)) + all_results: Final = tuple( + _classify_output_line_stats(entries, custom_llm_provider, model_name, model_info, vertex_location) + ) line_stats: Final = tuple(result for result in all_results if isinstance(result, _BatchOutputLineStats)) failed_requests: Final = sum(1 for result in all_results if result is _LineOutcome.PROVIDER_FAILED) successful_requests: Final = len(all_results) - failed_requests @@ -349,6 +371,7 @@ def calculate_vertex_ai_batch_cost_and_usage( vertex_ai_batch_responses: Iterable[dict], model_name: str | None = None, model_info: ModelInfo | None = None, + vertex_location: str | None = None, ) -> BatchCostUsageResult: """ Cost and usage of a native Vertex predictions.jsonl, one @@ -367,6 +390,7 @@ def calculate_vertex_ai_batch_cost_and_usage( model_info=model_info, calculate_usage=VertexGeminiConfig._calculate_usage, cost_calculator=batch_cost_calculator, + vertex_location=vertex_location, ) for row in vertex_ai_batch_responses ) diff --git a/litellm/cost_calculator.py b/litellm/cost_calculator.py index 845c62d91d6..80e96b8e888 100644 --- a/litellm/cost_calculator.py +++ b/litellm/cost_calculator.py @@ -36,6 +36,7 @@ from litellm.litellm_core_utils.llm_cost_calc.utils import ( get_batch_cost_rates, get_billable_input_tokens, get_token_type_cost_breakdown, + get_vertex_regional_endpoint_uplift, parse_prompt_tokens_details, select_cost_metric_for_model, ) @@ -627,6 +628,7 @@ def cost_per_token( model=model, custom_llm_provider=custom_llm_provider, data_residency=data_residency, + vertex_location=vertex_location, ) elif call_type == "atranscription" or call_type == "transcription": if _transcription_usage_has_token_details(usage_block): @@ -2571,6 +2573,8 @@ def batch_cost_calculator( custom_llm_provider: str | None = None, model_info: ModelInfo | None = None, data_residency: str | None = None, + *, + vertex_location: str | None = None, ) -> tuple[float, float]: """ Calculate the cost of a batch job. @@ -2656,7 +2660,8 @@ def batch_cost_calculator( total_prompt_cost *= uplift total_completion_cost *= uplift - return total_prompt_cost, total_completion_cost + vertex_uplift: Final = get_vertex_regional_endpoint_uplift(model_info, vertex_location) + return total_prompt_cost * vertex_uplift, total_completion_cost * vertex_uplift def _batch_prompt_cost( diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py index efa6fd5f1e8..eba580561d3 100644 --- a/litellm/litellm_core_utils/litellm_logging.py +++ b/litellm/litellm_core_utils/litellm_logging.py @@ -485,7 +485,7 @@ def _published_pricing(deployment_model: str | None) -> ModelInfo | None: return None -def _resolve_vertex_location_for_cost( +def resolve_vertex_location_for_cost( custom_llm_provider: str | None, litellm_params: Mapping[str, object] | None, optional_params: Mapping[str, object] | None, @@ -1909,7 +1909,7 @@ class Logging(LiteLLMLoggingBaseClass): if hasattr(self, "litellm_params") and self.litellm_params else None ), - "vertex_location": _resolve_vertex_location_for_cost( + "vertex_location": resolve_vertex_location_for_cost( custom_llm_provider=self.model_call_details.get("custom_llm_provider", None), litellm_params=(self.litellm_params if hasattr(self, "litellm_params") else None), optional_params=self.optional_params, @@ -3267,6 +3267,12 @@ class Logging(LiteLLMLoggingBaseClass): model_name=self.get_deployment_model_for_cost(), litellm_params=self.litellm_params, model_info=self.get_router_deployment_model_info(), + vertex_location=resolve_vertex_location_for_cost( + custom_llm_provider=self.custom_llm_provider, + litellm_params=self.litellm_params if hasattr(self, "litellm_params") else None, + optional_params=None, + model=self.get_deployment_model_for_cost() or self.model, + ), ) result._hidden_params["response_cost"] = batch_result.cost diff --git a/litellm/llms/vertex_ai/batches/transformation.py b/litellm/llms/vertex_ai/batches/transformation.py index 11c99d130be..be66b395b1c 100644 --- a/litellm/llms/vertex_ai/batches/transformation.py +++ b/litellm/llms/vertex_ai/batches/transformation.py @@ -54,6 +54,8 @@ class NativeVertexBatchCostCalculator(Protocol): model: str, custom_llm_provider: str | None = None, model_info: ModelInfo | None = None, + *, + vertex_location: str | None = None, ) -> tuple[float, float]: ... @@ -90,6 +92,7 @@ def native_vertex_batch_row_stats( model_info: ModelInfo | None, calculate_usage: Callable[[GenerateContentResponseBody], Usage], cost_calculator: NativeVertexBatchCostCalculator, + vertex_location: str | None = None, ) -> NativeVertexBatchRowStats | None: """ Usage and cost of one native Vertex predictions.jsonl row, a @@ -121,7 +124,11 @@ def native_vertex_batch_row_stats( ) try: prompt_cost, completion_cost = cost_calculator( - usage=usage, model=model, custom_llm_provider="vertex_ai", model_info=model_info + usage=usage, + model=model, + custom_llm_provider="vertex_ai", + model_info=model_info, + vertex_location=vertex_location, ) except Exception as e: # noqa: BLE001 # one unpriceable row must not abort the batch's cost accounting verbose_logger.warning( diff --git a/tests/unit/batches/test_batch_utils.py b/tests/unit/batches/test_batch_utils.py index dd95addac40..398b6fb1aed 100644 --- a/tests/unit/batches/test_batch_utils.py +++ b/tests/unit/batches/test_batch_utils.py @@ -640,7 +640,7 @@ async def test_calculate_vertex_disable_transform_path(monkeypatch): monkeypatch.setattr( bu, "calculate_vertex_ai_batch_cost_and_usage", - lambda content, model, model_info=None: bu.BatchCostUsageResult( + lambda content, model, model_info=None, vertex_location=None: bu.BatchCostUsageResult( cost=9.9, usage=Usage(prompt_tokens=1, completion_tokens=2, total_tokens=3), models=["gemini-2.0-flash-001"], @@ -671,7 +671,7 @@ async def test_calculate_vertex_disable_transform_needs_model_name(monkeypatch): monkeypatch.setattr( bu, "calculate_vertex_ai_batch_cost_and_usage", - lambda content, model, model_info=None: pytest.fail("raw vertex path should not run"), + lambda content, model, model_info=None, vertex_location=None: pytest.fail("raw vertex path should not run"), ) result = await bu.calculate_batch_cost_and_usage(file_content_dictionary=[], custom_llm_provider="vertex_ai") @@ -1112,6 +1112,36 @@ async def test_handle_completed_vertex_batch_computes_cost_usage_and_models(monk assert result.failed_requests == 0 +@pytest.mark.asyncio +async def test_handle_completed_vertex_batch_regional_location_costs_uplift_over_global(monkeypatch: pytest.MonkeyPatch) -> None: + import litellm.files.main as files_main + + rows = [_vertex_openai_row("request-1", "gemini-3.6-flash", 10, 5)] + + async def fake_afile_content(**kw): + return type("R", (), {"content": _vertex_jsonl(rows)})() + + monkeypatch.setattr(files_main, "afile_content", fake_afile_content) + + global_result = await bu._handle_completed_batch( + _batch("gs://litellm-bucket/output/predictions.jsonl"), + custom_llm_provider="vertex_ai", + litellm_params={"vertex_project": "proj-1", "vertex_location": "global"}, + vertex_location="global", + ) + regional_result = await bu._handle_completed_batch( + _batch("gs://litellm-bucket/output/predictions.jsonl"), + custom_llm_provider="vertex_ai", + litellm_params={"vertex_project": "proj-1", "vertex_location": "us-central1"}, + vertex_location="us-central1", + ) + + uplift = litellm.model_cost["vertex_ai/gemini-3.6-flash"]["regional_endpoint_uplift_multiplier"] + assert global_result.cost > 0 + assert regional_result.cost == pytest.approx(global_result.cost * uplift, rel=1e-9) + assert regional_result.usage == global_result.usage + + @pytest.mark.asyncio async def test_output_file_content_no_output_file_id_raises(): with pytest.raises(ValueError, match="Output file id is None"): @@ -1341,7 +1371,7 @@ async def test_handle_completed_batch_vertex_disable_transform_path(monkeypatch) monkeypatch.setattr(litellm, "disable_vertex_batch_output_transformation", True, raising=False) seen: dict = {} - def fake_vertex_calc(content, model, model_info=None): + def fake_vertex_calc(content, model, model_info=None, vertex_location=None): seen["content"] = content seen["model"] = model return bu.BatchCostUsageResult( diff --git a/tests/unit/litellm_core_utils/test_litellm_logging.py b/tests/unit/litellm_core_utils/test_litellm_logging.py index 10bc65201a1..c112a88177e 100644 --- a/tests/unit/litellm_core_utils/test_litellm_logging.py +++ b/tests/unit/litellm_core_utils/test_litellm_logging.py @@ -1331,6 +1331,56 @@ class TestRetrieveBatchCostPassesModelIdentity: assert captured["model_info"] is not None assert captured["model_info"]["input_cost_per_token"] == 0.0 + @pytest.mark.asyncio + async def test_forwards_vertex_location_of_the_deployment(self, monkeypatch: pytest.MonkeyPatch) -> None: + from litellm.litellm_core_utils import litellm_logging as logging_module + + captured: dict[str, object] = {} + + from litellm.batches.batch_utils import BatchCostUsageResult + from litellm.types.utils import LiteLLMBatch, Usage + + async def fake_handle_completed_batch(**kwargs: object) -> BatchCostUsageResult: + captured.update(kwargs) + return BatchCostUsageResult( + cost=1.25, + usage=Usage(prompt_tokens=1800, completion_tokens=1000, total_tokens=2800), + models=["gemini-3.5-flash"], + successful_requests=1, + failed_requests=0, + ) + + monkeypatch.setattr(logging_module, "_handle_completed_batch", fake_handle_completed_batch) + + obj = LitellmLogging( + model="vertex_ai/gemini-3.5-flash", + messages=[{"role": "user", "content": "Hey"}], + stream=False, + call_type="aretrieve_batch", + start_time=time.time(), + litellm_call_id="batch-call-2", + function_id="f", + ) + obj.custom_llm_provider = "vertex_ai" + obj.litellm_params = {"vertex_project": "proj-1", "vertex_location": "us-central1"} + + batch = LiteLLMBatch( + id="batch_vertex", + completion_window="24h", + created_at=1, + endpoint="/v1/chat/completions", + input_file_id="file-in", + object="batch", + status="completed", + output_file_id="file-out", + ) + + with contextlib.suppress(Exception): + await obj._async_success_handler_body(result=batch, start_time=None, end_time=None) + + assert captured, "handle_completed_batch was never called" + assert captured["vertex_location"] == "us-central1" + class TestRetrieveBatchPricesOnlyFinalBatches: """Regression (LIT-7048): retrieving a provider-id batch priced it on every poll. @@ -6796,10 +6846,10 @@ async def test_streaming_success_callbacks_survive_guardrail_logging_hook_failur def _resolve(custom_llm_provider, litellm_params, optional_params, model): from litellm.litellm_core_utils.litellm_logging import ( - _resolve_vertex_location_for_cost, + resolve_vertex_location_for_cost, ) - return _resolve_vertex_location_for_cost( + return resolve_vertex_location_for_cost( custom_llm_provider=custom_llm_provider, litellm_params=litellm_params, optional_params=optional_params, diff --git a/tests/unit/llms/custom_httpx/test_llm_http_handler.py b/tests/unit/llms/custom_httpx/test_llm_http_handler.py index 399e4dbf206..1dc5f717b04 100644 --- a/tests/unit/llms/custom_httpx/test_llm_http_handler.py +++ b/tests/unit/llms/custom_httpx/test_llm_http_handler.py @@ -2900,7 +2900,7 @@ async def test_async_anthropic_messages_handler_carries_deployment_vertex_locati from litellm.litellm_core_utils.litellm_logging import ( Logging, - _resolve_vertex_location_for_cost, + resolve_vertex_location_for_cost, ) monkeypatch.setenv("VERTEXAI_LOCATION", "us-east5") @@ -2949,7 +2949,7 @@ async def test_async_anthropic_messages_handler_carries_deployment_vertex_locati global_deployment = await logging_obj_after_handler(GenericLiteLLMParams(vertex_location="global")) assert global_deployment.litellm_params["vertex_location"] == "global" assert ( - _resolve_vertex_location_for_cost( + resolve_vertex_location_for_cost( custom_llm_provider="vertex_ai", litellm_params=global_deployment.litellm_params, optional_params=global_deployment.optional_params, diff --git a/tests/unit/test_cost_calculator.py b/tests/unit/test_cost_calculator.py index 99dea6366f9..237740cf9e6 100644 --- a/tests/unit/test_cost_calculator.py +++ b/tests/unit/test_cost_calculator.py @@ -9,6 +9,7 @@ from pydantic import BaseModel import litellm from litellm.cost_calculator import ( + batch_cost_calculator, BaseTokenUsageProcessor, RealtimeAPITokenUsageProcessor, ResponsesWebSocketTokenUsageProcessor, @@ -3220,6 +3221,29 @@ def _batch_cache_usage() -> Usage: ) +def test_batch_cost_calculator_vertex_regional_costs_uplift_over_global(monkeypatch: pytest.MonkeyPatch) -> None: + """ + Regression for https://github.com/BerriAI/litellm/issues/46880: a Vertex batch + on a regional location must cost the global batch times the model's + regional_endpoint_uplift_multiplier, the same invariant the online path keeps. + """ + monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") + monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url="")) + + usage = Usage(prompt_tokens=1_000_000, completion_tokens=1_000_000, total_tokens=2_000_000) + global_prompt, global_completion = batch_cost_calculator( + usage=usage, model="gemini-3.5-flash", custom_llm_provider="vertex_ai", vertex_location="global" + ) + regional_prompt, regional_completion = batch_cost_calculator( + usage=usage, model="gemini-3.5-flash", custom_llm_provider="vertex_ai", vertex_location="us-central1" + ) + + uplift = litellm.get_model_info("vertex_ai/gemini-3.5-flash")["regional_endpoint_uplift_multiplier"] + assert global_prompt + global_completion > 0 + assert regional_prompt == pytest.approx(global_prompt * uplift, rel=1e-9) + assert regional_completion == pytest.approx(global_completion * uplift, rel=1e-9) + + def test_batch_cost_calculator_prices_multimodal_tokens_at_modality_rates(): from litellm.cost_calculator import batch_cost_calculator From 3b9892eb1d45fa47707b7a88553c4befaa8a6a2e Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Mon, 19 Oct 2026 19:08:30 -0700 Subject: [PATCH 38/66] fix(proxy): price the estimated input tokens on a client-cancelled (499) request's spend row (#47436) * fix(proxy): price the estimated input tokens on a client-cancelled (499) request's spend row * fix(proxy): read the provider handoff before the proxy-only error handler stamps it so a pre-handoff 499 is not priced * fix(proxy): drop the pre-logging handoff read now that pre_call no longer stamps proxy-only failures --------- Backport of #47436 to stable/1.104.x Cherry-picked from 0e7c4908bb2269b43e6033ad1ea518cde2369348 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/proxy/utils.py | 22 +++++- tests/test_litellm/proxy/test_proxy_utils.py | 77 ++++++++++++++++++++ 2 files changed, 95 insertions(+), 4 deletions(-) diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py index eb4704a0fa8..ed733b3fc2b 100644 --- a/litellm/proxy/utils.py +++ b/litellm/proxy/utils.py @@ -52,6 +52,7 @@ from typing_extensions import ReadOnly, TypedDict from litellm import _custom_logger_compatible_callbacks_literal from litellm.constants import ( DEFAULT_MODEL_CREATED_AT_TIME, + LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED, LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL, MAX_TEAM_LIST_LIMIT, PROXY_REJECTED_BEFORE_ROUTING_KEY, @@ -947,8 +948,8 @@ def _failure_usage_to_lift( cost in model_call_details, so prefer it. Otherwise a request that was dispatched to a provider and failed without upstream usage gets an estimated input-side Usage. When the failure is one the provider bills - anyway (``provider_billed``: a read timeout, where the provider had the - prompt and kept working after LiteLLM hung up) that + anyway (``provider_billed``: a read timeout or a client disconnect, where + the provider had the prompt and kept working after LiteLLM hung up) that usage is priced at the model's input rate; any other post-dispatch failure stays at zero cost. The raw request body backfills the system prompt when the SDK bridges an endpoint (e.g. /v1/messages on a @@ -957,7 +958,11 @@ def _failure_usage_to_lift( recovered_usage: Final = model_call_details.get("combined_usage_object") if recovered_usage is not None: return recovered_usage, model_call_details.get("response_cost") - if not dispatched or model_call_details.get(LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL): + if not dispatched: + return None + if model_call_details.get(LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL) and not provider_billed: + # The proxy-only error handler stamps this flag on a client disconnect too, even though the + # request had already reached the provider, so a billed failure keeps its estimate. return None if str(model_call_details.get("call_type")) not in _INPUT_ESTIMABLE_CALL_TYPES: return None @@ -1132,6 +1137,15 @@ def _timed_out_reading_from_provider(exception: Exception) -> bool: ) +def _client_disconnected(exception: Exception) -> bool: + """The 499 the proxy raises when the caller hung up while the provider was still working on the request.""" + return getattr(exception, "status_code", None) == LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED + + +def _provider_billed_the_failure(exception: Exception) -> bool: + return _timed_out_reading_from_provider(exception) or _client_disconnected(exception) + + def _failure_fields_to_lift(request_data: Mapping[str, object], provider_billed: bool = False) -> Mapping[str, object]: """Failure-path callbacks run after ``litellm_logging_obj`` is popped from request_data (it is not serialisable), so the caller merges these fields @@ -3302,7 +3316,7 @@ class ProxyLogging: request_data.update( await offload_token_count(_failure_fields_to_lift)( - request_data, provider_billed=_timed_out_reading_from_provider(original_exception) + request_data, provider_billed=_provider_billed_the_failure(original_exception) ) ) diff --git a/tests/test_litellm/proxy/test_proxy_utils.py b/tests/test_litellm/proxy/test_proxy_utils.py index 7a85dedf813..7079d406a06 100644 --- a/tests/test_litellm/proxy/test_proxy_utils.py +++ b/tests/test_litellm/proxy/test_proxy_utils.py @@ -794,6 +794,83 @@ class TestPostCallFailureHookEstimatesDispatchedInputTokens: assert expected_input_cost > 0 assert request_data["response_cost"] == pytest.approx(expected_input_cost) + @pytest.mark.asyncio + async def test_client_disconnect_after_dispatch_is_priced_at_input_rate(self): + from datetime import datetime + + from fastapi import HTTPException + + from litellm.constants import LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED, LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL + from litellm.types.utils import Usage + + request_data = { + "litellm_logging_obj": self._logging_obj( + { + "first_api_call_start_time": datetime.now(), + "model": "gpt-3.5-turbo", + "messages": [{"role": "user", "content": "count these input tokens please"}], + "call_type": "acompletion", + LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL: True, + } + ), + "metadata": {}, + } + await self._run( + request_data, + original_exception=HTTPException( + status_code=LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED, detail="Client disconnected the request" + ), + ) + + estimated = request_data["combined_usage_object"] + assert isinstance(estimated, Usage) + expected_input_cost, _ = litellm.cost_per_token(model="gpt-3.5-turbo", prompt_tokens=estimated.prompt_tokens) + assert expected_input_cost > 0 + assert request_data["response_cost"] == pytest.approx(expected_input_cost) + + @pytest.mark.asyncio + async def test_client_disconnect_before_provider_handoff_is_not_priced(self): + """A caller that hung up while the request was still in pre-call hooks never reached the + provider, so there is no handoff instant on the logging object and the 499 row is not priced.""" + from datetime import datetime + from unittest.mock import AsyncMock, patch + + from fastapi import HTTPException + + from litellm.constants import LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED + from litellm.litellm_core_utils.litellm_logging import Logging + from litellm.proxy._types import UserAPIKeyAuth + + logging_obj = Logging( + model="gpt-3.5-turbo", + messages=[{"role": "user", "content": "count these input tokens please"}], + stream=False, + call_type="acompletion", + start_time=datetime.now(), + litellm_call_id="lit145-pre-handoff", + function_id="lit145", + ) + assert logging_obj.model_call_details.get("first_api_call_start_time") is None + request_data = {"litellm_logging_obj": logging_obj, "model": "gpt-3.5-turbo", "metadata": {}} + + proxy_logging_obj = ProxyLogging(user_api_key_cache=DualCache()) + proxy_logging_obj.alert_types = [] + with ( + patch.object(proxy_logging_obj, "update_request_status", new=AsyncMock()), + patch.object(proxy_logging_obj, "_dispatch_proxy_only_failure_handlers", new=AsyncMock()), + ): + await proxy_logging_obj.post_call_failure_hook( + request_data=request_data, + original_exception=HTTPException( + status_code=LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED, detail="Client disconnected the request" + ), + user_api_key_dict=UserAPIKeyAuth(request_route="/v1/chat/completions"), + ) + + assert request_data.get("first_api_call_start_time") is None + assert "combined_usage_object" not in request_data + assert request_data.get("response_cost", 0.0) == 0.0 + @pytest.mark.asyncio async def test_connect_timeout_never_reached_the_provider_stays_zero_cost(self): from datetime import datetime From e71d121736c7e1312d1495fc4e9476ec8f3203db Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Mon, 19 Oct 2026 19:55:21 -0700 Subject: [PATCH 39/66] fix(proxy): price a billed failure row at the deployment's own rate like the success path (#47437) Backport of #47437 to stable/1.104.x Cherry-picked from fb555b00dc886c88d6986a1bd60415a81d9f875a (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/proxy/utils.py | 51 ++++++-- tests/test_litellm/proxy/test_proxy_utils.py | 121 +++++++++++++++++++ 2 files changed, 163 insertions(+), 9 deletions(-) diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py index ed733b3fc2b..4f1dfffa75d 100644 --- a/litellm/proxy/utils.py +++ b/litellm/proxy/utils.py @@ -82,7 +82,7 @@ from litellm.proxy.common_utils.openai_error_payload import ( from litellm.proxy.spend_tracking.spend_log_error_logger import spend_log_error from litellm.types.guardrails import GuardrailEventHooks from litellm.types.proxy.model_listing import ModelInfoResponse -from litellm.types.utils import CallTypes, CallTypesLiteral, ModelInfo, Usage +from litellm.types.utils import CallTypes, CallTypesLiteral, CostPerToken, ModelInfo, Usage try: from litellm_enterprise.enterprise_callbacks.send_emails.base_email import ( @@ -145,7 +145,7 @@ from litellm.litellm_core_utils.core_helpers import ( independent_snapshot, is_expected_client_error, ) -from litellm.litellm_core_utils.litellm_logging import Logging +from litellm.litellm_core_utils.litellm_logging import Logging, deployment_pricing_model_info from litellm.litellm_core_utils.safe_json_dumps import safe_dumps from litellm.litellm_core_utils.safe_json_loads import safe_json_loads from litellm.litellm_core_utils.served_output_texts import ( @@ -250,6 +250,7 @@ from litellm.types.proxy.policy_engine.pipeline_types import PipelineExecutionRe from litellm.types.utils import LLMResponseTypes, LoggedLiteLLMParams from litellm.utils import ( _add_custom_logger_callback_to_specific_event, # pyright: ignore[reportPrivateUsage] # only string-to-logger helper + _get_base_model_from_metadata, # pyright: ignore[reportPrivateUsage] # main exposes it as get_base_model_from_metadata ) if TYPE_CHECKING: @@ -942,6 +943,8 @@ def _failure_usage_to_lift( request_body: Mapping[str, object], dispatched: bool, provider_billed: bool = False, + deployment_id: str | None = None, + base_model: str | None = None, ) -> tuple[object, object] | None: """A stream that broke mid-flight still billed the provider for the chunks already delivered; the streaming handler stashes that recovered usage and @@ -950,8 +953,11 @@ def _failure_usage_to_lift( estimated input-side Usage. When the failure is one the provider bills anyway (``provider_billed``: a read timeout or a client disconnect, where the provider had the prompt and kept working after LiteLLM hung up) that - usage is priced at the model's input rate; any other post-dispatch failure - stays at zero cost. The raw request body backfills + usage is priced at the model's input rate, the way the success path prices it: + at the rate the router registered under ``deployment_id`` (``Logging.get_router_model_id``) + when the deployment declares one, else the cost map's rate for ``base_model`` (an Azure + deployment's ``model_info.base_model``) or the deployment model; any other post-dispatch + failure stays at zero cost. The raw request body backfills the system prompt when the SDK bridges an endpoint (e.g. /v1/messages on a chat-completions provider) without filling optional_params. Returns the (combined_usage_object, response_cost) pair to lift, or None.""" @@ -982,18 +988,43 @@ def _failure_usage_to_lift( return None if not provider_billed: return estimated_usage, 0.0 - return estimated_usage, _estimated_input_cost(model_call_details, estimated_usage.prompt_tokens) + return estimated_usage, _estimated_input_cost( + model_call_details, estimated_usage.prompt_tokens, deployment_id=deployment_id, base_model=base_model + ) -def _estimated_input_cost(model_call_details: Mapping[str, object], prompt_tokens: int) -> float: - """Input price for the estimated prompt at the cost map's rate; an unmapped model keeps the - row at $0 rather than dropping the failure row.""" +def _deployment_cost_per_token(deployment_id: str | None, model: str) -> CostPerToken | None: + """The pricing the router registered for this deployment under its ``model_info.id``, read + through ``deployment_pricing_model_info`` exactly as the success path does; None means the + public cost map. The id is ``Logging.get_router_model_id()`` (the logging object's own + ``litellm_params``), never the flattened ``model_call_details`` copy a request body key can + overwrite.""" + model_info: Final = deployment_pricing_model_info(model_id=deployment_id, deployment_model=model) + if model_info is None: + return None + return CostPerToken( + input_cost_per_token=model_info["input_cost_per_token"] or 0.0, + output_cost_per_token=model_info["output_cost_per_token"] or 0.0, + ) + + +def _estimated_input_cost( + model_call_details: Mapping[str, object], + prompt_tokens: int, + deployment_id: str | None, + base_model: str | None, +) -> float: + """Input price for the estimated prompt: the deployment's registered rate when it has one, else + the cost map's rate for ``base_model`` or the deployment model (an Azure deployment name is not + in the cost map, its ``base_model`` is). An unpriceable model keeps the row at $0 rather than + dropping the failure row.""" try: model: Final = str(model_call_details.get("model") or "") estimated_input_cost, _ = litellm.cost_per_token( - model=model, + model=base_model or model, custom_llm_provider=str(model_call_details.get("custom_llm_provider") or "") or None, prompt_tokens=prompt_tokens, + custom_cost_per_token=_deployment_cost_per_token(deployment_id, model), ) except Exception as exc: # noqa: BLE001 # cost_per_token raises BadRequestError for an unmapped model and the row must still be written verbose_proxy_logger.debug( @@ -1163,6 +1194,8 @@ def _failure_fields_to_lift(request_data: Mapping[str, object], provider_billed: request_body=request_data, dispatched=_first_handoff is not None, provider_billed=provider_billed, + deployment_id=_logging_obj.get_router_model_id() if isinstance(_logging_obj, Logging) else None, + base_model=_get_base_model_from_metadata(model_call_details=_model_call_details), ) _entries: Final = ( ("start_time", _model_call_details.get("start_time")), diff --git a/tests/test_litellm/proxy/test_proxy_utils.py b/tests/test_litellm/proxy/test_proxy_utils.py index 7079d406a06..017dd7beeef 100644 --- a/tests/test_litellm/proxy/test_proxy_utils.py +++ b/tests/test_litellm/proxy/test_proxy_utils.py @@ -2105,6 +2105,127 @@ def test_a_timed_out_request_on_an_unmapped_model_keeps_its_row_at_zero_cost(): assert response_cost == 0.0 +def test_a_timed_out_request_is_priced_at_the_rate_the_router_registered_for_the_deployment(monkeypatch): + """Router._create_deployment registers a deployment's own ``input_cost_per_token`` under its + ``model_info.id``; the failure row prices with that entry through the same + ``deployment_pricing_model_info`` the success path uses.""" + from litellm.proxy.utils import _failure_usage_to_lift + + monkeypatch.setitem( + litellm.model_cost, + "dep-lit145", + {"litellm_provider": "openai", "mode": "chat", "input_cost_per_token": 0.25, "output_cost_per_token": 1.0}, + ) + + lifted = _failure_usage_to_lift( + model_call_details={ + "call_type": "acompletion", + "model": FAILURE_USAGE_MODEL, + "messages": ONE_USER_MESSAGE, + }, + request_body={}, + dispatched=True, + provider_billed=True, + deployment_id="dep-lit145", + ) + + assert lifted is not None + usage, response_cost = lifted + assert usage.prompt_tokens > 0 + assert response_cost == pytest.approx(usage.prompt_tokens * 0.25) + + +def _dispatched_failure_logging_obj(model: str, litellm_params: dict) -> object: + """A Logging object as the failure hook sees it: litellm_params in the real get_litellm_params() + shape (every key present, ``litellm_metadata`` None on chat completions) and a first-handoff + instant, so the lift treats the request as dispatched.""" + from litellm.litellm_core_utils.litellm_logging import Logging + + logging_obj = Logging( + model=model, + messages=ONE_USER_MESSAGE, + stream=False, + call_type="acompletion", + start_time=real_datetime.datetime.now(), + litellm_call_id="call-lit145", + function_id="fn-lit145", + ) + logging_obj.update_environment_variables(model=model, user="", optional_params={}, litellm_params=litellm_params) + logging_obj.model_call_details["first_api_call_start_time"] = real_datetime.datetime.now() + logging_obj.model_call_details["messages"] = ONE_USER_MESSAGE + logging_obj.model_call_details["call_type"] = "acompletion" + return logging_obj + + +def test_the_deployment_rate_is_found_on_the_logging_objects_real_litellm_params(monkeypatch): + """``get_litellm_params()`` always carries a ``litellm_metadata`` key (None on chat + completions) next to the router-stamped ``metadata.model_info.id``; the failure row must + still price at the deployment's own rate, like ``Logging.get_router_model_id`` on the + success path.""" + from litellm.litellm_core_utils.get_litellm_params import get_litellm_params + from litellm.proxy.utils import _failure_fields_to_lift + + monkeypatch.setitem( + litellm.model_cost, + "dep-lit145-real-shape", + {"litellm_provider": "openai", "mode": "chat", "input_cost_per_token": 0.25, "output_cost_per_token": 0.25}, + ) + litellm_params = get_litellm_params(metadata={"model_info": {"id": "dep-lit145-real-shape"}}) + assert "litellm_metadata" in litellm_params and litellm_params["litellm_metadata"] is None + logging_obj = _dispatched_failure_logging_obj(FAILURE_USAGE_MODEL, litellm_params) + + lifted = _failure_fields_to_lift({"litellm_logging_obj": logging_obj}, provider_billed=True) + + assert lifted["response_cost"] == pytest.approx(lifted["combined_usage_object"].prompt_tokens * 0.25) + + +def test_an_azure_deployment_is_priced_at_its_base_model_like_the_success_path(): + """An Azure deployment name is not in the cost map; the success path prices it through + ``model_info.base_model`` (``get_base_model_from_metadata``) and so must the failure row.""" + from litellm.litellm_core_utils.get_litellm_params import get_litellm_params + from litellm.proxy.utils import _failure_fields_to_lift + + logging_obj = _dispatched_failure_logging_obj( + "azure/lit145-not-in-cost-map", + get_litellm_params(metadata={"model_info": {"base_model": "azure/gpt-4.1"}}), + ) + logging_obj.model_call_details["custom_llm_provider"] = "azure" + + lifted = _failure_fields_to_lift({"litellm_logging_obj": logging_obj}, provider_billed=True) + + expected_cost, _ = litellm.cost_per_token( + model="azure/gpt-4.1", prompt_tokens=lifted["combined_usage_object"].prompt_tokens + ) + assert expected_cost > 0 + assert lifted["response_cost"] == pytest.approx(expected_cost) + + +def test_a_litellm_params_key_in_the_request_body_cannot_zero_the_timeout_price(): + """``model_call_details`` is flattened with the request's optional_params, so a body key + named ``litellm_params`` can land there; the deployment rate must come from the logging + object's own ``litellm_params`` instead.""" + from litellm.proxy.utils import _failure_usage_to_lift + + lifted = _failure_usage_to_lift( + model_call_details={ + "call_type": "acompletion", + "model": FAILURE_USAGE_MODEL, + "messages": ONE_USER_MESSAGE, + "litellm_params": {"input_cost_per_token": 0}, + }, + request_body={}, + dispatched=True, + provider_billed=True, + deployment_id=None, + ) + + assert lifted is not None + usage, response_cost = lifted + expected_cost, _ = litellm.cost_per_token(model=FAILURE_USAGE_MODEL, prompt_tokens=usage.prompt_tokens) + assert response_cost == pytest.approx(expected_cost) + assert response_cost > 0 + + def test_a_request_that_timed_out_at_a_provider_bills_its_input_at_the_input_rate(): from litellm.proxy.utils import _failure_usage_to_lift From b462563d140ab1a5e6bd2bdc92c911eebeb3c582 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 08:02:23 -0700 Subject: [PATCH 40/66] fix(logging): report the pay-as-you-go entry billing used on Azure PTU spillover (#47567) get_standard_logging_object_payload decided custom_pricing from litellm_params alone, so on an Azure PTU spillover response model_map_information kept the deployment's zeroed PTU entry while response_cost already used the standard model rate. Reuse the billing side LitellmLogging._custom_pricing_for so both read the same decision Backport of #47567 to stable/1.104.x Cherry-picked from 422252326153b3006ed17abe0c0549bf795c3526 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/litellm_core_utils/litellm_logging.py | 8 ++--- .../test_litellm_logging.py | 35 +++++++++++++++++++ 2 files changed, 39 insertions(+), 4 deletions(-) diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py index eba580561d3..63ec230b6f7 100644 --- a/litellm/litellm_core_utils/litellm_logging.py +++ b/litellm/litellm_core_utils/litellm_logging.py @@ -1882,7 +1882,7 @@ class Logging(LiteLLMLoggingBaseClass): router_model_id = self.get_router_model_id() ## RESPONSE COST ## - custom_pricing: Final = self._custom_pricing_for(priced_result) + custom_pricing: Final = self.custom_pricing_for(priced_result) prompt = self._prompt_for_cost_calculation() @@ -2021,7 +2021,7 @@ class Logging(LiteLLMLoggingBaseClass): model=model, completion_response=result, custom_llm_provider=custom_llm_provider, - custom_pricing=self._custom_pricing_for(result), + custom_pricing=self.custom_pricing_for(result), base_model=_get_base_model_from_metadata(model_call_details=self.model_call_details), router_model_id=router_model_id or self.get_router_model_id(), region_name=_resolve_mantle_region_for_cost( @@ -2046,7 +2046,7 @@ class Logging(LiteLLMLoggingBaseClass): usage=usage, ) - def _custom_pricing_for(self, result: object) -> bool: + def custom_pricing_for(self, result: object) -> bool: litellm_params: Final = getattr(self, "litellm_params", None) result_hidden_params: Final = getattr(result, "_hidden_params", None) or MappingProxyType({}) additional_headers: Final = ( @@ -6525,7 +6525,7 @@ def get_standard_logging_object_payload( # Fall back to the actual deployment model set by the router in metadata. if base_model is None: base_model = metadata.get("deployment") - custom_pricing: Final = use_custom_pricing_for_model(litellm_params=litellm_params) + custom_pricing: Final = logging_obj.custom_pricing_for(init_response_obj) raw_response_cost: Final = kwargs.get("response_cost") llm_response_cost: Final[float] = raw_response_cost or 0.0 guardrail_cost: Final = guardrail_information_cost(metadata.get("standard_logging_guardrail_information")) diff --git a/tests/unit/litellm_core_utils/test_litellm_logging.py b/tests/unit/litellm_core_utils/test_litellm_logging.py index c112a88177e..c6f624c26e6 100644 --- a/tests/unit/litellm_core_utils/test_litellm_logging.py +++ b/tests/unit/litellm_core_utils/test_litellm_logging.py @@ -27,6 +27,7 @@ from litellm.litellm_core_utils.litellm_logging import Logging as LitellmLogging from litellm.litellm_core_utils.litellm_logging import ( _extract_response_obj_and_hidden_params, _get_status_fields, + get_standard_logging_object_payload, set_callbacks, ) from litellm.llms.base_llm.ocr.transformation import OCRUsageInfo @@ -8510,6 +8511,40 @@ class TestAzurePTUSpilloverCost: finally: self._unregister_models() + def test_spillover_payload_reports_the_pay_as_you_go_entry_billing_used(self, monkeypatch) -> None: + self._register_models() + try: + obj = self._logging_obj(dict(self.PTU_MODEL_INFO), flag="True", litellm_rate=0.0, monkeypatch=monkeypatch) + response = self._response() + response._hidden_params["additional_headers"] = {"llm_provider-x-ms-is-spilled-over": "true"} + response_cost: Final = obj._response_cost_calculator(result=response) + + payload: Final = get_standard_logging_object_payload( + kwargs={ + "model": self.SERVED_MODEL, + "custom_llm_provider": "azure", + "litellm_params": obj.litellm_params, + "response_cost": response_cost, + }, + init_response_obj=response, + start_time=datetime.datetime.now(), + end_time=datetime.datetime.now(), + logging_obj=obj, + status="success", + ) + + assert response_cost == pytest.approx(self.EXPECTED_SPILL_COST) + assert payload is not None + model_map_value: Final = payload["model_map_information"]["model_map_value"] + assert model_map_value is not None + assert model_map_value["input_cost_per_token"] == litellm.model_cost[self.SERVED_MODEL]["input_cost_per_token"] + assert model_map_value["output_cost_per_token"] == litellm.model_cost[self.SERVED_MODEL]["output_cost_per_token"] + assert response_cost == pytest.approx( + 100 * model_map_value["input_cost_per_token"] + 50 * model_map_value["output_cost_per_token"] + ) + finally: + self._unregister_models() + def test_spillover_header_does_not_touch_non_ptu_custom_pricing(self, monkeypatch) -> None: self._register_models() custom_model_id: Final = "non-ptu-custom-router-model-id" From bd0b38b4aa3d1b94e2cf8e2256c6a467e8cae511 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 08:04:55 -0700 Subject: [PATCH 41/66] fix(litellm_proxy): forward tool_config cache_control_injection_points to the downstream proxy (#47570) PR #47394 withheld cache_control_injection_points from the OpenAI SDK extra_body for every provider on that path, which also covers litellm_proxy. The downstream LiteLLM proxy applies the point itself, so litellm_proxy keeps forwarding it while OpenAI and the other OpenAI-compatible providers still never receive it Backport of #47570 to stable/1.104.x Cherry-picked from 04e9ed4c52505b5a50840843bc8b367aa32d09eb (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/utils.py | 3 ++- tests/unit/test_utils.py | 15 +++++++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/litellm/utils.py b/litellm/utils.py index 0fe759cf0c8..ce686669bdd 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -5045,8 +5045,9 @@ def add_provider_specific_params_to_optional_params( # for openai, azure we should pass the extra/passed params within `extra_body` https://github.com/openai/openai-python/blob/ac33853ba10d13ac149b1fa3ca6dba7d613065c9/src/openai/resources/models.py#L46 if _should_drop_param(k="extra_body", additional_drop_params=additional_drop_params) is False: extra_body: Final = dict(passed_params.pop("extra_body", None) or {}) + withheld_params: Final = frozenset[str]() if custom_llm_provider == "litellm_proxy" else LITELLM_ONLY_PARAMS for k in passed_params: - if k not in openai_params and k not in LITELLM_ONLY_PARAMS and passed_params[k] is not None: + if k not in openai_params and k not in withheld_params and passed_params[k] is not None: extra_body[k] = passed_params[k] if not isinstance(optional_params.get("extra_body"), dict): optional_params["extra_body"] = {} diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py index fd254dc2c3f..fe1fe4879e5 100644 --- a/tests/unit/test_utils.py +++ b/tests/unit/test_utils.py @@ -6374,3 +6374,18 @@ def test_get_optional_params_keeps_a_tool_config_cache_point_out_of_the_openai_e assert optional_params["extra_body"] == {"kept": True} assert "cache_control_injection_points" not in optional_params + + +def test_get_optional_params_forwards_a_tool_config_cache_point_to_a_downstream_litellm_proxy(): + """A litellm_proxy deployment calls the downstream proxy through the OpenAI SDK, and that proxy + applies cache_control_injection_points itself, so the point must ride along in extra_body.""" + point: Final = {"location": "tool_config", "control": {"type": "ephemeral"}} + optional_params: Final[dict[str, object]] = litellm.utils.get_optional_params( + model="claude-sonnet-4-5", + custom_llm_provider="litellm_proxy", + tools=[{"type": "function", "function": {"name": "get_weather", "parameters": {"type": "object"}}}], + cache_control_injection_points=[point], + extra_body={"kept": True}, + ) + + assert optional_params["extra_body"] == {"kept": True, "cache_control_injection_points": [point]} From e2af1d25fe5245b2a0f3d02e5e8f71967f962a75 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 08:22:06 -0700 Subject: [PATCH 42/66] fix(decisions): log non-UTF-8 bytes as base64 so the request reaches validation and gets a 400 (#47564) Backport of #47564 to stable/1.104.x Cherry-picked from ce63f48ed2ee3a18b7860b72f292e90ebeb1a986 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/decisions/call.py | 2 +- tests/unit/decisions/test_call.py | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/litellm/decisions/call.py b/litellm/decisions/call.py index 1d75d6942f0..4299736bcff 100644 --- a/litellm/decisions/call.py +++ b/litellm/decisions/call.py @@ -160,7 +160,7 @@ def _jsonable_fallback(value: object) -> object: def _logged_request_message(caller_request: object) -> ChatCompletionUserMessage: caller_fields: Final = _LOGGED_FIELDS_ADAPTER.validate_python( - to_jsonable_python(caller_request, fallback=_jsonable_fallback) + to_jsonable_python(caller_request, fallback=_jsonable_fallback, bytes_mode="base64") ) sent_fields: Final = json.dumps( dict((name, value) for name, value in caller_fields.items() if value not in (None, [], {})) diff --git a/tests/unit/decisions/test_call.py b/tests/unit/decisions/test_call.py index 0aec79ceb09..138d9dba906 100644 --- a/tests/unit/decisions/test_call.py +++ b/tests/unit/decisions/test_call.py @@ -1,3 +1,4 @@ +import base64 import json from collections.abc import Mapping from datetime import datetime, timezone @@ -100,3 +101,20 @@ def test_decisions_request_is_logged_even_when_its_questions_fail_validation(): logged: Final = _logged_request(logging_obj) assert logged["questions"][0]["instructions"] == QUESTION_TEXT + + +def test_non_utf8_bytes_in_the_request_are_logged_and_rejected_with_a_400(): + logging_obj: Final = _logging_obj("adecisions") + raw_input: Final = b"\xff\xfe not utf-8" + + with pytest.raises(litellm.BadRequestError): + _prepare_decisions_call( + **CONNECTION, + decision_input=raw_input, + questions=[{"type": "predicate", "instructions": QUESTION_TEXT}], + kwargs={"litellm_logging_obj": logging_obj}, + ) + + logged: Final = _logged_request(logging_obj) + assert base64.urlsafe_b64decode(logged["input"]) == raw_input + assert logged["questions"][0]["instructions"] == QUESTION_TEXT From 23b420d513c81307b8a0f670c851335ec17f8833 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 09:08:11 -0700 Subject: [PATCH 43/66] feat(proxy): lift every earlier billed timed-out retry attempt onto the failed request (#47490) * feat(proxy): lift every earlier billed timed-out retry attempt onto the failed request _billed_earlier_attempts reads the router's previous_models records, keeps the Timeout ones other than the final attempt (matched on deployment_id plus attempted_retries, since the count restarts after a fallback hop and the fallback handler re-logs the exhausting attempt) and prices each at the deployment that served it. post_call_failure_hook lifts the tuple as billed_failed_attempts; nothing writes it yet. previous_models joins the router-reserved metadata fields so a client-planted record never reaches it * fix(proxy): price earlier timed-out attempts from the prompt estimate only The final row may lift a mid-stream recovered usage (prompt plus delivered chunks) or a failed_attempts_usage sum; earlier attempts never produced output, so they are priced from _estimated_prompt_usage, and when failed_attempts_usage already bills them into the final row none is lifted again --------- Backport of #47490 to stable/1.104.x Cherry-picked from 7a4a255d1d33cb6145546c65b69b444a5f136da2 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/proxy/litellm_pre_call_utils.py | 1 + litellm/proxy/utils.py | 153 ++++++++++++++++-- .../proxy/test_litellm_pre_call_utils.py | 2 + tests/test_litellm/proxy/test_proxy_utils.py | 109 +++++++++++++ 4 files changed, 253 insertions(+), 12 deletions(-) diff --git a/litellm/proxy/litellm_pre_call_utils.py b/litellm/proxy/litellm_pre_call_utils.py index 56f647d5acc..842824e7ec5 100644 --- a/litellm/proxy/litellm_pre_call_utils.py +++ b/litellm/proxy/litellm_pre_call_utils.py @@ -373,6 +373,7 @@ _ROUTER_RESERVED_METADATA_FIELDS: Final = frozenset( { "attempted_fallbacks", "original_model_group", + "previous_models", "request_retry_count", CLIENT_OUTPUT_CEILING_METADATA_KEY, ROUTER_USAGE_COUNTED_TOKENS_METADATA_KEY, diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py index 4f1dfffa75d..319fc53b5ba 100644 --- a/litellm/proxy/utils.py +++ b/litellm/proxy/utils.py @@ -957,9 +957,7 @@ def _failure_usage_to_lift( at the rate the router registered under ``deployment_id`` (``Logging.get_router_model_id``) when the deployment declares one, else the cost map's rate for ``base_model`` (an Azure deployment's ``model_info.base_model``) or the deployment model; any other post-dispatch - failure stays at zero cost. The raw request body backfills - the system prompt when the SDK bridges an endpoint (e.g. /v1/messages on a - chat-completions provider) without filling optional_params. Returns the + failure stays at zero cost. Returns the (combined_usage_object, response_cost) pair to lift, or None.""" recovered_usage: Final = model_call_details.get("combined_usage_object") if recovered_usage is not None: @@ -970,6 +968,22 @@ def _failure_usage_to_lift( # The proxy-only error handler stamps this flag on a client disconnect too, even though the # request had already reached the provider, so a billed failure keeps its estimate. return None + estimated_usage: Final = _estimated_prompt_usage(model_call_details, request_body) + if estimated_usage is None: + return None + if not provider_billed: + return estimated_usage, 0.0 + return estimated_usage, _estimated_input_cost( + model_call_details, estimated_usage.prompt_tokens, deployment_id=deployment_id, base_model=base_model + ) + + +def _estimated_prompt_usage( + model_call_details: Mapping[str, object], request_body: Mapping[str, object] +) -> Usage | None: + """The input-only Usage estimate for the prompt this request sent, or None when the call type has no + estimable input. The raw request body backfills the system prompt when the SDK bridges an endpoint + (e.g. /v1/messages on a chat-completions provider) without filling optional_params.""" if str(model_call_details.get("call_type")) not in _INPUT_ESTIMABLE_CALL_TYPES: return None optional_params: Final = model_call_details.get("optional_params") @@ -979,17 +993,118 @@ def _failure_usage_to_lift( else None ) system_input: Final = dispatched_system or request_body.get("system") or request_body.get("instructions") - estimated_usage: Final = _estimate_dispatched_failure_usage( + return _estimate_dispatched_failure_usage( model=str(model_call_details.get("model") or ""), request_input=model_call_details.get("messages"), system_input=system_input, ) - if estimated_usage is None: - return None - if not provider_billed: - return estimated_usage, 0.0 - return estimated_usage, _estimated_input_cost( - model_call_details, estimated_usage.prompt_tokens, deployment_id=deployment_id, base_model=base_model + + +@dataclass(frozen=True) +class BilledFailedAttempt: + """An earlier retry attempt the provider also billed, written as its own spend row.""" + + attempted_retries: int + deployment_id: str | None + usage: Usage + response_cost: float + + +_NO_RETRY_METADATA: Final[Mapping[str, object]] = MappingProxyType({}) + + +def _retry_metadata_bucket(litellm_params: Mapping[str, object] | None) -> Mapping[str, object]: + """The request metadata bucket the router writes retry state into, ``litellm_metadata`` when the + route carries one (/messages, /responses) and ``metadata`` otherwise, same order as the deployment id.""" + if litellm_params is None: + return _NO_RETRY_METADATA + for metadata_key in ("litellm_metadata", "metadata"): + metadata = litellm_params.get(metadata_key) + if isinstance(metadata, dict): + return cast("Mapping[str, object]", metadata) # cast-ok: untyped router dict, keys read with .get + return _NO_RETRY_METADATA + + +def _attempt_number(record: Mapping[str, object], index: int) -> int: + """The attempt a retry record describes: its own ``attempted_retries`` count, else its position.""" + recorded: Final = record.get("attempted_retries") + return recorded if isinstance(recorded, int) else index + + +def _retry_attempt_records(litellm_params: Mapping[str, object] | None) -> tuple[Mapping[str, object], ...]: + """The router's ``RetryAttemptRecord`` breadcrumbs, one per failed attempt, read from the same bucket.""" + if litellm_params is None: + return () + for metadata_key in ("litellm_metadata", "metadata"): + metadata = litellm_params.get(metadata_key) + if not isinstance(metadata, dict): + continue + records = cast("Mapping[str, object]", metadata).get("previous_models") # cast-ok: untyped router dict + if isinstance(records, (list, tuple)): + return tuple( + cast("Mapping[str, object]", record) # cast-ok: RetryAttemptRecord TypedDict, read with .get + for record in cast("Sequence[object]", records) # cast-ok: untyped router tuple + if isinstance(record, dict) + ) + return () + + +def _record_deployment_id(record: Mapping[str, object]) -> str | None: + deployment_id: Final = record.get("deployment_id") + return deployment_id if isinstance(deployment_id, str) else None + + +def _attempt_identity(record: Mapping[str, object]) -> tuple[str | None, int | None]: + """What tells one provider call from another across the request: the deployment that served it + and the retry count within its model group. Two records with the same identity describe the + same call (the fallback handler re-logs the attempt that exhausted the previous group).""" + attempted_retries: Final = record.get("attempted_retries") + return _record_deployment_id(record), attempted_retries if isinstance(attempted_retries, int) else None + + +def _timed_out_earlier_records( + litellm_params: Mapping[str, object] | None, final_identity: tuple[str | None, int | None] +) -> tuple[Mapping[str, object], ...]: + """The ``Timeout`` breadcrumbs for calls other than the final attempt, one per provider call.""" + by_identity: Final = { + _attempt_identity(record): record + for record in _retry_attempt_records(litellm_params) + if record.get("exception_type") == litellm.Timeout.__name__ + } + return tuple(record for identity, record in by_identity.items() if identity != final_identity) + + +def _billed_earlier_attempts( + model_call_details: Mapping[str, object], + litellm_params: Mapping[str, object] | None, + estimated_usage: Usage, + base_model: str | None, + deployment_id: str | None, +) -> tuple[BilledFailedAttempt, ...]: + """Every earlier retry attempt the provider also billed. The router records one + ``RetryAttemptRecord`` per failed attempt in ``metadata.previous_models``, the final attempt + included, which the failure row itself bills. The final attempt is the record with the + request's own deployment and retry count (``attempted_retries`` restarts at 0 after a fallback + hop, so the count alone cannot tell the groups apart). An earlier attempt that ended in a + ``Timeout`` had the same prompt accepted by its deployment, so it is billed like the final + attempt, at that deployment's input rate (else the cost map's rate for ``base_model`` or the + model). Only the exception class survives on the record, so an earlier connect timeout is + billed too; any other failure class is not.""" + final_attempt: Final = _retry_metadata_bucket(litellm_params).get("attempted_retries") + final_identity: Final = (deployment_id, final_attempt if isinstance(final_attempt, int) else None) + return tuple( + BilledFailedAttempt( + attempted_retries=_attempt_number(record, index), + deployment_id=_record_deployment_id(record), + usage=estimated_usage, + response_cost=_estimated_input_cost( + model_call_details, + estimated_usage.prompt_tokens, + deployment_id=_record_deployment_id(record), + base_model=base_model, + ), + ) + for index, record in enumerate(_timed_out_earlier_records(litellm_params, final_identity)) ) @@ -1189,13 +1304,26 @@ def _failure_fields_to_lift(request_data: Mapping[str, object], provider_billed: return _EMPTY_LIFT _model_call_details: Final = getattr(_logging_obj, "model_call_details", {}) _first_handoff: Final = _model_call_details.get("first_api_call_start_time") + _litellm_params: Final = getattr(_logging_obj, "litellm_params", None) + _base_model: Final = _get_base_model_from_metadata(model_call_details=_model_call_details) + _deployment_id: Final = _logging_obj.get_router_model_id() if isinstance(_logging_obj, Logging) else None _usage_to_lift: Final = _failure_usage_to_lift( model_call_details=_model_call_details, request_body=request_data, dispatched=_first_handoff is not None, provider_billed=provider_billed, - deployment_id=_logging_obj.get_router_model_id() if isinstance(_logging_obj, Logging) else None, - base_model=_get_base_model_from_metadata(model_call_details=_model_call_details), + deployment_id=_deployment_id, + base_model=_base_model, + ) + _prompt_estimate: Final = ( + _estimated_prompt_usage(_model_call_details, request_data) + if provider_billed and _first_handoff is not None and not _model_call_details.get("failed_attempts_usage") + else None + ) + _earlier_attempts: Final = ( + _billed_earlier_attempts(_model_call_details, _litellm_params, _prompt_estimate, _base_model, _deployment_id) + if _prompt_estimate is not None + else () ) _entries: Final = ( ("start_time", _model_call_details.get("start_time")), @@ -1204,6 +1332,7 @@ def _failure_fields_to_lift(request_data: Mapping[str, object], provider_billed: ("combined_usage_object", None if _usage_to_lift is None else _usage_to_lift[0]), ("response_cost", None if _usage_to_lift is None else (_usage_to_lift[1] or 0.0)), ("standard_logging_object", _model_call_details.get("standard_logging_object")), + ("billed_failed_attempts", _earlier_attempts or None), ) return MappingProxyType({key: value for key, value in _entries if value is not None}) diff --git a/tests/test_litellm/proxy/test_litellm_pre_call_utils.py b/tests/test_litellm/proxy/test_litellm_pre_call_utils.py index ee42042bb8e..457409bdf6a 100644 --- a/tests/test_litellm/proxy/test_litellm_pre_call_utils.py +++ b/tests/test_litellm/proxy/test_litellm_pre_call_utils.py @@ -7764,6 +7764,7 @@ _PLANTED_STAMPS = { "attempted_fallbacks": 99, "original_model_group": "spoofed-group", "request_retry_count": -100, + "previous_models": [{"exception_type": "Timeout", "deployment_id": "spoofed", "attempted_retries": 101}], "_client_output_ceiling": {"api_base": "https://attacker.example"}, ROUTER_USAGE_COUNTED_TOKENS_METADATA_KEY: 10**9, "client_key": "client_value", @@ -7798,6 +7799,7 @@ async def test_add_litellm_data_to_request_strips_router_reserved_stamps_from_bo assert "original_model_group" not in updated["metadata"] assert "_client_output_ceiling" not in updated["metadata"] assert "request_retry_count" not in updated["metadata"] + assert "previous_models" not in updated["metadata"] assert ROUTER_USAGE_COUNTED_TOKENS_METADATA_KEY not in updated["metadata"] assert updated["metadata"]["client_key"] == "client_value" diff --git a/tests/test_litellm/proxy/test_proxy_utils.py b/tests/test_litellm/proxy/test_proxy_utils.py index 017dd7beeef..6e4a4c6e4b1 100644 --- a/tests/test_litellm/proxy/test_proxy_utils.py +++ b/tests/test_litellm/proxy/test_proxy_utils.py @@ -2135,6 +2135,115 @@ def test_a_timed_out_request_is_priced_at_the_rate_the_router_registered_for_the assert response_cost == pytest.approx(usage.prompt_tokens * 0.25) +def test_every_earlier_timed_out_attempt_is_billed_at_its_own_deployment_rate(monkeypatch): + """The router leaves one RetryAttemptRecord per failed attempt in metadata.previous_models, the + final attempt included; the earlier Timeout ones are billed (each at the deployment that served + it), a 429 attempt is not, and the final attempt is left to the failure row itself.""" + from litellm.proxy.utils import _billed_earlier_attempts + + monkeypatch.setitem( + litellm.model_cost, + "dep-lit145-b", + {"litellm_provider": "openai", "mode": "chat", "input_cost_per_token": 0.25, "output_cost_per_token": 1.0}, + ) + usage = litellm.Usage(prompt_tokens=24, completion_tokens=0, total_tokens=24) + public_rate, _ = litellm.cost_per_token(model=FAILURE_USAGE_MODEL, prompt_tokens=24) + + attempts = _billed_earlier_attempts( + model_call_details={"model": FAILURE_USAGE_MODEL, "custom_llm_provider": "openai"}, + litellm_params={ + "metadata": { + "attempted_retries": 3, + "previous_models": ( + {"deployment_id": "dep-lit145-a", "exception_type": "Timeout", "attempted_retries": 0}, + {"deployment_id": "dep-lit145-b", "exception_type": "RateLimitError", "attempted_retries": 1}, + {"deployment_id": "dep-lit145-b", "exception_type": "Timeout", "attempted_retries": 2}, + {"deployment_id": "dep-lit145-a", "exception_type": "Timeout", "attempted_retries": 3}, + ), + } + }, + estimated_usage=usage, + base_model=None, + deployment_id="dep-lit145-a", + ) + + assert [(a.attempted_retries, a.deployment_id) for a in attempts] == [(0, "dep-lit145-a"), (2, "dep-lit145-b")] + assert attempts[0].response_cost == pytest.approx(public_rate) + assert attempts[0].response_cost > 0 + assert attempts[1].response_cost == pytest.approx(24 * 0.25) + assert all(a.usage is usage for a in attempts) + + +def test_earlier_attempts_are_priced_from_the_prompt_estimate_not_the_final_streams_recovered_usage(): + """A final attempt whose stream broke mid-flight lifts its recovered usage (prompt plus the chunks + delivered); the earlier timed-out attempts never produced output, so they are priced from the + input-only estimate and not from that recovered usage.""" + from litellm.litellm_core_utils.get_litellm_params import get_litellm_params + from litellm.proxy.utils import _estimated_prompt_usage, _failure_fields_to_lift + + logging_obj = _dispatched_failure_logging_obj( + FAILURE_USAGE_MODEL, + get_litellm_params( + metadata={ + "attempted_retries": 1, + "model_info": {"id": "dep-lit145-final"}, + "previous_models": ( + {"deployment_id": "dep-lit145-final", "exception_type": "Timeout", "attempted_retries": 0}, + ), + } + ), + ) + recovered = litellm.Usage(prompt_tokens=500, completion_tokens=40, total_tokens=540) + logging_obj.model_call_details["combined_usage_object"] = recovered + logging_obj.model_call_details["response_cost"] = 0.01 + + lifted = _failure_fields_to_lift({"litellm_logging_obj": logging_obj}, provider_billed=True) + + estimate = _estimated_prompt_usage(logging_obj.model_call_details, {}) + assert lifted["combined_usage_object"] is recovered + assert [(a.usage.prompt_tokens, a.usage.completion_tokens) for a in lifted["billed_failed_attempts"]] == [ + (estimate.prompt_tokens, 0) + ] + assert estimate.prompt_tokens < recovered.prompt_tokens + + +def test_a_timed_out_attempt_from_the_group_a_fallback_left_is_still_billed(): + """After a fallback hop the router restarts ``attempted_retries`` at 0 for the new model group and + re-logs the attempt that exhausted the previous group, so the final attempt (dep-b, retry 1) must be + told from the previous group's attempt with the same count (dep-a, retry 1), and the re-logged + record must bill once.""" + from litellm.proxy.utils import _billed_earlier_attempts + + usage = litellm.Usage(prompt_tokens=24, completion_tokens=0, total_tokens=24) + + attempts = _billed_earlier_attempts( + model_call_details={"model": FAILURE_USAGE_MODEL, "custom_llm_provider": "openai"}, + litellm_params={ + "metadata": { + "attempted_retries": 1, + "model_info": {"id": "dep-lit145-b"}, + "previous_models": ( + {"deployment_id": "dep-lit145-a", "exception_type": "Timeout", "attempted_retries": 0}, + {"deployment_id": "dep-lit145-a", "exception_type": "Timeout", "attempted_retries": 1}, + {"deployment_id": "dep-lit145-a", "exception_type": "Timeout", "attempted_retries": 1}, + {"deployment_id": "dep-lit145-b", "exception_type": "Timeout", "attempted_retries": 0}, + {"deployment_id": "dep-lit145-b", "exception_type": "Timeout", "attempted_retries": 1}, + ), + } + }, + estimated_usage=usage, + base_model=None, + deployment_id="dep-lit145-b", + ) + + assert [(a.attempted_retries, a.deployment_id) for a in attempts] == [ + (0, "dep-lit145-a"), + (1, "dep-lit145-a"), + (0, "dep-lit145-b"), + ] + assert all(a.response_cost > 0 for a in attempts) + + def _dispatched_failure_logging_obj(model: str, litellm_params: dict) -> object: """A Logging object as the failure hook sees it: litellm_params in the real get_litellm_params() shape (every key present, ``litellm_metadata`` None on chat completions) and a first-handoff From 23902fea6a3cc2c9515b01e65eaba0a75f1b2499 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 09:08:18 -0700 Subject: [PATCH 44/66] fix(proxy): requeue spend logs when a Postgres restart tears down the prisma engine mid-write (#47571) Backport of #47571 to stable/1.104.x Cherry-picked from ccd0d4ea493d1c5f9c2f6574261002407687663d (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/proxy/utils.py | 6 ++- .../test_proxy_update_spend.py | 50 +++++++++++++++++++ 2 files changed, 55 insertions(+), 1 deletion(-) diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py index 319fc53b5ba..b9c9bc30661 100644 --- a/litellm/proxy/utils.py +++ b/litellm/proxy/utils.py @@ -8018,7 +8018,11 @@ MAX_SPEND_LOG_ISOLATION_FAILURES_PER_BATCH: Final = 256 def _is_transient_spend_log_write_error(e: Exception) -> bool: - return PrismaDBExceptionHandler.is_database_transport_error(e) or PrismaDBExceptionHandler.is_deadlock_error(e) + return ( + PrismaDBExceptionHandler.is_database_transport_error(e) + or PrismaDBExceptionHandler.is_prisma_engine_internal_error(e) + or PrismaDBExceptionHandler.is_deadlock_error(e) + ) async def _create_spend_logs_with_poison_isolation( diff --git a/tests/test_litellm/proxy/utils/prisma_and_spend/test_proxy_update_spend.py b/tests/test_litellm/proxy/utils/prisma_and_spend/test_proxy_update_spend.py index 7099101db1c..eab52af51fb 100644 --- a/tests/test_litellm/proxy/utils/prisma_and_spend/test_proxy_update_spend.py +++ b/tests/test_litellm/proxy/utils/prisma_and_spend/test_proxy_update_spend.py @@ -917,3 +917,53 @@ async def test_update_spend_logs_parks_failed_batch_in_redis_with_wire_safe_date parked = await buffer.get_spend_logs_from_redis_buffer(limit=10) assert mock_prisma_client.spend_log_transactions == [] assert [(row["request_id"], row["startTime"]) for row in parked] == [("a", started.isoformat())] + + +async def _create_many_while_postgres_is_restarting(**_: object) -> int: + from prisma.engine.utils import handle_response_errors + + handle_response_errors( + MagicMock(), + [ + { + "error": "Error in connector: Can't reach database server at `127.0.0.1:5432`", + "user_facing_error": {"error_code": "P1001", "message": "Can't reach database server", "meta": None}, + } + ], + ) + return 0 + + +@pytest.mark.asyncio +async def test_update_spend_logs_retries_and_requeues_batch_when_postgres_restart_tears_down_prisma_engine( + mock_prisma_client: Any, make_spend_log_row: Any, monkeypatch: pytest.MonkeyPatch +) -> None: + """While Postgres restarts the prisma engine answers the write with a P1001 + payload whose ``meta`` is ``None``, which prisma's own response parser trips + over before it can build a typed error. That outage must be retried like + any other, and once retries exhaust the dequeued batch goes back to the head + of the queue so the rows land when Postgres is back. + """ + + async def _fake_sleep(_: float) -> None: + return None + + monkeypatch.setattr(utils_mod.asyncio, "sleep", _fake_sleep) + mock_prisma_client.db.litellm_spendlogs.create_many = AsyncMock( + side_effect=_create_many_while_postgres_is_restarting + ) + proxy_logging = MagicMock() + proxy_logging.failure_handler = AsyncMock() + mock_prisma_client.spend_log_transactions = [make_spend_log_row(request_id="c")] + + with pytest.raises(AttributeError): + await ProxyUpdateSpend.update_spend_logs( + n_retry_times=2, + prisma_client=mock_prisma_client, + db_writer_client=None, + proxy_logging_obj=proxy_logging, + logs_to_process=[make_spend_log_row(request_id="a"), make_spend_log_row(request_id="b")], + ) + + assert [row["request_id"] for row in mock_prisma_client.spend_log_transactions] == ["a", "b", "c"] + assert mock_prisma_client.db.litellm_spendlogs.create_many.await_count == 3 From 223690801ce1ae2a728879459a8dce9db2ae42a2 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 10:39:29 -0700 Subject: [PATCH 45/66] feat(proxy): write one spend row per billed timed-out retry attempt (#47416) _failure_spend_rows yields the final row plus one re-keyed row per lifted billed_failed_attempts entry (-attempt-, the attempt's usage, cost, retry count and deployment id), each written through DBSpendUpdateWriter.update_database so it also deducts from key, team and user spend Backport of #47416 to stable/1.104.x Cherry-picked from ad8ca533ca2cd5fa4360d519183c1a2aaccc084a (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../proxy/hooks/proxy_track_cost_callback.py | 111 ++++++++++++++++-- .../hooks/test_proxy_track_cost_callback.py | 61 ++++++++++ 2 files changed, 160 insertions(+), 12 deletions(-) diff --git a/litellm/proxy/hooks/proxy_track_cost_callback.py b/litellm/proxy/hooks/proxy_track_cost_callback.py index e097debde77..c374e47eb09 100644 --- a/litellm/proxy/hooks/proxy_track_cost_callback.py +++ b/litellm/proxy/hooks/proxy_track_cost_callback.py @@ -49,7 +49,7 @@ from litellm.proxy.spend_tracking.spend_tracking_utils import ( get_request_model_access_groups, should_store_prompts_and_responses_in_spend_logs, ) -from litellm.proxy.utils import ProxyUpdateSpend +from litellm.proxy.utils import BilledFailedAttempt, ProxyUpdateSpend from litellm.types.utils import ( CallTypes, LiteLLMBatch, @@ -91,6 +91,73 @@ def _proxy_spend_writer() -> DBSpendUpdateWriter: return proxy_logging_obj.db_spend_update_writer +def _billed_failed_attempts(request_data: Mapping[str, object]) -> tuple[BilledFailedAttempt, ...]: + """The earlier billed attempts ``_failure_fields_to_lift`` stashed on the request, if any.""" + attempts: Final = request_data.get("billed_failed_attempts") + if not isinstance(attempts, tuple): + return () + lifted: Final = cast("tuple[object, ...]", attempts) # cast-ok: lifted by _failure_fields_to_lift, checked below + return tuple(attempt for attempt in lifted if isinstance(attempt, BilledFailedAttempt)) + + +def _failure_spend_rows( + request_data: Mapping[str, object], final_cost: float, late_guardrails_snapshot: object +) -> tuple[tuple[float, Mapping[str, object]], ...]: + """One ``(response_cost, kwargs)`` per spend row a failure writes: the final attempt under the + request id, then every earlier attempt the provider also billed under its own row.""" + final_row: Final[Mapping[str, object]] = ( + request_data + if late_guardrails_snapshot is None + else {**request_data, "standard_logging_object": late_guardrails_snapshot} + ) + return ( + (final_cost, final_row), + *( + (attempt.response_cost, _attempt_spend_row_kwargs(request_data, attempt, position)) + for position, attempt in enumerate(_billed_failed_attempts(request_data)) + ), + ) + + +def _attempt_spend_row_kwargs( + request_data: Mapping[str, object], attempt: BilledFailedAttempt, position: int +) -> Mapping[str, object]: + """The final attempt's row kwargs re-keyed for one earlier billed attempt: its own + ``request_id`` (``-attempt-``, since ``request_id`` is the spend-log primary key + and the retry count restarts after a fallback hop), its estimated usage and cost, its retry + count under ``attempted_retries`` and the deployment that billed it under ``model_info.id``.""" + suffix: Final = f"-attempt-{position}" + raw_params: Final = cast("Mapping[str, object]", request_data.get("litellm_params") or {}) # cast-ok: request dict + litellm_params: Final = dict(raw_params) + metadata: Final = { + **cast("Mapping[str, object]", litellm_params.get("metadata") or {}), # cast-ok: request dict + "attempted_retries": attempt.attempted_retries, + } + metadata.pop("previous_models", None) + if attempt.deployment_id is not None: + metadata["model_info"] = { + **cast("Mapping[str, object]", metadata.get("model_info") or {}), # cast-ok: router dict + "id": attempt.deployment_id, + } + litellm_params["metadata"] = metadata + row: Final = { + **request_data, + "litellm_params": litellm_params, + "combined_usage_object": attempt.usage, + "response_cost": attempt.response_cost, + } + row.pop("billed_failed_attempts", None) + call_id: Final = request_data.get("litellm_call_id") or litellm_params.get("litellm_call_id") + if isinstance(call_id, str): + row["litellm_call_id"] = f"{call_id}{suffix}" + standard_logging_object: Final = request_data.get("standard_logging_object") + if isinstance(standard_logging_object, dict): + payload: Final = cast("Mapping[str, object]", standard_logging_object) # cast-ok: StandardLoggingPayload dict + if isinstance(payload.get("id"), str): + row["standard_logging_object"] = {**payload, "id": f"{payload['id']}{suffix}"} + return row + + class _ProxyDBLogger(CustomLogger): def __init__( self, @@ -258,20 +325,40 @@ class _ProxyDBLogger(CustomLogger): existing_metadata.get("standard_logging_guardrail_information") ) - await self._spend_writer().update_database( - token=LiteLLMProxyRequestSetup.get_logged_api_key(user_api_key_dict), - response_cost=recovered_response_cost, - user_id=user_api_key_dict.user_id, - end_user_id=user_api_key_dict.end_user_id, - team_id=user_api_key_dict.team_id, - kwargs=request_data, - completion_response=original_exception, + await self._write_failure_spend_rows( + user_api_key_dict=user_api_key_dict, + original_exception=original_exception, start_time=actual_start_time, - end_time=datetime.now(), - org_id=user_api_key_dict.org_id, - project_id=user_api_key_dict.project_id, + spend_rows=_failure_spend_rows( + cast("Mapping[str, object]", request_data), # cast-ok: request dict, copied per row below + recovered_response_cost, + None, + ), ) + async def _write_failure_spend_rows( + self, + user_api_key_dict: UserAPIKeyAuth, + original_exception: Exception, + start_time: datetime, + spend_rows: Sequence[tuple[float, Mapping[str, object]]], + ) -> None: + """One spend row (and one key/team/user spend deduction) per ``(response_cost, kwargs)`` pair.""" + for row_cost, row_kwargs in spend_rows: + await self._spend_writer().update_database( + token=LiteLLMProxyRequestSetup.get_logged_api_key(user_api_key_dict), + response_cost=row_cost, + user_id=user_api_key_dict.user_id, + end_user_id=user_api_key_dict.end_user_id, + team_id=user_api_key_dict.team_id, + kwargs=dict(row_kwargs), + completion_response=original_exception, + start_time=start_time, + end_time=datetime.now(), + org_id=user_api_key_dict.org_id, + project_id=user_api_key_dict.project_id, + ) + @log_db_metrics async def _PROXY_track_cost_callback( self, diff --git a/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py b/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py index b5e594db701..55eefeaa4ed 100644 --- a/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py +++ b/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py @@ -8,6 +8,8 @@ from unittest.mock import AsyncMock, MagicMock, patch import httpx import pytest +import litellm + from litellm._logging import verbose_proxy_logger from litellm.litellm_core_utils.internal_call_metadata import MODEL_ACCESS_GROUP_METADATA_KEY from litellm.proxy._types import SpendLogsPayload, UserAPIKeyAuth @@ -93,6 +95,65 @@ async def test_async_post_call_failure_hook(): assert metadata["original_key"] == "original_value" +@pytest.mark.asyncio +async def test_each_earlier_billed_attempt_gets_its_own_spend_row(): + """A timed-out request that the router retried writes one row per billed attempt: the final + attempt under the request id, every earlier Timeout attempt under ``-attempt-`` with its + own cost, attempt number and deployment.""" + from litellm.proxy.utils import BilledFailedAttempt + + logger = _ProxyDBLogger() + user_api_key_dict = UserAPIKeyAuth(api_key="test_api_key", user_id="u1", team_id="t1") + usage = litellm.Usage(prompt_tokens=24, completion_tokens=0, total_tokens=24) + request_data = { + "model": "gpt-4.1", + "litellm_call_id": "call-1", + "standard_logging_object": {"id": "call-1", "model_id": "dep-final"}, + "metadata": { + "attempted_retries": 2, + "model_info": {"id": "dep-final", "input_cost_per_token": 0.5}, + "previous_models": ({"exception_type": "Timeout"}, {"exception_type": "Timeout"}), + }, + "combined_usage_object": usage, + "response_cost": 0.5, + "billed_failed_attempts": ( + BilledFailedAttempt(attempted_retries=0, deployment_id="dep-a", usage=usage, response_cost=0.25), + BilledFailedAttempt(attempted_retries=0, deployment_id="dep-final", usage=usage, response_cost=0.5), + ), + } + + with patch( + "litellm.proxy.db.db_spend_update_writer.DBSpendUpdateWriter.update_database", + new_callable=AsyncMock, + ) as mock_update_database: + await logger.async_post_call_failure_hook( + request_data=request_data, + original_exception=litellm.Timeout("Request timed out.", model="gpt-4.1", llm_provider="openai"), + user_api_key_dict=user_api_key_dict, + ) + + rows = [call.kwargs for call in mock_update_database.call_args_list] + assert [row["response_cost"] for row in rows] == [0.5, 0.25, 0.5] + final_row, attempt_0, attempt_1 = (row["kwargs"] for row in rows) + assert final_row["litellm_call_id"] == "call-1" + assert final_row["litellm_params"]["metadata"]["attempted_retries"] == 2 + assert attempt_0["litellm_call_id"] == "call-1-attempt-0" + assert attempt_0["standard_logging_object"]["id"] == "call-1-attempt-0" + assert attempt_0["litellm_params"]["metadata"]["attempted_retries"] == 0 + assert attempt_0["litellm_params"]["metadata"]["model_info"]["id"] == "dep-a" + assert "previous_models" not in attempt_0["litellm_params"]["metadata"] + assert "billed_failed_attempts" not in attempt_0 + assert attempt_0["combined_usage_object"] is usage + assert attempt_1["litellm_call_id"] == "call-1-attempt-1" + assert attempt_1["litellm_params"]["metadata"]["attempted_retries"] == 0 + assert attempt_1["litellm_params"]["metadata"]["model_info"]["id"] == "dep-final" + assert final_row["litellm_params"]["metadata"]["model_info"]["id"] == "dep-final" + for row in rows: + assert row["token"] == "test_api_key" + assert row["user_id"] == "u1" + assert row["team_id"] == "t1" + + @pytest.mark.asyncio async def test_async_post_call_failure_hook_carries_guardrail_info_from_litellm_metadata(): """ From de1e76bd13fa2e7bd36dbf77ee49a85655c1a6ad Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 10:50:26 -0700 Subject: [PATCH 46/66] feat(proxy): opt-in free-tier allowance for Google Search grounding spend (#47494) * feat(proxy): opt-in free-tier allowance for Google Search grounding spend * fix(proxy): declare the search free tier counter's service target * test(cost_map): allow search_free_requests in the cost map schema * fix(proxy): skip cache hits and never free more than the billed cost in the search free tier --------- Backport of #47494 to stable/1.104.x Cherry-picked from e63aec029a9111616d039712aec0df498bbfbd1b (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ci_cd/generate_model_prices_schema.py | 11 + litellm/__init__.py | 1 + litellm/constants.py | 1 + ...odel_prices_and_context_window_backup.json | 47 +++++ .../proxy/hooks/proxy_track_cost_callback.py | 27 ++- litellm/proxy/hooks/search_free_tier.py | 121 +++++++++++ litellm/types/utils.py | 7 + litellm/utils.py | 1 + model_prices_and_context_window.json | 47 +++++ model_prices_and_context_window.schema.json | 27 +++ .../hooks/test_proxy_track_cost_callback.py | 90 +++++++- .../unit/proxy/hooks/test_search_free_tier.py | 194 ++++++++++++++++++ tests/unit/test_model_prices_schema.py | 29 +++ tests/unit/test_utils.py | 10 + 14 files changed, 610 insertions(+), 3 deletions(-) create mode 100644 litellm/proxy/hooks/search_free_tier.py create mode 100644 tests/unit/proxy/hooks/test_search_free_tier.py diff --git a/ci_cd/generate_model_prices_schema.py b/ci_cd/generate_model_prices_schema.py index a5a4b7f6f3b..4ca09155d1b 100644 --- a/ci_cd/generate_model_prices_schema.py +++ b/ci_cd/generate_model_prices_schema.py @@ -91,6 +91,17 @@ OBJECT_KEYS: dict[str, JsonSchema] = { }, "additionalProperties": False, }, + "search_free_requests": { + "type": "object", + "description": "Free Google Search grounding requests per period, shared across models in the same shared_group.", + "required": ["count", "period", "shared_group"], + "additionalProperties": False, + "properties": { + "count": {"type": "integer", "minimum": 0}, + "period": {"type": "string", "enum": ["day", "month"]}, + "shared_group": {"type": "string", "pattern": "\\S"}, + }, + }, "guardrail_cost_per_unit": { "type": "object", "description": "USD cost per billable guardrail unit, keyed by the provider's usage counter name (e.g. Bedrock's contentPolicyUnits).", diff --git a/litellm/__init__.py b/litellm/__init__.py index 21f2f570157..5f483655caa 100644 --- a/litellm/__init__.py +++ b/litellm/__init__.py @@ -556,6 +556,7 @@ from litellm.litellm_core_utils.get_model_cost_map import get_model_cost_map, ma model_cost = get_model_cost_map(url=model_cost_map_url) cost_discount_config: Dict[str, float] = {} # Provider-specific cost discounts {"vertex_ai": 0.05} = 5% discount +apply_search_free_tier: bool = False cost_margin_config: Dict[ str, Union[float, Dict[str, float]] ] = {} # Provider-specific or global cost margins. Examples: diff --git a/litellm/constants.py b/litellm/constants.py index 3b14d99bfc3..4420fd73e77 100644 --- a/litellm/constants.py +++ b/litellm/constants.py @@ -1871,6 +1871,7 @@ LITELLM_SETTINGS_SAFE_DB_OVERRIDES: Final = [ "public_model_groups", "public_model_groups_links", "cost_discount_config", + "apply_search_free_tier", "cost_margin_config", "block_requests_for_models_without_pricing", "budget_exceeded_throttle_percentage", diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 9635cf3ce72..d0020004e19 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -26338,6 +26338,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 1.5e-07, @@ -26450,6 +26451,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3-pro-image-preview": { @@ -26501,6 +26503,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image": { @@ -26547,6 +26550,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image-preview": { @@ -26589,6 +26593,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-lite-image": { @@ -26679,6 +26684,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -26740,6 +26746,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -26799,6 +26806,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -26885,6 +26893,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-08, "input_cost_per_token_batches": 5e-08, @@ -26939,6 +26948,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -26985,6 +26995,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -27171,6 +27182,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, "input_cost_per_token_batches": 6.25e-07, @@ -27198,6 +27210,7 @@ "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_image": 0.00012, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27293,6 +27306,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -27349,6 +27363,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3-flash-preview": { @@ -27363,6 +27378,7 @@ "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 3e-06, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27460,6 +27476,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -27523,6 +27540,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -27582,6 +27600,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -27603,6 +27622,7 @@ "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "regional_endpoint_uplift_multiplier": 1.1, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27746,6 +27766,7 @@ "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_image": 0.00012, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27847,6 +27868,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -28174,6 +28196,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "supports_reasoning": false }, @@ -28218,6 +28241,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite-preview": { @@ -28279,6 +28303,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -28428,6 +28453,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 1.5e-07, @@ -28538,6 +28564,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "supports_reasoning": false }, @@ -28602,6 +28629,7 @@ "output_cost_per_token_batches": 1.5e-06, "rpm": 1000, "tpm": 4000000, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -28757,6 +28785,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 1.5e-07, "input_cost_per_token_batches": 5e-08, @@ -28960,6 +28989,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, @@ -29055,6 +29085,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -29115,6 +29146,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29171,6 +29203,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 5e-07, @@ -29234,6 +29267,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -29299,6 +29333,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29360,6 +29395,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29421,6 +29457,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29516,6 +29553,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, @@ -29579,6 +29617,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, @@ -29597,6 +29636,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -29726,6 +29766,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -29789,6 +29830,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29848,6 +29890,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29868,6 +29911,7 @@ "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -49878,6 +49922,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -49940,6 +49985,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -50000,6 +50046,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, diff --git a/litellm/proxy/hooks/proxy_track_cost_callback.py b/litellm/proxy/hooks/proxy_track_cost_callback.py index c374e47eb09..48eb8b9cf73 100644 --- a/litellm/proxy/hooks/proxy_track_cost_callback.py +++ b/litellm/proxy/hooks/proxy_track_cost_callback.py @@ -1,9 +1,12 @@ import asyncio import traceback from collections.abc import Callable, Mapping, Sequence -from datetime import datetime +from datetime import datetime, timezone +from types import MappingProxyType from typing import TYPE_CHECKING, Any, Final, Protocol, cast +from pydantic import TypeAdapter, ValidationError + import litellm from litellm._logging import verbose_proxy_logger from litellm.batches.batch_utils import batch_cost_is_final @@ -29,6 +32,7 @@ from litellm.proxy.db.db_spend_update_writer import ( debitable_model_access_groups, get_llm_router, ) +from litellm.proxy.hooks.search_free_tier import apply_search_free_tier from litellm.proxy.litellm_pre_call_utils import LiteLLMProxyRequestSetup from litellm.proxy.spend_tracking.spend_event import ( ObjectMapping, @@ -158,6 +162,12 @@ def _attempt_spend_row_kwargs( return row +def _str_keyed_fields(value: object) -> Mapping[str, object]: + if not isinstance(value, Mapping): + return {} + return cast("Mapping[str, object]", value) # cast-ok: payload dicts are str-keyed + + class _ProxyDBLogger(CustomLogger): def __init__( self, @@ -416,8 +426,21 @@ class _ProxyDBLogger(CustomLogger): key_alias: Final = cast(str | None, metadata.get("user_api_key_alias", None)) end_user_max_budget: Final = metadata.get("user_api_end_user_max_budget", None) sl_object: Final[StandardLoggingPayload | None] = kwargs.get("standard_logging_object", None) + raw_cost: Final = _str_keyed_fields( + sl_object if sl_object is not None else kwargs # pyright: ignore[reportUnknownArgumentType] # untyped success-callback payload + ).get("response_cost") + priced_cost: Final = raw_cost if isinstance(raw_cost, (int, float)) else None response_cost: Final = ( - sl_object.get("response_cost", None) if sl_object is not None else kwargs.get("response_cost", None) + await apply_search_free_tier( + kwargs=kwargs, # pyright: ignore[reportUnknownArgumentType] # untyped success-callback payload + sl_object=sl_object, # pyright: ignore[reportUnknownArgumentType] # payload carries untyped lists + response_cost=priced_cost, + completion_response=completion_response, + counter=proxy_logging_obj.internal_usage_cache.dual_cache.redis_cache, + now=datetime.now(timezone.utc), + ) + if litellm.apply_search_free_tier and sl_object is not None and priced_cost is not None + else priced_cost ) tags: Final = _get_request_tags_for_cost_tracking( sl_object=sl_object, diff --git a/litellm/proxy/hooks/search_free_tier.py b/litellm/proxy/hooks/search_free_tier.py new file mode 100644 index 00000000000..b9beb8599b3 --- /dev/null +++ b/litellm/proxy/hooks/search_free_tier.py @@ -0,0 +1,121 @@ +from collections.abc import MutableMapping +from datetime import datetime +from types import MappingProxyType +from typing import Final, Protocol + +from pydantic import BaseModel, ConfigDict, TypeAdapter, ValidationError + +from litellm._logging import verbose_proxy_logger +from litellm.litellm_core_utils.duration_parser import get_next_standardized_reset_time +from litellm.litellm_core_utils.llm_cost_calc.utils import get_web_search_requests_from_usage +from litellm.llms.gemini.cost_calculator import cost_per_web_search_request +from litellm.types.utils import CostBreakdown, ModelInfo, SearchFreeRequests, StandardLoggingPayload, Usage + +_PERIOD_DURATION: Final = MappingProxyType({"day": "1d", "month": "1mo"}) +_PERIOD_STAMP: Final = MappingProxyType({"day": "%Y-%m-%d", "month": "%Y-%m"}) +_TTL_GRACE_SECONDS: Final = 3600 +_COUNTED_KWARG: Final = "search_free_tier_counted" +_COST_BREAKDOWN: Final = TypeAdapter(CostBreakdown) + + +class SharedCounter(Protocol): + async def async_increment(self, key: str, value: float, ttl: int | None = None) -> float: ... + + +class _UsageCarrier(BaseModel): + model_config = ConfigDict(frozen=True, extra="ignore", from_attributes=True) + + usage: Usage | None = None + + +def freed_units(allowance: int, units: int, total_after: int) -> int: + """Units of this request that landed under the allowance, given the shared total after they were added.""" + return max(0, min(units, allowance - (total_after - units))) + + +def search_free_tier_key(allowance: SearchFreeRequests, now: datetime) -> str: + return f"litellm:search_free_tier:{allowance['shared_group']}:{now.strftime(_PERIOD_STAMP[allowance['period']])}" + + +def search_free_tier_ttl(allowance: SearchFreeRequests, now: datetime) -> int: + reset: Final = get_next_standardized_reset_time(_PERIOD_DURATION[allowance["period"]], now, "UTC") + return int((reset - now).total_seconds()) + _TTL_GRACE_SECONDS + + +def _usage_of(completion_response: object) -> Usage | None: + try: + return _UsageCarrier.model_validate(completion_response, from_attributes=True).usage + except ValidationError: + return None + + +def _grounding_queries(usage: Usage) -> int: + details: Final = usage.prompt_tokens_details + from_details: Final = getattr(details, "web_search_requests", None) if details is not None else None + return from_details or get_web_search_requests_from_usage(usage) or 0 + + +def _billable_units(usage: Usage, model_info: ModelInfo) -> int: + queries: Final = _grounding_queries(usage) + if queries == 0: + return 0 + return queries if model_info.get("web_search_billing_unit") == "per_query" else 1 + + +def _record_freed_cost( + kwargs: MutableMapping[str, object], # mutable-ok: writes the reduced cost where the spend row reads it + sl_object: StandardLoggingPayload, + original_cost: float, + freed_cost: float, +) -> float: + reduced_cost: Final = original_cost - freed_cost + breakdown: Final = sl_object["cost_breakdown"] or CostBreakdown(total_cost=original_cost) + sl_object["cost_breakdown"] = _COST_BREAKDOWN.validate_python( # rebind-ok: the spend row reads this payload + { + **breakdown, + "total_cost": reduced_cost, + "original_cost": breakdown.get("original_cost", original_cost), + "discount_amount": breakdown.get("discount_amount", 0.0) + freed_cost, + } + ) + sl_object["response_cost"] = reduced_cost # rebind-ok: the spend row reads this payload + kwargs["response_cost"] = reduced_cost # rebind-ok: the spend row reads kwargs["response_cost"] + return reduced_cost + + +async def apply_search_free_tier( + kwargs: MutableMapping[str, object], # mutable-ok: writes the reduced cost where the spend row reads it + sl_object: StandardLoggingPayload, + response_cost: float, + completion_response: object, + counter: SharedCounter | None, + now: datetime, +) -> float: + """Zero the grounding queries that landed under the model's shared free allowance, everything else is unchanged.""" + model_info: Final = sl_object["model_map_information"]["model_map_value"] + allowance: Final = model_info.get("search_free_requests") if model_info is not None else None + usage: Final = _usage_of(completion_response) + if model_info is None or allowance is None or usage is None or sl_object["cache_hit"]: + return response_cost + units: Final = _billable_units(usage, model_info) + if units == 0 or kwargs.get(_COUNTED_KWARG): + return response_cost + if counter is None: + verbose_proxy_logger.warning( + "apply_search_free_tier is on but the proxy has no Redis, grounding is billed at full price" + ) + return response_cost + key: Final = search_free_tier_key(allowance, now) + try: + total_after: Final = await counter.async_increment(key, units, ttl=search_free_tier_ttl(allowance, now)) + except Exception: # noqa: BLE001 # any counter failure means full price, never a lost spend row + verbose_proxy_logger.warning( + "search free tier counter %s is unavailable, grounding is billed at full price", key + ) + return response_cost + kwargs[_COUNTED_KWARG] = True # rebind-ok: the proxy runs this callback twice per request, count it once + freed: Final = freed_units(allowance["count"], units, int(total_after)) + if freed == 0: + return response_cost + freed_cost: Final = min(response_cost, cost_per_web_search_request(usage, model_info) * freed / units) + return _record_freed_cost(kwargs, sl_object, response_cost, freed_cost) diff --git a/litellm/types/utils.py b/litellm/types/utils.py index 2cce951ca60..c3b4ebdf58f 100644 --- a/litellm/types/utils.py +++ b/litellm/types/utils.py @@ -223,6 +223,12 @@ class SearchContextCostPerQuery(TypedDict, total=False): search_context_size_high: float +class SearchFreeRequests(TypedDict): + count: ReadOnly[int] + period: ReadOnly[Literal["day", "month"]] + shared_group: ReadOnly[str] + + class AgenticLoopParams(TypedDict, total=False): """ Parameters passed to agentic loop hooks (e.g., WebSearch interception). @@ -390,6 +396,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): web_search_billing_unit: ( Literal["per_query", "per_prompt"] | None ) # "per_query" (Gemini 3.x) or "per_prompt" (Gemini 2.x) + search_free_requests: ReadOnly[SearchFreeRequests | None] google_maps_grounding_cost_per_query: ReadOnly[float | None] citation_cost_per_token: float | None # Cost per citation token for Perplexity tiered_pricing: list[dict[str, Any]] | None # Tiered pricing structure for models like Dashscope diff --git a/litellm/utils.py b/litellm/utils.py index ce686669bdd..6bd4c499b0c 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -6312,6 +6312,7 @@ def _get_model_info_helper( supports_computer_use=_model_info.get("supports_computer_use", None), search_context_cost_per_query=_model_info.get("search_context_cost_per_query", None), web_search_billing_unit=_model_info.get("web_search_billing_unit", None), + search_free_requests=_model_info.get("search_free_requests", None), google_maps_grounding_cost_per_query=_model_info.get("google_maps_grounding_cost_per_query", None), tpm=_model_info.get("tpm", None), rpm=_model_info.get("rpm", None), diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 9635cf3ce72..d0020004e19 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -26338,6 +26338,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 1.5e-07, @@ -26450,6 +26451,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3-pro-image-preview": { @@ -26501,6 +26503,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image": { @@ -26547,6 +26550,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image-preview": { @@ -26589,6 +26593,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-lite-image": { @@ -26679,6 +26684,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -26740,6 +26746,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -26799,6 +26806,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -26885,6 +26893,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-08, "input_cost_per_token_batches": 5e-08, @@ -26939,6 +26948,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -26985,6 +26995,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -27171,6 +27182,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, "input_cost_per_token_batches": 6.25e-07, @@ -27198,6 +27210,7 @@ "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_image": 0.00012, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27293,6 +27306,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -27349,6 +27363,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3-flash-preview": { @@ -27363,6 +27378,7 @@ "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 3e-06, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27460,6 +27476,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -27523,6 +27540,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -27582,6 +27600,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -27603,6 +27622,7 @@ "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, "regional_endpoint_uplift_multiplier": 1.1, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27746,6 +27766,7 @@ "output_cost_per_token_above_200k_tokens": 1.8e-05, "output_cost_per_token_batches": 6e-06, "output_cost_per_image": 0.00012, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27847,6 +27868,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -28174,6 +28196,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "supports_reasoning": false }, @@ -28218,6 +28241,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite-preview": { @@ -28279,6 +28303,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -28428,6 +28453,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 1.5e-07, @@ -28538,6 +28564,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "supports_reasoning": false }, @@ -28602,6 +28629,7 @@ "output_cost_per_token_batches": 1.5e-06, "rpm": 1000, "tpm": 4000000, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -28757,6 +28785,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 1.5e-07, "input_cost_per_token_batches": 5e-08, @@ -28960,6 +28989,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, @@ -29055,6 +29085,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -29115,6 +29146,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29171,6 +29203,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 5e-07, @@ -29234,6 +29267,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -29299,6 +29333,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29360,6 +29395,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29421,6 +29457,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29516,6 +29553,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, @@ -29579,6 +29617,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, @@ -29597,6 +29636,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -29726,6 +29766,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -29789,6 +29830,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29848,6 +29890,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29868,6 +29911,7 @@ "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -49878,6 +49922,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -49940,6 +49985,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -50000,6 +50046,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, diff --git a/model_prices_and_context_window.schema.json b/model_prices_and_context_window.schema.json index 5b2d52f11ee..7048dfa9dcb 100644 --- a/model_prices_and_context_window.schema.json +++ b/model_prices_and_context_window.schema.json @@ -844,6 +844,33 @@ }, "additionalProperties": false }, + "search_free_requests": { + "type": "object", + "description": "Free Google Search grounding requests per period, shared across models in the same shared_group.", + "required": [ + "count", + "period", + "shared_group" + ], + "additionalProperties": false, + "properties": { + "count": { + "type": "integer", + "minimum": 0 + }, + "period": { + "type": "string", + "enum": [ + "day", + "month" + ] + }, + "shared_group": { + "type": "string", + "pattern": "\\S" + } + } + }, "source": { "type": "string", "description": "URL of the provider pricing/model page this entry was taken from." diff --git a/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py b/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py index 55eefeaa4ed..bdafb966574 100644 --- a/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py +++ b/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py @@ -29,7 +29,7 @@ from litellm.proxy.utils import ProxyUpdateSpend from litellm.proxy.spend_tracking.spend_event import SpendEventDecodeError, build_spend_event, decode_spend_event from litellm.proxy.spend_tracking.spend_event_producer import SpendEventProducer, UnixAddress from litellm.proxy.spend_tracking.spend_tracking_utils import get_logging_payload -from litellm.types.utils import CallTypes, LiteLLMBatch, ModelResponse, Usage +from litellm.types.utils import CallTypes, LiteLLMBatch, ModelResponse, PromptTokensDetailsWrapper, Usage @pytest.mark.asyncio @@ -2773,3 +2773,91 @@ async def test_track_cost_callback_failure_alert_never_carries_request_metadata_ assert "headers" in failure_debug_lines[0] else: assert failure_debug_lines == [] + +class _SharedCounter: + def __init__(self) -> None: + self.totals: dict[str, float] = {} + + async def async_increment(self, key: str, value: float, ttl: int | None = None) -> float: + self.totals[key] = self.totals.get(key, 0) + value + return self.totals[key] + + +def _grounded_gemini_kwargs(response_cost: float) -> dict: + return { + "model": "vertex_ai/gemini-test", + "call_type": "acompletion", + "response_cost": response_cost, + "litellm_params": {"metadata": {"user_api_key": "sk-test", "user_api_key_user_id": "user-1"}}, + "standard_logging_object": { + "response_cost": response_cost, + "request_tags": None, + "cache_hit": None, + "cost_breakdown": { + "input_cost": 0.0, + "output_cost": 0.0, + "tool_usage_cost": 0.5, + "total_cost": response_cost, + }, + "model_map_information": { + "model_map_key": "vertex_ai/gemini-test", + "model_map_value": { + "litellm_provider": "vertex_ai", + "mode": "chat", + "web_search_billing_unit": "per_query", + "search_context_cost_per_query": {"search_context_size_medium": 0.1}, + "search_free_requests": {"count": 100, "period": "month", "shared_group": "test"}, + }, + }, + }, + "stream": False, + } + + +@pytest.mark.asyncio +@pytest.mark.parametrize("opted_in", [True, False]) +async def test_track_cost_callback_frees_grounding_under_the_allowance_only_when_opted_in(monkeypatch, opted_in): + monkeypatch.setattr(litellm, "apply_search_free_tier", opted_in, raising=False) + counter = _SharedCounter() + kwargs = _grounded_gemini_kwargs(response_cost=1.0) + response = ModelResponse( + usage=Usage( + prompt_tokens=10, + completion_tokens=5, + total_tokens=15, + prompt_tokens_details=PromptTokensDetailsWrapper(web_search_requests=5), + ) + ) + + with ( + patch( # test-quality-ok: increment_spend_counters is a proxy_server global the callback reads lazily, no seam + "litellm.proxy.proxy_server.increment_spend_counters", new_callable=AsyncMock + ), + patch( # test-quality-ok: update_cache is a proxy_server global the callback reads lazily, no seam + "litellm.proxy.proxy_server.update_cache", new_callable=AsyncMock + ), + patch( # test-quality-ok: callback imports proxy_logging_obj off proxy_server in its body, no seam + "litellm.proxy.proxy_server.proxy_logging_obj" + ) as mock_proxy_logging, + ): + mock_proxy_logging.failed_tracking_alert = AsyncMock() + mock_proxy_logging.db_spend_update_writer.update_database = AsyncMock(return_value=True) + mock_proxy_logging.slack_alerting_instance.customer_spend_alert = AsyncMock() + mock_proxy_logging.internal_usage_cache.dual_cache.redis_cache = counter + + await _ProxyDBLogger()._PROXY_track_cost_callback( + kwargs=kwargs, completion_response=response, start_time=datetime.now(), end_time=datetime.now() + ) + await asyncio.sleep(0) + + mock_proxy_logging.failed_tracking_alert.assert_not_called() + mock_proxy_logging.db_spend_update_writer.update_database.assert_awaited_once() + + breakdown = kwargs["standard_logging_object"]["cost_breakdown"] + if opted_in: + assert kwargs["response_cost"] == pytest.approx(1.0 - 5 * 0.1) + assert breakdown["original_cost"] == 1.0 and breakdown["discount_amount"] == pytest.approx(5 * 0.1) + assert sum(counter.totals.values()) == 5 + else: + assert kwargs["response_cost"] == 1.0 and "discount_amount" not in breakdown + assert counter.totals == {} diff --git a/tests/unit/proxy/hooks/test_search_free_tier.py b/tests/unit/proxy/hooks/test_search_free_tier.py new file mode 100644 index 00000000000..3dc89c0dc72 --- /dev/null +++ b/tests/unit/proxy/hooks/test_search_free_tier.py @@ -0,0 +1,194 @@ +from datetime import datetime, timedelta, timezone +from typing import Final + +import pytest + +from litellm.proxy.hooks.search_free_tier import ( + apply_search_free_tier, + freed_units, + search_free_tier_key, + search_free_tier_ttl, +) +from litellm.types.utils import ModelResponse, PromptTokensDetailsWrapper, Usage + +NOW: Final = datetime(2026, 10, 20, 12, 30, tzinfo=timezone.utc) +RATE: Final = 0.01 + + +class _Counter: + def __init__(self) -> None: + self.totals: dict[str, float] = {} + self.ttls: dict[str, int | None] = {} + + async def async_increment(self, key: str, value: float, ttl: int | None = None) -> float: + self.totals[key] = self.totals.get(key, 0) + value + self.ttls[key] = ttl + return self.totals[key] + + +class _BrokenCounter: + async def async_increment(self, key: str, value: float, ttl: int | None = None) -> float: + raise ConnectionError("redis is down") + + +def _model_info(billing_unit: str, count: int, period: str = "month") -> dict: + return { + "litellm_provider": "vertex_ai", + "mode": "chat", + "web_search_billing_unit": billing_unit, + "search_context_cost_per_query": {"search_context_size_medium": RATE}, + "search_free_requests": {"count": count, "period": period, "shared_group": "test-group"}, + } + + +def _response(queries: int | None) -> ModelResponse: + details = PromptTokensDetailsWrapper(web_search_requests=queries) if queries is not None else None + return ModelResponse( + usage=Usage(prompt_tokens=10, completion_tokens=5, total_tokens=15, prompt_tokens_details=details) + ) + + +def _call(model_info: dict, response_cost: float, cache_hit: bool | None = None) -> tuple[dict, dict]: + sl_object = { + "response_cost": response_cost, + "cache_hit": cache_hit, + "cost_breakdown": {"input_cost": 0.1, "output_cost": 0.2, "tool_usage_cost": 0.5, "total_cost": response_cost}, + "model_map_information": {"model_map_key": "gemini-test", "model_map_value": model_info}, + } + return {"response_cost": response_cost, "standard_logging_object": sl_object}, sl_object + + +@pytest.mark.parametrize( + ("allowance", "units", "total_after", "expected"), + [ + (5000, 5, 5, 5), + (5000, 5, 5000, 5), + (5000, 10, 5005, 5), + (5000, 5, 5010, 0), + (2, 5, 5, 2), + (0, 3, 3, 0), + ], +) +def test_freed_units_covers_only_what_landed_under_the_allowance(allowance, units, total_after, expected): + assert freed_units(allowance, units, total_after) == expected + + +def test_counter_key_is_per_group_and_utc_period(): + assert search_free_tier_key({"count": 1, "period": "month", "shared_group": "g3"}, NOW) == ( + "litellm:search_free_tier:g3:2026-10" + ) + assert search_free_tier_key({"count": 1, "period": "day", "shared_group": "g2"}, NOW) == ( + "litellm:search_free_tier:g2:2026-10-20" + ) + + +@pytest.mark.parametrize( + ("period", "boundary"), + [("month", datetime(2026, 11, 1, tzinfo=timezone.utc)), ("day", datetime(2026, 10, 21, tzinfo=timezone.utc))], +) +def test_counter_ttl_outlives_the_period_boundary_by_under_two_hours(period, boundary): + expiry = NOW + timedelta(seconds=search_free_tier_ttl({"count": 1, "period": period, "shared_group": "g"}, NOW)) + assert boundary < expiry < boundary + timedelta(hours=2) + + +@pytest.mark.asyncio +async def test_per_query_allowance_is_shared_across_calls_and_split_on_the_crossing_call(): + counter = _Counter() + model_info = _model_info("per_query", count=7) + reduced = [] + for _ in range(3): + kwargs, sl_object = _call(model_info, response_cost=1.0) + cost = await apply_search_free_tier(kwargs, sl_object, 1.0, _response(5), counter, NOW) + reduced.append((cost, kwargs["response_cost"], sl_object["response_cost"], sl_object["cost_breakdown"])) + (c1, k1, s1, b1), (c2, k2, s2, b2), (c3, k3, s3, b3) = reduced + assert c1 == k1 == s1 == pytest.approx(1.0 - 5 * RATE) + assert b1["original_cost"] == 1.0 and b1["discount_amount"] == pytest.approx(5 * RATE) + assert b1["total_cost"] == pytest.approx(c1) and b1["tool_usage_cost"] == 0.5 + assert c2 == k2 == s2 == pytest.approx(1.0 - 2 * RATE) + assert b2["discount_amount"] == pytest.approx(2 * RATE) + assert c3 == k3 == s3 == 1.0 and "discount_amount" not in b3 + assert counter.totals == {"litellm:search_free_tier:test-group:2026-10": 15} + assert counter.ttls["litellm:search_free_tier:test-group:2026-10"] > 0 + + +@pytest.mark.asyncio +async def test_per_prompt_allowance_counts_a_grounded_prompt_once_whatever_the_query_count(): + counter = _Counter() + model_info = _model_info("per_prompt", count=1, period="day") + kwargs, sl_object = _call(model_info, response_cost=1.0) + first = await apply_search_free_tier(kwargs, sl_object, 1.0, _response(5), counter, NOW) + kwargs, sl_object = _call(model_info, response_cost=1.0) + second = await apply_search_free_tier(kwargs, sl_object, 1.0, _response(5), counter, NOW) + assert first == pytest.approx(1.0 - RATE) + assert second == 1.0 + assert counter.totals == {"litellm:search_free_tier:test-group:2026-10-20": 2} + + +@pytest.mark.asyncio +async def test_sidecar_shaped_response_mapping_is_counted_like_a_model_response(): + counter = _Counter() + kwargs, sl_object = _call(_model_info("per_query", count=100), response_cost=1.0) + response = { + "usage": { + "prompt_tokens": 1, + "completion_tokens": 1, + "total_tokens": 2, + "prompt_tokens_details": {"web_search_requests": 3}, + } + } + assert await apply_search_free_tier(kwargs, sl_object, 1.0, response, counter, NOW) == pytest.approx(1.0 - 3 * RATE) + + +@pytest.mark.asyncio +@pytest.mark.parametrize("counter", [None, _BrokenCounter()]) +async def test_full_price_when_no_counter_is_available(counter): + kwargs, sl_object = _call(_model_info("per_query", count=100), response_cost=1.0) + assert await apply_search_free_tier(kwargs, sl_object, 1.0, _response(5), counter, NOW) == 1.0 + assert kwargs["response_cost"] == 1.0 and "discount_amount" not in sl_object["cost_breakdown"] + + +@pytest.mark.asyncio +@pytest.mark.parametrize("response", [_response(0), _response(None), ModelResponse()]) +async def test_requests_without_grounding_never_touch_the_counter(response): + counter = _Counter() + kwargs, sl_object = _call(_model_info("per_query", count=100), response_cost=1.0) + assert await apply_search_free_tier(kwargs, sl_object, 1.0, response, counter, NOW) == 1.0 + assert counter.totals == {} + + +@pytest.mark.asyncio +async def test_models_without_an_allowance_never_touch_the_counter(): + counter = _Counter() + model_info = {k: v for k, v in _model_info("per_query", count=100).items() if k != "search_free_requests"} + kwargs, sl_object = _call(model_info, response_cost=1.0) + assert await apply_search_free_tier(kwargs, sl_object, 1.0, _response(5), counter, NOW) == 1.0 + assert counter.totals == {} + + +@pytest.mark.asyncio +async def test_a_second_callback_run_on_the_same_request_counts_it_once(): + counter = _Counter() + kwargs, sl_object = _call(_model_info("per_query", count=100), response_cost=1.0) + first = await apply_search_free_tier(kwargs, sl_object, 1.0, _response(5), counter, NOW) + second = await apply_search_free_tier(kwargs, sl_object, first, _response(5), counter, NOW) + assert first == second == pytest.approx(1.0 - 5 * RATE) + assert counter.totals == {"litellm:search_free_tier:test-group:2026-10": 5} + + +@pytest.mark.asyncio +async def test_a_cache_hit_with_grounded_usage_is_not_counted_and_stays_at_zero(): + counter = _Counter() + kwargs, sl_object = _call(_model_info("per_query", count=100), response_cost=0.0, cache_hit=True) + assert await apply_search_free_tier(kwargs, sl_object, 0.0, _response(2), counter, NOW) == 0.0 + assert counter.totals == {} + assert "discount_amount" not in sl_object["cost_breakdown"] + + +@pytest.mark.asyncio +async def test_freed_cost_never_exceeds_the_billed_cost(): + counter = _Counter() + billed = 3 * RATE + kwargs, sl_object = _call(_model_info("per_query", count=100), response_cost=billed) + assert await apply_search_free_tier(kwargs, sl_object, billed, _response(5), counter, NOW) == 0.0 + assert sl_object["cost_breakdown"]["discount_amount"] == pytest.approx(billed) + assert counter.totals == {"litellm:search_free_tier:test-group:2026-10": 5} diff --git a/tests/unit/test_model_prices_schema.py b/tests/unit/test_model_prices_schema.py index 211a43d2574..faa6b6d2ef7 100644 --- a/tests/unit/test_model_prices_schema.py +++ b/tests/unit/test_model_prices_schema.py @@ -10,11 +10,13 @@ from typing import Final import jsonschema import pytest +from pydantic import JsonValue, TypeAdapter import litellm from litellm.llms.openai.chat.gpt_5_transformation import is_gpt_reasoning_series_name from litellm.llms.openai_like.json_loader import JSONProviderRegistry from litellm.router_utils.reasoning_effort_capability import resolve_supported_reasoning_efforts +from litellm.types.utils import SearchFreeRequests REPO_ROOT = Path(__file__).parents[2] GENERATOR_PATH = REPO_ROOT / "ci_cd" / "generate_model_prices_schema.py" @@ -579,3 +581,30 @@ def test_unregistered_provider_guard_flags_only_labels_nobody_registered(): "unknown_root-new_family_models", "vertex_ai-new_family_models", ] + + +def _search_free_requests_rows(path: Path) -> Mapping[str, dict[str, JsonValue]]: + prices: Final[dict[str, JsonValue]] = TypeAdapter(dict[str, JsonValue]).validate_json(path.read_bytes()) + return MappingProxyType( + {key: row for key, row in prices.items() if isinstance(row, dict) and "search_free_requests" in row} + ) + + +@pytest.mark.parametrize("path", (PRICES_PATH, BACKUP_PRICES_PATH), ids=("main", "backup")) +def test_search_free_requests_rows_are_grounding_rows_with_one_allowance_per_group(path: Path) -> None: + rows = _search_free_requests_rows(path) + assert rows + allowances = { + key: TypeAdapter(SearchFreeRequests).validate_python(row["search_free_requests"]) for key, row in rows.items() + } + for key, row in rows.items(): + assert row.get("supports_web_search") is True, key + assert row.get("search_context_cost_per_query"), key + assert allowances[key]["count"] > 0, key + for group in {allowance["shared_group"] for allowance in allowances.values()}: + same_group = {(a["count"], a["period"]) for a in allowances.values() if a["shared_group"] == group} + assert len(same_group) == 1, (group, same_group) + + +def test_search_free_requests_backup_rows_match_the_main_catalog() -> None: + assert _search_free_requests_rows(BACKUP_PRICES_PATH) == _search_free_requests_rows(PRICES_PATH) diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py index fe1fe4879e5..67f50decf21 100644 --- a/tests/unit/test_utils.py +++ b/tests/unit/test_utils.py @@ -1038,6 +1038,16 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "type": "string", "enum": ["per_prompt", "per_query"], }, + "search_free_requests": { + "type": "object", + "properties": { + "count": {"type": "integer", "minimum": 1}, + "period": {"type": "string", "enum": ["day", "month"]}, + "shared_group": {"type": "string"}, + }, + "required": ["count", "period", "shared_group"], + "additionalProperties": False, + }, "citation_cost_per_token": {"type": "number"}, "supported_modalities": { "type": "array", From dbbebd07bfcfac854d77c78682a4e9281ee266ba Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 12:21:42 -0700 Subject: [PATCH 47/66] fix(proxy): flush the spend-log queue only for Responses turns the bridge reads back (#47614) Every /v1/responses spend log asked its worker to flush the queue right away so a chained previous_response_id could find the row. Only the chat-completions bridge reads that row. Native Responses providers hold the conversation upstream, so their rows now wait for the batch write like chat rows do Backport of #47614 to stable/1.104.x Cherry-picked from 423362bab26203fe613867497b01fc0579efdc0f (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/proxy/db/db_spend_update_writer.py | 48 +++++++++++++++-- litellm/responses/main.py | 16 ++++++ .../proxy/db/test_db_spend_update_writer.py | 51 +++++++++++++++---- 3 files changed, 99 insertions(+), 16 deletions(-) diff --git a/litellm/proxy/db/db_spend_update_writer.py b/litellm/proxy/db/db_spend_update_writer.py index 17e6152bef6..cfc2563988f 100644 --- a/litellm/proxy/db/db_spend_update_writer.py +++ b/litellm/proxy/db/db_spend_update_writer.py @@ -88,6 +88,7 @@ if TYPE_CHECKING: from litellm.proxy.db.autorouter_session_rollup import AutoRouterTurnTransaction from litellm.proxy.db.baseline_accounting import DailyBaselineAttribution from litellm.proxy.utils import PrismaClient, ProxyLogging + from litellm.router import Router else: PrismaClient = Any ProxyLogging = Any @@ -97,6 +98,34 @@ RESPONSES_SESSION_CALL_TYPES: Final = frozenset({CallTypes.responses.value, Call _SPEND_METADATA_ADAPTER: Final = TypeAdapter(Mapping[str, object]) +def _turn_chains_through_the_db(payload: Mapping[str, object], llm_router: "Router | None") -> bool: + """A Responses turn the chat-completions bridge replays from its spend log on the next `previous_response_id`. + + Native Responses providers hold the conversation themselves, so their rows can wait for the batch write. + A row with no router deployment behind it is treated as bridged, which keeps today's immediate flush. + """ + if payload.get("call_type") not in RESPONSES_SESSION_CALL_TYPES: + return False + model_id: Final = payload.get("model_id") + deployment: Final = ( + llm_router.get_deployment(model_id=model_id) if llm_router is not None and isinstance(model_id, str) else None + ) + if deployment is None: + return True + from litellm.responses.main import provider_stores_the_conversation + + litellm_params: Final = deployment.litellm_params + return not provider_stores_the_conversation( + litellm_params.model, + litellm_params.custom_llm_provider, + { + "use_chat_completions_api": litellm_params.use_chat_completions_api, + "model_info": deployment.model_info.model_dump(), + "api_base": litellm_params.api_base, + }, + ) + + def _org_member_transaction_key(org_id: str, user_id: str) -> str: return f"organization_id::{quote(org_id, safe='')}::user_id::{quote(user_id, safe='')}" @@ -527,12 +556,13 @@ class DBSpendUpdateWriter: get_request_model_access_groups, ) + llm_router: Final = get_llm_router() payload: Final = get_logging_payload( kwargs=kwargs, response_obj=completion_response, start_time=start_time, end_time=end_time, - llm_router=get_llm_router(), + llm_router=llm_router, ) payload["spend"] = response_cost or 0.0 if isinstance(payload["startTime"], datetime): @@ -547,7 +577,10 @@ class DBSpendUpdateWriter: payload["team_id"] = team_id if not await self._record_spend_log( - payload=payload, prisma_client=prisma_client, disable_spend_logs=disable_spend_logs + payload=payload, + prisma_client=prisma_client, + disable_spend_logs=disable_spend_logs, + llm_router=llm_router, ): return False @@ -608,14 +641,18 @@ class DBSpendUpdateWriter: return True async def _record_spend_log( - self, payload: SpendLogsPayload, prisma_client: "PrismaClient | None", disable_spend_logs: bool + self, + payload: SpendLogsPayload, + prisma_client: "PrismaClient | None", + disable_spend_logs: bool, + llm_router: "Router | None" = None, ) -> bool: if prisma_client is not None and _is_batch_cost_row(payload): return await self._claim_batch_cost_spend_log( payload=payload, prisma_client=prisma_client, disable_spend_logs=disable_spend_logs ) if disable_spend_logs is False: - await self._insert_spend_log_to_db(payload=payload, prisma_client=prisma_client) + await self._insert_spend_log_to_db(payload=payload, prisma_client=prisma_client, llm_router=llm_router) return True async def _claim_batch_cost_spend_log( @@ -1462,6 +1499,7 @@ class DBSpendUpdateWriter: payload: dict | SpendLogsPayload, prisma_client: PrismaClient | None = None, spend_logs_url: str | None = os.getenv("SPEND_LOGS_URL"), + llm_router: "Router | None" = None, ) -> PrismaClient | None: verbose_proxy_logger.debug( "Writing spend log to db - request_id: {}, spend: {}".format( @@ -1472,7 +1510,7 @@ class DBSpendUpdateWriter: from litellm.proxy.utils import enqueue_spend_logs, request_spend_log_flush await enqueue_spend_logs(prisma_client, (payload,)) - if payload.get("call_type") in RESPONSES_SESSION_CALL_TYPES: + if _turn_chains_through_the_db(_SPEND_METADATA_ADAPTER.validate_python(payload), llm_router): request_spend_log_flush(prisma_client) else: verbose_proxy_logger.debug("prisma_client is None. Skipping writing spend logs to db.") diff --git a/litellm/responses/main.py b/litellm/responses/main.py index 93c72bc2d3b..0724d014f5d 100644 --- a/litellm/responses/main.py +++ b/litellm/responses/main.py @@ -547,6 +547,22 @@ def _will_bridge_to_chat_completions( ) +def provider_stores_the_conversation(model: str, custom_llm_provider: str | None, kwargs: Mapping[str, object]) -> bool: + """Whether the provider, not a LiteLLM spend log, holds this turn for a `previous_response_id` follow-up. + + A bridged turn is replayed from its spend log, so the bridge needs that row in the DB, and a bridged + first MCP round runs as an internal call that writes no spend log at all. + """ + api_base: Final = _api_base_kwarg(kwargs) + return not _will_bridge_to_chat_completions( + model, + custom_llm_provider or litellm.get_llm_provider(model=model, api_base=api_base)[1], + bool(kwargs.get("use_chat_completions_api")), + kwargs.get("model_info"), + api_base, + ) + + @contextmanager def _prompt_management_sees_a_provisional_message_list( kwargs: dict[str, object], # mutable-ok: the signal is read and popped out of the caller's own kwargs diff --git a/tests/test_litellm/proxy/db/test_db_spend_update_writer.py b/tests/test_litellm/proxy/db/test_db_spend_update_writer.py index 7abb6e1ef92..a369d1c15da 100644 --- a/tests/test_litellm/proxy/db/test_db_spend_update_writer.py +++ b/tests/test_litellm/proxy/db/test_db_spend_update_writer.py @@ -3843,28 +3843,57 @@ async def test_commit_spend_updates_retries_deadlock_on_every_entity_path(monkey proxy_logging.failure_handler.assert_not_called() +def _responses_router() -> litellm.Router: + return litellm.Router( + model_list=[ + { + "model_name": "native", + "litellm_params": {"model": "openai/gpt-5.1", "api_key": "sk-test"}, + "model_info": {"id": "dep-native"}, + }, + { + "model_name": "bridged", + "litellm_params": {"model": "anthropic/claude-sonnet-4-5", "api_key": "sk-test"}, + "model_info": {"id": "dep-bridged"}, + }, + { + "model_name": "forced-bridge", + "litellm_params": {"model": "openai/gpt-5.1", "api_key": "sk-test", "use_chat_completions_api": True}, + "model_info": {"id": "dep-forced-bridge"}, + }, + ] + ) + + @pytest.mark.asyncio @pytest.mark.parametrize( - "call_type, expects_flush", - [("aresponses", True), ("responses", True), ("acompletion", False)], + "call_type, model_id, expects_flush", + [ + ("aresponses", "dep-bridged", True), + ("responses", "dep-bridged", True), + ("aresponses", "dep-forced-bridge", True), + ("aresponses", None, True), + ("aresponses", "dep-native", False), + ("responses", "dep-native", False), + ("acompletion", "dep-bridged", False), + ], ) -async def test_insert_spend_log_asks_for_an_immediate_flush_on_rows_other_workers_read_back( - call_type: str, expects_flush: bool +async def test_insert_spend_log_asks_for_an_immediate_flush_only_on_rows_the_bridge_reads_back( + call_type: str, model_id: str | None, expects_flush: bool ): """ - A `previous_response_id` chained straight off the previous turn reads the DB, so a - Responses row cannot sit in this worker's queue until the monitor's next poll. + A `previous_response_id` chained straight off a bridged turn reads that turn's row from the + DB, so it cannot sit in this worker's queue until the monitor's next poll. A native Responses + provider holds the conversation itself, so its row waits for the batch write like a chat row. """ db_writer = DBSpendUpdateWriter() prisma = _tool_usage_prisma() prisma.spend_log_flush_requested = asyncio.Event() + payload = {"request_id": "req-1", "call_type": call_type, "model_id": model_id} - await db_writer._insert_spend_log_to_db( - payload={"request_id": "req-1", "call_type": call_type}, - prisma_client=prisma, - ) + await db_writer._insert_spend_log_to_db(payload=payload, prisma_client=prisma, llm_router=_responses_router()) - assert prisma.spend_log_transactions == [{"request_id": "req-1", "call_type": call_type}] + assert prisma.spend_log_transactions == [payload] assert prisma.spend_log_flush_requested.is_set() is expects_flush From d388cb82531d7b49b9fc54fe6ac1e7209ba832a2 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 12:24:38 -0700 Subject: [PATCH 48/66] fix(proxy): bill partial Responses API streams when the client disconnects (#47611) * fix(proxy): bill partial Responses API streams when the client disconnects Streamed /v1/responses requests and the default-route OpenAI and Azure /v1/messages requests behind them logged a 499 with zero spend when the client went away mid-stream, while /v1/chat/completions already billed the chunks it had sent. The Responses API iterator now keeps the response.created payload and can hand the disconnect cleanup a response.incomplete event with counted usage and the served service_tier, and the messages-route byte stream and router wrappers delegate to it. * fix(proxy): satisfy lint gates for partial Responses API disconnect billing Make the disconnect helper public so the proxy, router and messages adapter can import it without reportPrivateUsage, type the SSE byte stream as an AsyncGenerator so aclose is known, read litellm_call_id off the logging object, and keep the new tests on Final locals with the recorder injected through dynamic_async_success_callbacks instead of litellm.callbacks. * fix(router): bill the primary stream's tokens after a mid-stream hop and chat-bridge Responses streams on disconnect The router's fallback wrapper now folds the primary Responses stream's relayed tokens into the fallback's disconnect event the way _combine_responses_fallback_usage does for a natural end of stream, and LiteLLMCompletionStreamingIterator (chat-only providers served through /v1/responses) builds its disconnect event from the chat completion chunks it collected. stamp_responses_usage_cost is now public so the bridge module can price that event. * Potential fix for pull request finding 'CodeQL / Log Injection' Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> --------- Backport of #47611 to stable/1.104.x Cherry-picked from f0ae445cc4567335d33a01030891fae94ef32467 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> --- .../responses_adapters/streaming_iterator.py | 38 +++++- litellm/proxy/common_request_processing.py | 12 ++ .../streaming_iterator.py | 40 ++++++- litellm/responses/streaming_iterator.py | 72 ++++++++++- litellm/router.py | 26 ++++ .../proxy/test_common_request_processing.py | 112 ++++++++++++++++++ .../test_litellm_completion_responses.py | 37 ++++++ .../test_responses_streaming_iterator.py | 99 ++++++++++++++++ .../unit/responses/test_streaming_iterator.py | 20 ++-- tests/unit/test_router/test_router.py | 65 ++++++++++ 10 files changed, 504 insertions(+), 17 deletions(-) diff --git a/litellm/llms/anthropic/experimental_pass_through/responses_adapters/streaming_iterator.py b/litellm/llms/anthropic/experimental_pass_through/responses_adapters/streaming_iterator.py index f753e87fee3..3d9c3ea32b3 100644 --- a/litellm/llms/anthropic/experimental_pass_through/responses_adapters/streaming_iterator.py +++ b/litellm/llms/anthropic/experimental_pass_through/responses_adapters/streaming_iterator.py @@ -4,11 +4,12 @@ import asyncio import json import traceback from collections import deque -from collections.abc import AsyncIterator, Iterator, Mapping +from collections.abc import AsyncGenerator, Iterator, Mapping from typing import TYPE_CHECKING, Any, Final from litellm import verbose_logger from litellm._uuid import uuid +from litellm.responses.streaming_iterator import partial_responses_incomplete_event_on_disconnect from litellm.litellm_core_utils.prompt_templates.common_utils import ( encrypted_reasoning_signature, ) @@ -25,6 +26,7 @@ from .transformation import ( if TYPE_CHECKING: from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObject + from litellm.types.llms.openai import ResponseIncompleteEvent class AnthropicResponsesStreamWrapper: @@ -391,8 +393,11 @@ class AnthropicResponsesStreamWrapper: raise StopAsyncIteration - async def async_anthropic_sse_wrapper(self) -> AsyncIterator[bytes]: - """Yield SSE-encoded bytes for each Anthropic event chunk.""" + def async_anthropic_sse_wrapper(self) -> "AnthropicResponsesSSEByteStream": + """SSE-encoded bytes for each Anthropic event chunk.""" + return AnthropicResponsesSSEByteStream(self) + + async def _sse_frames(self) -> AsyncGenerator[bytes, None]: async for chunk in self: if isinstance(chunk, dict): event_type: str = str(chunk.get("type", "message")) @@ -400,3 +405,30 @@ class AnthropicResponsesStreamWrapper: yield payload.encode() else: yield chunk + + def partial_response_on_disconnect(self) -> "ResponseIncompleteEvent | None": + return partial_responses_incomplete_event_on_disconnect(self.responses_stream) + + +class AnthropicResponsesSSEByteStream: + """ + The byte stream the proxy relays for a default-route /v1/messages request. + Keeps the Responses API iterator reachable so a client disconnect can bill + the partial output the way native /v1/responses streams do. + """ + + def __init__(self, wrapper: AnthropicResponsesStreamWrapper) -> None: + self._wrapper: Final = wrapper + self._frames: Final = wrapper._sse_frames() # pyright: ignore[reportPrivateUsage] # the wrapper's own byte stream + + def __aiter__(self) -> "AnthropicResponsesSSEByteStream": + return self + + async def __anext__(self) -> bytes: + return await self._frames.__anext__() + + async def aclose(self) -> None: + await self._frames.aclose() + + def partial_response_on_disconnect(self) -> "ResponseIncompleteEvent | None": + return self._wrapper.partial_response_on_disconnect() diff --git a/litellm/proxy/common_request_processing.py b/litellm/proxy/common_request_processing.py index 1d642e72de5..ef165e58134 100644 --- a/litellm/proxy/common_request_processing.py +++ b/litellm/proxy/common_request_processing.py @@ -111,6 +111,7 @@ from litellm.proxy.guardrails.auto_router_compression import arm_pre_call as _ar from litellm.proxy.native_compaction import with_proxy_compaction_executor from litellm.proxy.route_llm_request import route_request from litellm.proxy.utils import ProxyLogging, _check_and_merge_model_level_guardrails +from litellm.responses.streaming_iterator import partial_responses_incomplete_event_on_disconnect from litellm.router import Router from litellm.router_utils.add_retry_fallback_headers import get_hidden_params_dict from litellm.router_utils.common_utils import resolve_model_group_alias @@ -418,6 +419,13 @@ async def _bill_partial_streamed_spend_on_disconnect(request_data: dict, respons # A natural end-of-stream success event already fired and released the # slot; do not bill again, and let the caller skip the slot release. return True + partial_responses_event: Final = partial_responses_incomplete_event_on_disconnect(response) + if partial_responses_event is not None: + verbose_proxy_logger.debug( + "Billing partial streamed Responses API spend after client disconnect, litellm_call_id=%s", + logging_obj.litellm_call_id, + ) + return await _dispatch_disconnect_billing_event(logging_obj, partial_responses_event) chunks: Final[object] = getattr(response, "chunks", None) if not isinstance(chunks, list) or not chunks: return False @@ -447,6 +455,10 @@ async def _bill_partial_streamed_spend_on_disconnect(request_data: dict, respons partial_usage: Final = getattr(partial_response, "usage", None) if isinstance(partial_usage, Usage): backfill_missing_cache_usage_fields(partial_usage) + return await _dispatch_disconnect_billing_event(logging_obj, partial_response) + + +async def _dispatch_disconnect_billing_event(logging_obj: LiteLLMLoggingObj, partial_response: object) -> bool: try: await logging_obj.dispatch_success_handlers( partial_response, diff --git a/litellm/responses/litellm_completion_transformation/streaming_iterator.py b/litellm/responses/litellm_completion_transformation/streaming_iterator.py index 5173cd04a89..4f291165012 100644 --- a/litellm/responses/litellm_completion_transformation/streaming_iterator.py +++ b/litellm/responses/litellm_completion_transformation/streaming_iterator.py @@ -14,9 +14,10 @@ from litellm.responses.litellm_completion_transformation.custom_tools import ( from litellm.responses.litellm_completion_transformation.transformation import ( LiteLLMCompletionResponsesConfig, ) -from litellm.responses.streaming_iterator import ResponsesAPIStreamingIterator +from litellm.responses.streaming_iterator import ResponsesAPIStreamingIterator, stamp_responses_usage_cost from litellm.responses.utils import ResponsesAPIRequestUtils from litellm.types.llms.openai import ( + ResponseIncompleteEvent, PART_UNION_TYPES, BaseLiteLLMOpenAIResponseObject, ContentPartAddedEvent, @@ -1258,6 +1259,43 @@ class LiteLLMCompletionStreamingIterator(ResponsesAPIStreamingIterator): ) return reasoning_aligned + def partial_response_on_disconnect(self) -> ResponseIncompleteEvent | None: + """ + The response.incomplete event to bill when the client went away mid-stream. + Built from the chat completion chunks relayed so far, so the usage is what + stream_chunk_builder counts for them. + """ + if self.completed_response is not None or not self.collected_chat_completion_chunks: + return None + built: Final = stream_chunk_builder( + chunks=self.collected_chat_completion_chunks, + messages=LiteLLMCompletionResponsesConfig.transform_responses_api_input_to_messages( # pyright: ignore[reportUnknownMemberType] # the transformer's signature is partially untyped + input=self.request_input, + responses_api_request=dict(self.responses_api_request), + ), + logging_obj=self.litellm_logging_obj, + ) + if not isinstance(built, ModelResponse): + return None + responses_api_response: Final = ( + LiteLLMCompletionResponsesConfig.transform_chat_completion_response_to_responses_api_response( # pyright: ignore[reportUnknownMemberType] # the transformer's signature is partially untyped + request_input=self.request_input, + chat_completion_response=built, + responses_api_request=self.responses_api_request, + ) + ) + partial: Final = self._with_encoded_response_id( + responses_api_response.model_copy( + update={ + "id": self._cached_response_id or responses_api_response.id, + "status": "incomplete", + "output": list(self._output_with_streamed_item_ids(responses_api_response)), + } + ) + ) + stamp_responses_usage_cost(partial, self.litellm_logging_obj) + return ResponseIncompleteEvent(type=ResponsesAPIStreamEvents.RESPONSE_INCOMPLETE, response=partial) + def _emit_response_completed_event(self, litellm_model_response: ModelResponse) -> ResponseCompletedEvent | None: if litellm_model_response: # Transform the response diff --git a/litellm/responses/streaming_iterator.py b/litellm/responses/streaming_iterator.py index 70f2a7db6da..c691a0118d1 100644 --- a/litellm/responses/streaming_iterator.py +++ b/litellm/responses/streaming_iterator.py @@ -41,10 +41,12 @@ from litellm.types.integrations.custom_logger import converted_stream_requested from litellm.types.llms.openai import ( PART_UNION_TYPES, ResponseAPIUsage, + ResponseIncompleteEvent, ResponsesAPIResponse, ResponsesAPIStreamEvents, ResponsesAPIStreamingResponse, ) +from litellm.types.responses.main import GenericResponseOutputItem, OutputText from litellm.types.utils import CallTypes from litellm.utils import async_post_call_success_deployment_hook @@ -289,6 +291,7 @@ class BaseResponsesAPIStreamingIterator: self._yielded_first_chunk = False self._generated_content = "" self._generated_tool_arguments = "" + self._created_response: ResponsesAPIResponse | None = None self._completed_response_cached = False self._completed_response_logged = False self._completed_response_cache_hit: bool | None = None @@ -450,6 +453,10 @@ class BaseResponsesAPIStreamingIterator: # Store the completed response (also for incomplete/failed so logging still fires) _chunk_type: Final = getattr(openai_responses_api_chunk, "type", None) openai_types = _get_openai_response_types() + if _chunk_type == openai_types.ResponsesAPIStreamEvents.RESPONSE_CREATED: + _created: Final[object] = getattr(openai_responses_api_chunk, "response", None) + if isinstance(_created, ResponsesAPIResponse): + self._created_response = _created if openai_responses_api_chunk and _chunk_type in ( openai_types.ResponsesAPIStreamEvents.RESPONSE_COMPLETED, openai_types.ResponsesAPIStreamEvents.RESPONSE_INCOMPLETE, @@ -481,7 +488,7 @@ class BaseResponsesAPIStreamingIterator: else openai_responses_api_chunk.model_copy(update={"response": _billed_response}) ) self.completed_response = _terminal_chunk - _stamp_responses_usage_cost(_billed_response, self.logging_obj) + stamp_responses_usage_cost(_billed_response, self.logging_obj) if _chunk_type == openai_types.ResponsesAPIStreamEvents.RESPONSE_FAILED: self._handle_logging_failed_response() @@ -874,6 +881,34 @@ class BaseResponsesAPIStreamingIterator: except Exception: pass + def partial_response_on_disconnect(self) -> ResponseIncompleteEvent | None: + """ + The response.incomplete event to bill when the client went away mid-stream, + the same shape the success handler assembles for a natural end of stream. + Its response is the response.created payload (it carries the served + service_tier) plus the text and tool arguments relayed so far, with counted + usage since the provider never sent any. None when nothing was relayed yet + or the stream already reached its terminal event and billed itself. + """ + created: Final = self._created_response + generated: Final = self._generated_content + self._generated_tool_arguments + if self.completed_response is not None or created is None or not generated: + return None + usage: Final = _estimate_usage_safely( + self.model or "", self.request_data.get("input"), self.request_data, generated + ) + if usage is None: + return None + partial: Final = created.model_copy( + update={ + "status": "incomplete", + "usage": usage, + "output": _partial_output_items(self._generated_content), + } + ) + stamp_responses_usage_cost(partial, self.logging_obj) + return ResponseIncompleteEvent(type=ResponsesAPIStreamEvents.RESPONSE_INCOMPLETE, response=partial) + async def call_post_streaming_hooks_for_testing( iterator: object, chunk: ResponsesAPIStreamingResponse @@ -1347,6 +1382,37 @@ def _add_text_like_part_events( ) +@runtime_checkable +class _BillsPartialStreamOnDisconnect(Protocol): + def partial_response_on_disconnect(self) -> ResponseIncompleteEvent | None: ... + + +def partial_responses_incomplete_event_on_disconnect(stream: object) -> ResponseIncompleteEvent | None: + """Ask the stream behind a proxy or router wrapper for the partial response to bill, if it can build one.""" + if not isinstance(stream, _BillsPartialStreamOnDisconnect): + return None + try: + partial: Final = stream.partial_response_on_disconnect() + except Exception as e: # noqa: BLE001 # disconnect billing is best-effort; never break stream teardown + verbose_logger.debug("Failed to build partial Responses API response for disconnect billing: %s", e) + return None + return partial if isinstance(partial, ResponseIncompleteEvent) else None + + +def _partial_output_items(generated_text: str) -> Sequence[GenericResponseOutputItem]: + if not generated_text: + return [] + return [ + GenericResponseOutputItem( + type="message", + id=f"msg_{uuid.uuid4()}", + status="incomplete", + role="assistant", + content=[OutputText(type="output_text", text=generated_text, annotations=[])], + ) + ] + + def _billed_terminal_response( response_obj: object, estimate: Callable[[], ResponseAPIUsage | None] | None ) -> ResponsesAPIResponse | None: @@ -1453,7 +1519,7 @@ def _estimate_usage_safely( return None -def _stamp_responses_usage_cost( +def stamp_responses_usage_cost( response_obj: ResponsesAPIResponse | None, logging_obj: LiteLLMLoggingObj | None ) -> None: if response_obj is None or logging_obj is None: @@ -1479,7 +1545,7 @@ def build_synthetic_response_events( chunk_size: int, ) -> list[ResponsesAPIStreamingResponse]: openai_types: Final = _get_openai_response_types() - _stamp_responses_usage_cost(transformed, logging_obj) + stamp_responses_usage_cost(transformed, logging_obj) events: Final[list[ResponsesAPIStreamingResponse]] = [ _build_response_status_event(openai_types.ResponsesAPIStreamEvents.RESPONSE_CREATED, transformed), diff --git a/litellm/router.py b/litellm/router.py index 1bf6c85c61b..8539071d85f 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -364,6 +364,7 @@ if TYPE_CHECKING: from litellm.types.llms.base import BaseLiteLLMOpenAIResponseObject from litellm.types.llms.openai import ( ResponseAPIUsage, + ResponseIncompleteEvent, ResponseInputParam, ResponsesAPIResponse, ) @@ -641,6 +642,11 @@ class FallbackAwareAnthropicMessagesStream: self._source_iterator = fallback_response self.fallback_headers_adopted = True + def partial_response_on_disconnect(self) -> "ResponseIncompleteEvent | None": + from litellm.responses.streaming_iterator import partial_responses_incomplete_event_on_disconnect + + return partial_responses_incomplete_event_on_disconnect(self._source_iterator) + def __aiter__(self) -> "FallbackAwareAnthropicMessagesStream": return self @@ -3254,6 +3260,7 @@ class Router: from datetime import datetime self._async_generator = async_generator + self._billing_source: object = source_iterator # Mirror every attribute BaseResponsesAPIStreamingIterator.__init__ # would have set. The wrapper bypasses super().__init__ (it has no # httpx.Response of its own and no provider config to drive), so @@ -3302,10 +3309,29 @@ class Router: def adopt_fallback_headers(self, fallback_response: object) -> tuple[dict[str, object], dict[str, object]]: prepared: Final = Router._prepare_fallback_hidden_params(fallback_response) + self._billing_source = fallback_response self._hidden_params = {**prepared[0], "additional_headers": prepared[1]} # mutable-ok: stream metadata self.fallback_headers_adopted = True return prepared + def partial_response_on_disconnect(self) -> "ResponseIncompleteEvent | None": + """ + The event to bill on a client disconnect. After a mid-stream hop the primary + stream's relayed tokens are folded into the fallback's event, the way + _combine_responses_fallback_usage does for a natural end of stream. + """ + from litellm.responses.streaming_iterator import partial_responses_incomplete_event_on_disconnect + + current: Final = partial_responses_incomplete_event_on_disconnect(self._billing_source) + if self._billing_source is source_iterator: + return current + primary: Final = partial_responses_incomplete_event_on_disconnect(source_iterator) + if current is None or primary is None: + return current or primary + if primary.response.usage is not None: + Router._combine_responses_fallback_usage(current, primary.response.usage) + return current + def __aiter__(self): return self diff --git a/tests/test_litellm/proxy/test_common_request_processing.py b/tests/test_litellm/proxy/test_common_request_processing.py index 7b74e69685c..03c36932154 100644 --- a/tests/test_litellm/proxy/test_common_request_processing.py +++ b/tests/test_litellm/proxy/test_common_request_processing.py @@ -7637,6 +7637,118 @@ def _apply_stream_usage_tracking( ) + async def _start_partial_responses_stream(self, recorder: _RecordingSuccessLogger, *, relay_text: bool = True): + from litellm.llms.openai.responses.transformation import OpenAIResponsesAPIConfig + from litellm.responses.streaming_iterator import ResponsesAPIStreamingIterator + + mocked: Final = await litellm.aresponses( + model="gpt-4o-mini", + input="tell me a story", + mock_response="The codename is AZURE-FALCON-42 and the story is long.", + stream=True, + api_key="test-key", + ) + logging_obj: Final = mocked.logging_obj + logging_obj.dynamic_async_success_callbacks = [recorder] + stream: Final = ResponsesAPIStreamingIterator( + response=httpx.Response(200), + model="gpt-4o-mini", + responses_api_provider_config=OpenAIResponsesAPIConfig(), + logging_obj=logging_obj, + request_data={"model": "gpt-4o-mini", "input": "tell me a story"}, + custom_llm_provider="openai", + ) + created: Final = { + "type": "response.created", + "sequence_number": 0, + "response": { + "id": "resp_partial", + "object": "response", + "created_at": 1700000000.0, + "model": "gpt-4o-mini", + "status": "in_progress", + "output": [], + "parallel_tool_calls": True, + "tool_choice": "auto", + "tools": [], + "service_tier": "priority", + }, + } + delta: Final = { + "type": "response.output_text.delta", + "sequence_number": 1, + "item_id": "msg_partial", + "output_index": 0, + "content_index": 0, + "delta": "The codename is AZURE-FALCON-42", + } + for event in (created, delta) if relay_text else (created,): + stream._process_chunk(json.dumps(event)) + return stream + + async def _bill_and_wait(self, recorder: _RecordingSuccessLogger, streamed: object, logging_obj: object) -> bool: + billed: Final = await _bill_partial_streamed_spend_on_disconnect({"litellm_logging_obj": logging_obj}, streamed) + for _ in range(50): + if recorder.success_events: + break + await asyncio.sleep(0.1) + await asyncio.sleep(0.5) + return billed + + @pytest.mark.asyncio + async def test_disconnect_bills_partial_native_responses_stream_with_counted_usage(self): + from litellm.types.llms.openai import ResponsesAPIResponse + + recorder: Final = _RecordingSuccessLogger() + stream: Final = await self._start_partial_responses_stream(recorder) + billed: Final = await self._bill_and_wait(recorder, stream, stream.logging_obj) + + assert billed is True + assert len(recorder.success_events) == 1 + partial_response: Final = recorder.success_events[0]["response_obj"] + assert isinstance(partial_response, ResponsesAPIResponse) + assert partial_response.status == "incomplete" + assert getattr(partial_response, "service_tier") == "priority" + assert partial_response.usage.output_tokens == litellm.token_counter( + model="gpt-4o-mini", text="The codename is AZURE-FALCON-42" + ) + assert partial_response.usage.input_tokens > 0 + + @pytest.mark.asyncio + async def test_disconnect_bills_partial_default_route_messages_stream_through_the_responses_adapter(self): + from litellm.llms.anthropic.pass_through.responses_adapters.streaming_iterator import ( + AnthropicResponsesStreamWrapper, + ) + from litellm.router import FallbackAwareAnthropicMessagesStream + from litellm.types.llms.openai import ResponsesAPIResponse + + async def _sse_frames() -> AsyncGenerator[bytes, None]: + yield b"event: message_start\n\n" + + recorder: Final = _RecordingSuccessLogger() + stream: Final = await self._start_partial_responses_stream(recorder) + wrapper: Final = AnthropicResponsesStreamWrapper(responses_stream=stream, model="gpt-4o-mini") + streamed: Final = FallbackAwareAnthropicMessagesStream(_sse_frames(), wrapper.async_anthropic_sse_wrapper()) + billed: Final = await self._bill_and_wait(recorder, streamed, stream.logging_obj) + + assert billed is True + assert len(recorder.success_events) == 1 + partial_response: Final = recorder.success_events[0]["response_obj"] + assert isinstance(partial_response, ResponsesAPIResponse) + assert partial_response.usage.output_tokens == litellm.token_counter( + model="gpt-4o-mini", text="The codename is AZURE-FALCON-42" + ) + + @pytest.mark.asyncio + async def test_disconnect_before_any_responses_output_bills_nothing(self): + recorder: Final = _RecordingSuccessLogger() + stream: Final = await self._start_partial_responses_stream(recorder, relay_text=False) + billed: Final = await self._bill_and_wait(recorder, stream, stream.logging_obj) + + assert billed is False + assert recorder.success_events == [] + + class TestApplyStreamUsageTracking: def test_default_injects_usage_and_marks_strip_for_chat_completions(self): data = {"stream": True, "model": "gpt-5.4-nano"} diff --git a/tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py b/tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py index 7b9de4644b4..2b33034f060 100644 --- a/tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py +++ b/tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py @@ -5172,3 +5172,40 @@ async def test_bridge_rejects_untranslatable_tool_choice_with_a_400(stream: bool ) assert exc_info.value.status_code == 400 assert "tool_choice={'type': 'file_search'}" in str(exc_info.value) + + +@pytest.mark.asyncio +async def test_bridge_partial_response_on_disconnect_bills_the_relayed_chat_chunks(): + from litellm.responses.litellm_completion_transformation.streaming_iterator import ( + LiteLLMCompletionStreamingIterator, + ) + + chat_stream: Final = await litellm.acompletion( + model="gpt-4o-mini", + messages=[{"role": "user", "content": "tell me a story"}], + mock_response="The codename is AZURE-FALCON-42 and the story is long.", + stream=True, + api_key="test-key", + ) + iterator: Final = LiteLLMCompletionStreamingIterator( + model="gpt-4o-mini", + litellm_custom_stream_wrapper=chat_stream, + request_input="tell me a story", + responses_api_request={}, + custom_llm_provider="openai", + ) + assert iterator.partial_response_on_disconnect() is None, "nothing relayed yet, nothing to bill" + events: Final = [await iterator.__anext__() for _ in range(6)] + relayed_text: Final = "".join( + getattr(event, "delta", "") for event in events if event.type == "response.output_text.delta" + ) + assert relayed_text, "the bridge should have relayed some text by now" + + incomplete_event: Final = iterator.partial_response_on_disconnect() + + assert incomplete_event is not None + assert incomplete_event.type == "response.incomplete" + assert incomplete_event.response.status == "incomplete" + assert incomplete_event.response.usage is not None + assert incomplete_event.response.usage.output_tokens == litellm.token_counter(model="gpt-4o-mini", text=relayed_text) + assert incomplete_event.response.usage.input_tokens > 0 diff --git a/tests/unit/responses/test_responses_streaming_iterator.py b/tests/unit/responses/test_responses_streaming_iterator.py index 9ba7dfcaa80..f8064f9bc88 100644 --- a/tests/unit/responses/test_responses_streaming_iterator.py +++ b/tests/unit/responses/test_responses_streaming_iterator.py @@ -7,7 +7,10 @@ crashed with exit 139 whenever any CustomLogger was registered). """ import asyncio +import json import time +from collections.abc import Mapping +from typing import Final import httpx import pytest @@ -17,6 +20,7 @@ from litellm.integrations.custom_logger import CustomLogger from litellm.litellm_core_utils import thread_pool_executor as thread_pool_executor_module from litellm.responses import streaming_iterator as responses_streaming_iterator_module from litellm.litellm_core_utils.litellm_logging import Logging as LitellmLogging +from litellm.llms.openai.responses.transformation import OpenAIResponsesAPIConfig from litellm.responses.streaming_iterator import ResponsesAPIStreamingIterator from litellm.types.llms.openai import ResponsesAPIResponse @@ -156,3 +160,98 @@ async def test_sync_callbacks_run_only_after_async_handler_completes(recording_e submit_times = recording_executor.submit_times_for(logging_obj) assert len(submit_times) == 1 assert submit_times[0] >= recorder.async_hook_finished + + +_CREATED_RESPONSE_WITH_PRIORITY_TIER: Final[Mapping[str, object]] = { + "id": "resp_partial", + "object": "response", + "created_at": 1700000000.0, + "model": "gpt-5.4-nano", + "status": "in_progress", + "output": [], + "parallel_tool_calls": True, + "tool_choice": "auto", + "tools": [], + "service_tier": "priority", +} +_CREATED_WITH_PRIORITY_TIER: Final[Mapping[str, object]] = { + "type": "response.created", + "sequence_number": 0, + "response": _CREATED_RESPONSE_WITH_PRIORITY_TIER, +} + + +def _text_delta(text: str, sequence_number: int) -> Mapping[str, object]: + return { + "type": "response.output_text.delta", + "sequence_number": sequence_number, + "item_id": "msg_partial", + "output_index": 0, + "content_index": 0, + "delta": text, + } + + +def _completed_after(text: str) -> Mapping[str, object]: + return { + "type": "response.completed", + "sequence_number": 9, + "response": { + **_CREATED_RESPONSE_WITH_PRIORITY_TIER, + "status": "completed", + "usage": {"input_tokens": 5, "output_tokens": 7, "total_tokens": 12}, + }, + } + + +def _live_iterator(logging_obj: LitellmLogging) -> ResponsesAPIStreamingIterator: + return ResponsesAPIStreamingIterator( + response=httpx.Response(200), + model="gpt-5.4-nano", + responses_api_provider_config=OpenAIResponsesAPIConfig(), + logging_obj=logging_obj, + request_data={"model": "gpt-5.4-nano", "input": "tell me a story"}, + custom_llm_provider="openai", + ) + + +def test_partial_response_on_disconnect_bills_the_relayed_text_at_the_served_service_tier(): + iterator: Final = _live_iterator(_make_logging_obj()) + for event in (_CREATED_WITH_PRIORITY_TIER, _text_delta("Once upon a time ", 1), _text_delta("a fox slept.", 2)): + iterator._process_chunk(json.dumps(event)) + + incomplete_event: Final = iterator.partial_response_on_disconnect() + + assert incomplete_event is not None + assert incomplete_event.type == "response.incomplete" + partial: Final = incomplete_event.response + assert partial.status == "incomplete" + assert getattr(partial, "service_tier") == "priority" + assert partial.output[0].content[0].text == "Once upon a time a fox slept." + assert partial.usage.output_tokens == litellm.token_counter( + model="gpt-5.4-nano", text="Once upon a time a fox slept." + ) + assert partial.usage.input_tokens == litellm.token_counter( + model="gpt-5.4-nano", messages=[{"role": "user", "content": "tell me a story"}] + ) + assert partial.usage.total_tokens == partial.usage.input_tokens + partial.usage.output_tokens + + +@pytest.mark.parametrize( + "events", + [ + (), + (_CREATED_WITH_PRIORITY_TIER,), + (_CREATED_WITH_PRIORITY_TIER, _text_delta("Once upon a time", 1), _completed_after("Once upon a time")), + ], + ids=["nothing_relayed", "created_only", "already_completed"], +) +@pytest.mark.asyncio +async def test_partial_response_on_disconnect_is_none_when_there_is_nothing_to_bill_or_the_stream_billed_itself( + events: tuple[Mapping[str, object], ...], +): + iterator: Final = _live_iterator(_make_logging_obj()) + for event in events: + iterator._process_chunk(json.dumps(event)) + + assert iterator.partial_response_on_disconnect() is None diff --git a/tests/unit/responses/test_streaming_iterator.py b/tests/unit/responses/test_streaming_iterator.py index dbf54ec3b9b..597d0432682 100644 --- a/tests/unit/responses/test_streaming_iterator.py +++ b/tests/unit/responses/test_streaming_iterator.py @@ -437,26 +437,26 @@ def _responses_api_response_with_usage() -> ResponsesAPIResponse: def test_stamp_responses_usage_cost_stamps_computed_cost(): - from litellm.responses.streaming_iterator import _stamp_responses_usage_cost + from litellm.responses.streaming_iterator import stamp_responses_usage_cost response = _responses_api_response_with_usage() logging_obj = Mock(spec=LiteLLMLoggingObj) logging_obj._response_cost_calculator.return_value = 0.000704 - _stamp_responses_usage_cost(response, logging_obj) + stamp_responses_usage_cost(response, logging_obj) assert getattr(response.usage, "cost", None) == pytest.approx(0.000704) logging_obj._response_cost_calculator.assert_called_once_with(result=response) def test_stamp_responses_usage_cost_keeps_provider_reported_cost(): - from litellm.responses.streaming_iterator import _stamp_responses_usage_cost + from litellm.responses.streaming_iterator import stamp_responses_usage_cost response = _responses_api_response_with_usage() setattr(response.usage, "cost", 0.5) logging_obj = Mock(spec=LiteLLMLoggingObj) - _stamp_responses_usage_cost(response, logging_obj) + stamp_responses_usage_cost(response, logging_obj) assert getattr(response.usage, "cost", None) == pytest.approx(0.5) logging_obj._response_cost_calculator.assert_not_called() @@ -476,7 +476,7 @@ def _unvalidated_response_with_dict_usage(usage: dict) -> ResponsesAPIResponse: def test_stamp_responses_usage_cost_keeps_provider_cost_from_dict_usage(): - from litellm.responses.streaming_iterator import _stamp_responses_usage_cost + from litellm.responses.streaming_iterator import stamp_responses_usage_cost response = _unvalidated_response_with_dict_usage( { "input_tokens": 29, @@ -488,7 +488,7 @@ def test_stamp_responses_usage_cost_keeps_provider_cost_from_dict_usage(): ) logging_obj = Mock(spec=LiteLLMLoggingObj) - _stamp_responses_usage_cost(response, logging_obj) + stamp_responses_usage_cost(response, logging_obj) assert isinstance(response.usage, ResponseAPIUsage) assert response.usage.cost == pytest.approx(3e-05) @@ -497,12 +497,12 @@ def test_stamp_responses_usage_cost_keeps_provider_cost_from_dict_usage(): def test_stamp_responses_usage_cost_computes_cost_for_dict_usage_without_cost(): - from litellm.responses.streaming_iterator import _stamp_responses_usage_cost + from litellm.responses.streaming_iterator import stamp_responses_usage_cost response = _unvalidated_response_with_dict_usage({"input_tokens": 29, "output_tokens": 120, "total_tokens": 149}) logging_obj = Mock(spec=LiteLLMLoggingObj) logging_obj._response_cost_calculator.return_value = 0.000704 - _stamp_responses_usage_cost(response, logging_obj) + stamp_responses_usage_cost(response, logging_obj) assert isinstance(response.usage, ResponseAPIUsage) assert response.usage.cost == pytest.approx(0.000704) @@ -510,13 +510,13 @@ def test_stamp_responses_usage_cost_computes_cost_for_dict_usage_without_cost(): def test_stamp_responses_usage_cost_survives_calculator_failure(): - from litellm.responses.streaming_iterator import _stamp_responses_usage_cost + from litellm.responses.streaming_iterator import stamp_responses_usage_cost response = _responses_api_response_with_usage() logging_obj = Mock(spec=LiteLLMLoggingObj) logging_obj._response_cost_calculator.side_effect = RuntimeError("cost map unavailable") - _stamp_responses_usage_cost(response, logging_obj) + stamp_responses_usage_cost(response, logging_obj) assert getattr(response.usage, "cost", None) is None diff --git a/tests/unit/test_router/test_router.py b/tests/unit/test_router/test_router.py index 80131534183..1437f54cc68 100644 --- a/tests/unit/test_router/test_router.py +++ b/tests/unit/test_router/test_router.py @@ -18143,3 +18143,68 @@ def test_bare_model_group_served_by_wildcard_deployment_has_provider_prefixed_co assert router._has_content_policy_fallback("claude-sonnet-4-6", {}) is True assert router._has_content_policy_fallback("claude-haiku-4-5", {}) is False + + +@pytest.mark.asyncio +async def test_responses_fallback_wrapper_disconnect_billing_keeps_the_primary_streams_tokens(): + """After a mid-stream hop, a disconnect bills the primary's relayed text plus the fallback's, not the fallback alone.""" + import json + + from litellm.llms.openai.responses.transformation import OpenAIResponsesAPIConfig + from litellm.responses.streaming_iterator import ResponsesAPIStreamingIterator + + def _relayed_iterator(text: str) -> ResponsesAPIStreamingIterator: + logging_obj: Final = MagicMock(spec=LiteLLMLogging) + logging_obj.model_call_details = {"litellm_params": {}} + logging_obj.completion_start_time = None + iterator: Final = ResponsesAPIStreamingIterator( + response=httpx.Response(200), + model="gpt-5.4", + responses_api_provider_config=OpenAIResponsesAPIConfig(), + logging_obj=logging_obj, + request_data={"model": "gpt-5.4", "input": "Hi"}, + custom_llm_provider="openai", + ) + created: Final = { + "id": "resp_1", + "object": "response", + "created_at": 1700000000.0, + "model": "gpt-5.4", + "status": "in_progress", + "output": [], + "parallel_tool_calls": True, + "tool_choice": "auto", + "tools": [], + } + iterator._process_chunk(json.dumps({"type": "response.created", "sequence_number": 0, "response": created})) + iterator._process_chunk( + json.dumps( + { + "type": "response.output_text.delta", + "sequence_number": 1, + "item_id": "msg_1", + "output_index": 0, + "content_index": 0, + "delta": text, + } + ) + ) + return iterator + + router: Final = Router( + model_list=[{"model_name": "primary", "litellm_params": {"model": "openai/gpt-5.4", "api_key": "k"}}] + ) + primary: Final = _relayed_iterator("Once upon a time there was a lighthouse keeper") + fallback: Final = _relayed_iterator("who lit the lamp") + wrapped: Final = await router._aresponses_streaming_iterator( + response=primary, + initial_kwargs={"model": "primary", "stream": True, "input": "Hi", "original_generic_function": AsyncMock()}, + ) + primary_tokens: Final = primary.partial_response_on_disconnect().response.usage.output_tokens + fallback_tokens: Final = fallback.partial_response_on_disconnect().response.usage.output_tokens + + assert wrapped.partial_response_on_disconnect().response.usage.output_tokens == primary_tokens + + wrapped.adopt_fallback_headers(fallback) + + assert wrapped.partial_response_on_disconnect().response.usage.output_tokens == primary_tokens + fallback_tokens From 13779e98bd219d51c8d35c5d9a65f0ef597295c7 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 14:14:18 -0700 Subject: [PATCH 49/66] fix(proxy): strip caller base_model from spend pricing and reject lone surrogates in multipart metadata (#47639) * fix(proxy): strip caller base_model from spend pricing and reject lone surrogates in multipart metadata * fix(proxy): type the parsed multipart metadata so basedpyright does not grow reportArgumentType --------- Backport of #47639 to stable/1.104.x Cherry-picked from 2a268951c4ec277a64b194ed693b8ddfb264832d (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../proxy/common_utils/http_parsing_utils.py | 27 ++++++++++++-- litellm/proxy/litellm_pre_call_utils.py | 5 +-- litellm/proxy/utils.py | 2 +- .../common_utils/test_http_parsing_utils.py | 36 +++++++++++++++++++ .../proxy/test_pricing_field_strip.py | 22 ++++++++++-- tests/unit/proxy/test_update_spend.py | 28 +++++++++++++++ 6 files changed, 111 insertions(+), 9 deletions(-) diff --git a/litellm/proxy/common_utils/http_parsing_utils.py b/litellm/proxy/common_utils/http_parsing_utils.py index 1c2bd7ea217..e5aea016839 100644 --- a/litellm/proxy/common_utils/http_parsing_utils.py +++ b/litellm/proxy/common_utils/http_parsing_utils.py @@ -119,6 +119,23 @@ def coerce_numeric_form_fields( } +def _parse_form_metadata(raw_metadata: str) -> object: + """The JSON body path rejects a lone surrogate escape (``"\\ud800"``) with a + 400 because no provider or database can encode it. ``json.loads`` accepts + the escape, so the multipart ``metadata`` field gets the same check.""" + parsed: Final[object] = json.loads(raw_metadata) + try: + json.dumps(parsed, ensure_ascii=False).encode("utf-8") + except UnicodeEncodeError as e: + raise ProxyException( + message=f"Invalid form payload: metadata {e}", + type="invalid_request_error", + param="metadata", + code=status.HTTP_400_BAD_REQUEST, + ) from e + return parsed + + async def _read_request_body(request: Request | None) -> dict: """ Safely read the request body and parse it as JSON. @@ -158,9 +175,13 @@ async def _read_request_body(request: Request | None) -> dict: param="request_body", code=status.HTTP_400_BAD_REQUEST, ) - parsed_body = dict(form_data) - if "metadata" in parsed_body and isinstance(parsed_body["metadata"], str): - parsed_body["metadata"] = json.loads(parsed_body["metadata"]) + form_body: Final = dict(form_data) + raw_metadata: Final = form_body.get("metadata") + parsed_body = ( + {**form_body, "metadata": _parse_form_metadata(raw_metadata)} + if isinstance(raw_metadata, str) + else form_body + ) else: # Read the request body body: Final = await request.body() diff --git a/litellm/proxy/litellm_pre_call_utils.py b/litellm/proxy/litellm_pre_call_utils.py index 842824e7ec5..0acdbfaedd8 100644 --- a/litellm/proxy/litellm_pre_call_utils.py +++ b/litellm/proxy/litellm_pre_call_utils.py @@ -358,8 +358,9 @@ _ALLOW_CLIENT_MESSAGE_REDACTION_OPT_OUT_METADATA_KEY: Final = "allow_client_mess # ``litellm.model_cost`` map. Both effects belong to deployment configuration, # not to user-supplied request bodies, so the proxy strips them before they # reach the call path. Built from the Pydantic model so newly-added pricing -# fields are covered automatically. -_CLIENT_PRICING_CONTROL_FIELDS: Final = frozenset(CustomPricingLiteLLMParams.model_fields.keys()) +# fields are covered automatically. ``base_model`` selects which cost-map entry +# prices the row, so a caller naming a cheaper model lowers their own spend. +_CLIENT_PRICING_CONTROL_FIELDS: Final = frozenset(CustomPricingLiteLLMParams.model_fields.keys()) | {"base_model"} # ``model_info`` carries the same pricing fields when read by # ``use_custom_pricing_for_model``; strip from metadata for the same reason. # ``standard_logging_guardrail_information`` is proxy-written telemetry summed diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py index b9c9bc30661..ea008fcd8e9 100644 --- a/litellm/proxy/utils.py +++ b/litellm/proxy/utils.py @@ -8056,7 +8056,7 @@ async def _create_spend_logs_with_poison_isolation( await repo.table.create_many(data=rows, skip_duplicates=True) return failure_budget except Exception as e: - if not PrismaDBExceptionHandler.is_prisma_data_error(e): + if not (PrismaDBExceptionHandler.is_prisma_data_error(e) or isinstance(e, UnicodeEncodeError)): raise if PrismaDBExceptionHandler.is_database_service_unavailable_error(e): raise diff --git a/tests/test_litellm/proxy/common_utils/test_http_parsing_utils.py b/tests/test_litellm/proxy/common_utils/test_http_parsing_utils.py index 7929a0b21af..6532855dd4e 100644 --- a/tests/test_litellm/proxy/common_utils/test_http_parsing_utils.py +++ b/tests/test_litellm/proxy/common_utils/test_http_parsing_utils.py @@ -1210,3 +1210,39 @@ class TestCoerceNumericFormFields: numeric_fields=self.numeric_fields, ) assert result == {"n": 3, "temperature": None, "image": buffer} + + +@pytest.mark.asyncio +async def test_form_data_metadata_with_lone_surrogate_escape_is_rejected_like_a_json_body(): + """``json.loads`` accepts ``"\\ud800"`` and yields a lone surrogate that no + provider or database can utf-8 encode. The JSON body path already answers + 400, so the multipart ``metadata`` field must too, instead of letting the + value through to the spend log writers.""" + mock_request = MagicMock() + mock_request.form = AsyncMock( + return_value=FormData({"model": "whisper-1", "metadata": '{"tags": ["poison-\\ud800-tag"]}'}) + ) + mock_request.headers = {"content-type": "multipart/form-data"} + mock_request.scope = {} + mock_request.state._cached_headers = None + + with pytest.raises(ProxyException) as exc_info: + await _read_request_body(mock_request) + + assert exc_info.value.code == "400" + assert "metadata" in exc_info.value.message + + +@pytest.mark.asyncio +async def test_form_data_metadata_keeps_non_ascii_and_valid_surrogate_pairs(): + mock_request = MagicMock() + mock_request.form = AsyncMock( + return_value=FormData({"model": "whisper-1", "metadata": '{"tags": ["caf\\u00e9", "\\ud83d\\ude00"]}'}) + ) + mock_request.headers = {"content-type": "multipart/form-data"} + mock_request.scope = {} + mock_request.state._cached_headers = None + + result = await _read_request_body(mock_request) + + assert result["metadata"]["tags"] == ["café", "😀"] diff --git a/tests/test_litellm/proxy/test_pricing_field_strip.py b/tests/test_litellm/proxy/test_pricing_field_strip.py index a84c6ba2b8a..e2eaf714f7d 100644 --- a/tests/test_litellm/proxy/test_pricing_field_strip.py +++ b/tests/test_litellm/proxy/test_pricing_field_strip.py @@ -58,9 +58,7 @@ class TestStripClientPricingOverrides: # The strip set is built from the model so additions are picked up # automatically — this test guards against the model and the strip # set drifting apart if someone replaces the auto-derivation later. - assert _CLIENT_PRICING_CONTROL_FIELDS == frozenset( - CustomPricingLiteLLMParams.model_fields.keys() - ) + assert _CLIENT_PRICING_CONTROL_FIELDS >= frozenset(CustomPricingLiteLLMParams.model_fields.keys()) # Sanity: the obvious top-level pricing fields are in the set. for field in ( "input_cost_per_token", @@ -84,6 +82,22 @@ class TestStripClientPricingOverrides: "messages": [{"role": "user", "content": "hi"}], } + def test_root_base_model_dropped(self): + # ``base_model`` picks the cost-map entry a spend row is priced with + # (success rows via the standard logging payload, billed failure rows + # via the failure lift), so a caller naming a cheaper model lowers + # their own recorded spend. + data = { + "model": "gpt-4o", + "messages": [{"role": "user", "content": "hi"}], + "base_model": "gpt-4o-mini", + } + _strip_client_pricing_overrides(data) + assert data == { + "model": "gpt-4o", + "messages": [{"role": "user", "content": "hi"}], + } + def test_metadata_model_info_dropped(self): data = { "model": "gpt-4", @@ -264,6 +278,7 @@ async def test_add_litellm_data_to_request_skips_strip_with_key_opt_in(): "model": "gpt-4", "messages": [{"role": "user", "content": "hi"}], "input_cost_per_token": 0.0001, + "base_model": "gpt-4o-mini", "metadata": {"model_info": {"output_cost_per_token": 0.0002}}, } @@ -279,6 +294,7 @@ async def test_add_litellm_data_to_request_skips_strip_with_key_opt_in(): assert updated["input_cost_per_token"] == 0.0001 assert updated["metadata"]["model_info"] == {"output_cost_per_token": 0.0002} + assert updated["base_model"] == "gpt-4o-mini" @pytest.mark.asyncio diff --git a/tests/unit/proxy/test_update_spend.py b/tests/unit/proxy/test_update_spend.py index ebe505b3d60..ea80d675142 100644 --- a/tests/unit/proxy/test_update_spend.py +++ b/tests/unit/proxy/test_update_spend.py @@ -321,3 +321,31 @@ async def test_update_spend_logs_multiple_batches_with_failure(): # Verify all logs were cleared from transactions assert len(prisma_client.spend_log_transactions) == 0 + + +@pytest.mark.asyncio +async def test_update_spend_logs_drops_row_prisma_cannot_encode_and_keeps_the_rest(): + """A row the Prisma engine cannot utf-8 encode (a lone surrogate in a string + column) is permanent, so it must be dropped like any other poison row instead + of being requeued at the head of the queue where it would block every tenant.""" + prisma_client = MockPrismaClient() + proxy_logging_obj = create_mock_proxy_logging() + prisma_client.spend_log_transactions = [ + {"request_id": "good-1", "request_tags": '["a"]'}, + {"request_id": "poison", "request_tags": "\ud800"}, + {"request_id": "good-2", "request_tags": '["b"]'}, + ] + written = [] + + async def create_many(data, skip_duplicates): + if any("\ud800" in row["request_tags"] for row in data): + raise UnicodeEncodeError("utf-8", "\ud800", 0, 1, "surrogates not allowed") + written.extend(row["request_id"] for row in data) + + prisma_client.db.litellm_spendlogs.create_many = AsyncMock(side_effect=create_many) + + await update_spend(prisma_client, None, proxy_logging_obj) + + assert sorted(written) == ["good-1", "good-2"] + assert prisma_client.spend_log_transactions == [] + proxy_logging_obj.failure_handler.assert_not_called() From b092d90f751cd1bcabb74aa6f055f7555e30ac3a Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 14:55:28 -0700 Subject: [PATCH 50/66] fix(proxy): price a billed failure row at the deployment's long-context tier like the success path (#47647) Backport of #47647 to stable/1.104.x Cherry-picked from 70ece3501f5be4d5ed20e99958f2bc37183878a8 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/proxy/utils.py | 80 ++++++++++++-------- tests/test_litellm/proxy/test_proxy_utils.py | 29 +++++++ 2 files changed, 78 insertions(+), 31 deletions(-) diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py index ea008fcd8e9..d8bbb7cc808 100644 --- a/litellm/proxy/utils.py +++ b/litellm/proxy/utils.py @@ -82,7 +82,7 @@ from litellm.proxy.common_utils.openai_error_payload import ( from litellm.proxy.spend_tracking.spend_log_error_logger import spend_log_error from litellm.types.guardrails import GuardrailEventHooks from litellm.types.proxy.model_listing import ModelInfoResponse -from litellm.types.utils import CallTypes, CallTypesLiteral, CostPerToken, ModelInfo, Usage +from litellm.types.utils import CallTypes, CallTypesLiteral, ModelInfo, Usage try: from litellm_enterprise.enterprise_callbacks.send_emails.base_email import ( @@ -146,6 +146,7 @@ from litellm.litellm_core_utils.core_helpers import ( is_expected_client_error, ) from litellm.litellm_core_utils.litellm_logging import Logging, deployment_pricing_model_info +from litellm.litellm_core_utils.llm_cost_calc.utils import generic_cost_per_token from litellm.litellm_core_utils.safe_json_dumps import safe_dumps from litellm.litellm_core_utils.safe_json_loads import safe_json_loads from litellm.litellm_core_utils.served_output_texts import ( @@ -1108,19 +1109,38 @@ def _billed_earlier_attempts( ) -def _deployment_cost_per_token(deployment_id: str | None, model: str) -> CostPerToken | None: - """The pricing the router registered for this deployment under its ``model_info.id``, read - through ``deployment_pricing_model_info`` exactly as the success path does; None means the - public cost map. The id is ``Logging.get_router_model_id()`` (the logging object's own - ``litellm_params``), never the flattened ``model_call_details`` copy a request body key can - overwrite.""" - model_info: Final = deployment_pricing_model_info(model_id=deployment_id, deployment_model=model) - if model_info is None: +def _deployment_priced_input_cost( + model: str, custom_llm_provider: str | None, prompt_tokens: int, deployment_pricing: ModelInfo +) -> float: + """Input price for the estimated prompt at the deployment's registered rates, read through + ``deployment_pricing_model_info`` and priced by ``generic_cost_per_token`` the way the success + path prices them, so a long-context tier the deployment declares (``input_cost_per_token_above_200k_tokens``) + is honoured instead of flattened to the standard rate. An entry it cannot price keeps the row at $0.""" + usage: Final = Usage(prompt_tokens=prompt_tokens, completion_tokens=0, total_tokens=prompt_tokens) + try: + prompt_cost, _ = generic_cost_per_token( + model=model, + usage=usage, + custom_llm_provider=custom_llm_provider or str(deployment_pricing.get("litellm_provider") or ""), + model_info=deployment_pricing, + ) + except Exception as exc: # noqa: BLE001 # a malformed registered entry must not drop the failure row + verbose_proxy_logger.debug("failure spend estimate: could not price deployment of %s: %s", model, exc) + return 0.0 + return prompt_cost + + +def _priced_input_cost(pricing_model: str, custom_llm_provider: str | None, prompt_tokens: int) -> float | None: + try: + estimated_input_cost, _ = litellm.cost_per_token( + model=pricing_model, + custom_llm_provider=custom_llm_provider, + prompt_tokens=prompt_tokens, + ) + except Exception as exc: # noqa: BLE001 # cost_per_token raises BadRequestError for an unmapped model and the row must still be written + verbose_proxy_logger.debug("failure spend estimate: could not price %s: %s", pricing_model, exc) return None - return CostPerToken( - input_cost_per_token=model_info["input_cost_per_token"] or 0.0, - output_cost_per_token=model_info["output_cost_per_token"] or 0.0, - ) + return estimated_input_cost def _estimated_input_cost( @@ -1129,24 +1149,22 @@ def _estimated_input_cost( deployment_id: str | None, base_model: str | None, ) -> float: - """Input price for the estimated prompt: the deployment's registered rate when it has one, else - the cost map's rate for ``base_model`` or the deployment model (an Azure deployment name is not - in the cost map, its ``base_model`` is). An unpriceable model keeps the row at $0 rather than - dropping the failure row.""" - try: - model: Final = str(model_call_details.get("model") or "") - estimated_input_cost, _ = litellm.cost_per_token( - model=base_model or model, - custom_llm_provider=str(model_call_details.get("custom_llm_provider") or "") or None, - prompt_tokens=prompt_tokens, - custom_cost_per_token=_deployment_cost_per_token(deployment_id, model), - ) - except Exception as exc: # noqa: BLE001 # cost_per_token raises BadRequestError for an unmapped model and the row must still be written - verbose_proxy_logger.debug( - "failure spend estimate: could not price %s: %s", model_call_details.get("model"), exc - ) - return 0.0 - return estimated_input_cost + """Input price for the estimated prompt: the deployment's registered rates when it has any (the id + is ``Logging.get_router_model_id()``, never the flattened ``model_call_details`` copy a request body + key can overwrite), else the cost map's rate for ``base_model``, else the deployment model, the same + candidate order ``completion_cost`` walks (an Azure deployment name is not in the cost map, its + ``base_model`` is; a ``base_model`` the cost map does not know falls through to the deployment + model). A model no candidate can price keeps the row at $0 rather than dropping the failure row.""" + model: Final = str(model_call_details.get("model") or "") + custom_llm_provider: Final = str(model_call_details.get("custom_llm_provider") or "") or None + deployment_pricing: Final = deployment_pricing_model_info(model_id=deployment_id, deployment_model=model) + if deployment_pricing is not None: + return _deployment_priced_input_cost(model, custom_llm_provider, prompt_tokens, deployment_pricing) + pricing_models: Final = (base_model, model) if base_model is not None else (model,) + candidate_costs: Final = ( + _priced_input_cost(pricing_model, custom_llm_provider, prompt_tokens) for pricing_model in pricing_models + ) + return next((cost for cost in candidate_costs if cost is not None), 0.0) _EMPTY_LIFT: Final = MappingProxyType({}) diff --git a/tests/test_litellm/proxy/test_proxy_utils.py b/tests/test_litellm/proxy/test_proxy_utils.py index 6e4a4c6e4b1..8064d9cee57 100644 --- a/tests/test_litellm/proxy/test_proxy_utils.py +++ b/tests/test_litellm/proxy/test_proxy_utils.py @@ -2135,6 +2135,35 @@ def test_a_timed_out_request_is_priced_at_the_rate_the_router_registered_for_the assert response_cost == pytest.approx(usage.prompt_tokens * 0.25) +@pytest.mark.parametrize(("prompt_tokens", "expected_rate"), [(1_000, 1e-7), (250_000, 5e-7)]) +def test_a_timed_out_request_is_priced_at_the_deployments_long_context_tier(monkeypatch, prompt_tokens, expected_rate): + """A deployment that declares ``input_cost_per_token_above_200k_tokens`` next to its standard rate + bills a 250k-token prompt at the tier on the success path; the failure row must not flatten it to + the standard rate.""" + from litellm.proxy.utils import _estimated_input_cost + + monkeypatch.setitem( + litellm.model_cost, + "dep-lit-f9-tiered", + { + "litellm_provider": "openai", + "mode": "chat", + "input_cost_per_token": 1e-7, + "input_cost_per_token_above_200k_tokens": 5e-7, + "output_cost_per_token": 4e-7, + }, + ) + + response_cost = _estimated_input_cost( + model_call_details={"model": FAILURE_USAGE_MODEL, "custom_llm_provider": "openai"}, + prompt_tokens=prompt_tokens, + deployment_id="dep-lit-f9-tiered", + base_model=None, + ) + + assert response_cost == pytest.approx(prompt_tokens * expected_rate) + + def test_every_earlier_timed_out_attempt_is_billed_at_its_own_deployment_rate(monkeypatch): """The router leaves one RetryAttemptRecord per failed attempt in metadata.previous_models, the final attempt included; the earlier Timeout ones are billed (each at the deployment that served From b2ed8bc1c35d1e6960ade40e9dcd72da363a296c Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 15:01:53 -0700 Subject: [PATCH 51/66] fix(proxy): scope the search free-tier counter to the request's provider (#47646) * fix(proxy): scope the search free-tier counter to the request's provider * fix(proxy): read the provider with get so partial spend payloads still get the free tier * test(proxy): give the grounded spend payload fixture its provider --------- Backport of #47646 to stable/1.104.x Cherry-picked from 640f2d865bfa954d37bbbffc447f4e504e1dad21 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/proxy/hooks/search_free_tier.py | 8 ++-- .../hooks/test_proxy_track_cost_callback.py | 1 + .../unit/proxy/hooks/test_search_free_tier.py | 40 +++++++++++++------ 3 files changed, 34 insertions(+), 15 deletions(-) diff --git a/litellm/proxy/hooks/search_free_tier.py b/litellm/proxy/hooks/search_free_tier.py index b9beb8599b3..254fe567bf2 100644 --- a/litellm/proxy/hooks/search_free_tier.py +++ b/litellm/proxy/hooks/search_free_tier.py @@ -33,8 +33,9 @@ def freed_units(allowance: int, units: int, total_after: int) -> int: return max(0, min(units, allowance - (total_after - units))) -def search_free_tier_key(allowance: SearchFreeRequests, now: datetime) -> str: - return f"litellm:search_free_tier:{allowance['shared_group']}:{now.strftime(_PERIOD_STAMP[allowance['period']])}" +def search_free_tier_key(provider: str, allowance: SearchFreeRequests, now: datetime) -> str: + period_stamp: Final = now.strftime(_PERIOD_STAMP[allowance["period"]]) + return f"litellm:search_free_tier:{provider}:{allowance['shared_group']}:{period_stamp}" def search_free_tier_ttl(allowance: SearchFreeRequests, now: datetime) -> int: @@ -105,7 +106,8 @@ async def apply_search_free_tier( "apply_search_free_tier is on but the proxy has no Redis, grounding is billed at full price" ) return response_cost - key: Final = search_free_tier_key(allowance, now) + provider: Final = sl_object["custom_llm_provider"] or model_info["litellm_provider"] + key: Final = search_free_tier_key(provider, allowance, now) try: total_after: Final = await counter.async_increment(key, units, ttl=search_free_tier_ttl(allowance, now)) except Exception: # noqa: BLE001 # any counter failure means full price, never a lost spend row diff --git a/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py b/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py index bdafb966574..eb51e4ffa36 100644 --- a/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py +++ b/tests/test_litellm/proxy/hooks/test_proxy_track_cost_callback.py @@ -2793,6 +2793,7 @@ def _grounded_gemini_kwargs(response_cost: float) -> dict: "response_cost": response_cost, "request_tags": None, "cache_hit": None, + "custom_llm_provider": "vertex_ai", "cost_breakdown": { "input_cost": 0.0, "output_cost": 0.0, diff --git a/tests/unit/proxy/hooks/test_search_free_tier.py b/tests/unit/proxy/hooks/test_search_free_tier.py index 3dc89c0dc72..b57908378e5 100644 --- a/tests/unit/proxy/hooks/test_search_free_tier.py +++ b/tests/unit/proxy/hooks/test_search_free_tier.py @@ -31,9 +31,9 @@ class _BrokenCounter: raise ConnectionError("redis is down") -def _model_info(billing_unit: str, count: int, period: str = "month") -> dict: +def _model_info(billing_unit: str, count: int, period: str = "month", provider: str = "vertex_ai") -> dict: return { - "litellm_provider": "vertex_ai", + "litellm_provider": provider, "mode": "chat", "web_search_billing_unit": billing_unit, "search_context_cost_per_query": {"search_context_size_medium": RATE}, @@ -52,6 +52,7 @@ def _call(model_info: dict, response_cost: float, cache_hit: bool | None = None) sl_object = { "response_cost": response_cost, "cache_hit": cache_hit, + "custom_llm_provider": model_info["litellm_provider"], "cost_breakdown": {"input_cost": 0.1, "output_cost": 0.2, "tool_usage_cost": 0.5, "total_cost": response_cost}, "model_map_information": {"model_map_key": "gemini-test", "model_map_value": model_info}, } @@ -73,12 +74,12 @@ def test_freed_units_covers_only_what_landed_under_the_allowance(allowance, unit assert freed_units(allowance, units, total_after) == expected -def test_counter_key_is_per_group_and_utc_period(): - assert search_free_tier_key({"count": 1, "period": "month", "shared_group": "g3"}, NOW) == ( - "litellm:search_free_tier:g3:2026-10" +def test_counter_key_is_per_provider_group_and_utc_period(): + assert search_free_tier_key("gemini", {"count": 1, "period": "month", "shared_group": "g3"}, NOW) == ( + "litellm:search_free_tier:gemini:g3:2026-10" ) - assert search_free_tier_key({"count": 1, "period": "day", "shared_group": "g2"}, NOW) == ( - "litellm:search_free_tier:g2:2026-10-20" + assert search_free_tier_key("vertex_ai", {"count": 1, "period": "day", "shared_group": "g2"}, NOW) == ( + "litellm:search_free_tier:vertex_ai:g2:2026-10-20" ) @@ -107,8 +108,23 @@ async def test_per_query_allowance_is_shared_across_calls_and_split_on_the_cross assert c2 == k2 == s2 == pytest.approx(1.0 - 2 * RATE) assert b2["discount_amount"] == pytest.approx(2 * RATE) assert c3 == k3 == s3 == 1.0 and "discount_amount" not in b3 - assert counter.totals == {"litellm:search_free_tier:test-group:2026-10": 15} - assert counter.ttls["litellm:search_free_tier:test-group:2026-10"] > 0 + assert counter.totals == {"litellm:search_free_tier:vertex_ai:test-group:2026-10": 15} + assert counter.ttls["litellm:search_free_tier:vertex_ai:test-group:2026-10"] > 0 + + +@pytest.mark.asyncio +async def test_gemini_api_and_vertex_ai_grounding_draw_on_separate_allowances(): + counter = _Counter() + gemini_api = _model_info("per_query", count=3, provider="gemini") + vertex_ai = _model_info("per_query", count=3, provider="vertex_ai") + kwargs, sl_object = _call(gemini_api, response_cost=1.0) + await apply_search_free_tier(kwargs, sl_object, 1.0, _response(2), counter, NOW) + kwargs, sl_object = _call(vertex_ai, response_cost=1.0) + vertex_cost = await apply_search_free_tier(kwargs, sl_object, 1.0, _response(4), counter, NOW) + kwargs, sl_object = _call(gemini_api, response_cost=1.0) + gemini_cost = await apply_search_free_tier(kwargs, sl_object, 1.0, _response(1), counter, NOW) + assert vertex_cost == pytest.approx(1.0 - 3 * RATE), "vertex ai had its whole allowance left" + assert gemini_cost == pytest.approx(1.0 - RATE), "gemini api had one free query left" @pytest.mark.asyncio @@ -121,7 +137,7 @@ async def test_per_prompt_allowance_counts_a_grounded_prompt_once_whatever_the_q second = await apply_search_free_tier(kwargs, sl_object, 1.0, _response(5), counter, NOW) assert first == pytest.approx(1.0 - RATE) assert second == 1.0 - assert counter.totals == {"litellm:search_free_tier:test-group:2026-10-20": 2} + assert counter.totals == {"litellm:search_free_tier:vertex_ai:test-group:2026-10-20": 2} @pytest.mark.asyncio @@ -172,7 +188,7 @@ async def test_a_second_callback_run_on_the_same_request_counts_it_once(): first = await apply_search_free_tier(kwargs, sl_object, 1.0, _response(5), counter, NOW) second = await apply_search_free_tier(kwargs, sl_object, first, _response(5), counter, NOW) assert first == second == pytest.approx(1.0 - 5 * RATE) - assert counter.totals == {"litellm:search_free_tier:test-group:2026-10": 5} + assert counter.totals == {"litellm:search_free_tier:vertex_ai:test-group:2026-10": 5} @pytest.mark.asyncio @@ -191,4 +207,4 @@ async def test_freed_cost_never_exceeds_the_billed_cost(): kwargs, sl_object = _call(_model_info("per_query", count=100), response_cost=billed) assert await apply_search_free_tier(kwargs, sl_object, billed, _response(5), counter, NOW) == 0.0 assert sl_object["cost_breakdown"]["discount_amount"] == pytest.approx(billed) - assert counter.totals == {"litellm:search_free_tier:test-group:2026-10": 5} + assert counter.totals == {"litellm:search_free_tier:vertex_ai:test-group:2026-10": 5} From f9800f1fc08f06fd79a31e28afd6f5fe0d4e3f47 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 15:11:45 -0700 Subject: [PATCH 52/66] fix(proxy): price a 499 spend row only for the proxy's own disconnect, and never after the call already completed (#47652) * fix(proxy): price a 499 spend row only for the proxy's own disconnect, and never after the call already completed * fix(proxy): gate the zero-cost 499 row on the success log being enqueued, not merely claimed --------- Backport of #47652 to stable/1.104.x Cherry-picked from ffb7133d326e979506f17abee0412ca66de53d3a (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/litellm_core_utils/litellm_logging.py | 11 ++ litellm/proxy/utils.py | 11 +- litellm/utils.py | 1 + tests/test_litellm/proxy/test_proxy_utils.py | 117 ++++++++++++++++++ 4 files changed, 136 insertions(+), 4 deletions(-) diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py index 63ec230b6f7..2304189b363 100644 --- a/litellm/litellm_core_utils/litellm_logging.py +++ b/litellm/litellm_core_utils/litellm_logging.py @@ -711,6 +711,7 @@ class Logging(LiteLLMLoggingBaseClass): self._defer_async_logging: bool = False self._enqueue_deferred_logging: Callable[[], None] | None = None self._on_detached_stream_failure: Callable[[Exception], Awaitable[None]] | None = None + self._async_success_enqueued: bool = False self.shadow_eval_request_snapshot: GuardrailRequestSnapshot | None = None def set_response_timing_metrics(self, timing_metrics: Mapping[str, float]) -> None: @@ -2266,6 +2267,16 @@ class Logging(LiteLLMLoggingBaseClass): except Exception: return True + @property + def async_success_log_enqueued(self) -> bool: + """True once the success log task was actually created, not merely claimed, so a later failure raised + around it (a disconnect cancelling a still-pending guardrail task) must not bill the prompt a second + time. A claimed log parked in the deferred slot never runs once a 499 interrupts, so it stays False.""" + return self._async_success_enqueued + + def mark_async_success_log_enqueued(self) -> None: + self._async_success_enqueued = True + def has_run_logging( self, event_type: Literal["async_success", "sync_success", "async_failure", "sync_failure"], diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py index d8bbb7cc808..eb07c9e61c5 100644 --- a/litellm/proxy/utils.py +++ b/litellm/proxy/utils.py @@ -1302,8 +1302,9 @@ def _timed_out_reading_from_provider(exception: Exception) -> bool: def _client_disconnected(exception: Exception) -> bool: - """The 499 the proxy raises when the caller hung up while the provider was still working on the request.""" - return getattr(exception, "status_code", None) == LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED + """The 499 the proxy itself raises when the caller hung up while the provider was still working on the + request. A provider's own 499 arrives as a litellm exception and is a plain upstream failure.""" + return isinstance(exception, HTTPException) and exception.status_code == LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED def _provider_billed_the_failure(exception: Exception) -> bool: @@ -1325,17 +1326,19 @@ def _failure_fields_to_lift(request_data: Mapping[str, object], provider_billed: _litellm_params: Final = getattr(_logging_obj, "litellm_params", None) _base_model: Final = _get_base_model_from_metadata(model_call_details=_model_call_details) _deployment_id: Final = _logging_obj.get_router_model_id() if isinstance(_logging_obj, Logging) else None + _success_already_logged: Final = isinstance(_logging_obj, Logging) and _logging_obj.async_success_log_enqueued + _billed: Final = provider_billed and not _success_already_logged _usage_to_lift: Final = _failure_usage_to_lift( model_call_details=_model_call_details, request_body=request_data, dispatched=_first_handoff is not None, - provider_billed=provider_billed, + provider_billed=_billed, deployment_id=_deployment_id, base_model=_base_model, ) _prompt_estimate: Final = ( _estimated_prompt_usage(_model_call_details, request_data) - if provider_billed and _first_handoff is not None and not _model_call_details.get("failed_attempts_usage") + if _billed and _first_handoff is not None and not _model_call_details.get("failed_attempts_usage") else None ) _earlier_attempts: Final = ( diff --git a/litellm/utils.py b/litellm/utils.py index 6bd4c499b0c..9e93497f559 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -1365,6 +1365,7 @@ def _schedule_async_success_logging( """ def _enqueue_async_logging() -> None: + logging_obj.mark_async_success_log_enqueued() asyncio.create_task( _client_async_logging_helper( logging_obj=logging_obj, diff --git a/tests/test_litellm/proxy/test_proxy_utils.py b/tests/test_litellm/proxy/test_proxy_utils.py index 8064d9cee57..f03c5f57808 100644 --- a/tests/test_litellm/proxy/test_proxy_utils.py +++ b/tests/test_litellm/proxy/test_proxy_utils.py @@ -828,6 +828,123 @@ class TestPostCallFailureHookEstimatesDispatchedInputTokens: assert expected_input_cost > 0 assert request_data["response_cost"] == pytest.approx(expected_input_cost) + @pytest.mark.asyncio + async def test_upstream_499_error_is_a_plain_failure_not_a_priced_disconnect(self): + """A provider answering HTTP 499 surfaces as litellm.APIError with status_code 499. Only the + proxy's own disconnect HTTPException means the caller hung up mid-generation, so the upstream + error keeps the estimated usage at zero cost like any other post-dispatch provider error.""" + from datetime import datetime + + from litellm.constants import LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED + from litellm.types.utils import Usage + + request_data = { + "litellm_logging_obj": self._logging_obj( + { + "first_api_call_start_time": datetime(2026, 1, 1, 12, 0, 0), + "model": "gpt-3.5-turbo", + "messages": [{"role": "user", "content": "count these input tokens please"}], + "call_type": "acompletion", + } + ), + "metadata": {}, + } + await self._run( + request_data, + original_exception=litellm.APIError( + status_code=LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED, + message="client closed request", + llm_provider="openai", + model="gpt-3.5-turbo", + ), + ) + + estimated = request_data["combined_usage_object"] + assert isinstance(estimated, Usage) + assert estimated.prompt_tokens > 0 + assert request_data["response_cost"] == 0.0 + + @pytest.mark.asyncio + async def test_client_disconnect_after_the_call_already_completed_is_not_priced_again(self): + """The LLM task finished and claimed its success log (which carries the real usage and cost) + while a during_call guardrail task was still pending, then the caller hung up. The 499 raised + for that disconnect must not price the prompt a second time.""" + from datetime import datetime + + from fastapi import HTTPException + + from litellm.constants import LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED + from litellm.litellm_core_utils.litellm_logging import Logging + + logging_obj = Logging( + model="gpt-3.5-turbo", + messages=[{"role": "user", "content": "count these input tokens please"}], + stream=False, + call_type="acompletion", + start_time=datetime(2026, 1, 1, 12, 0, 0), + litellm_call_id="completed-before-disconnect", + function_id="fn", + ) + logging_obj.model_call_details.update( + { + "first_api_call_start_time": datetime(2026, 1, 1, 12, 0, 1), + "model": "gpt-3.5-turbo", + "messages": [{"role": "user", "content": "count these input tokens please"}], + "call_type": "acompletion", + } + ) + logging_obj.mark_async_success_log_enqueued() + request_data = {"litellm_logging_obj": logging_obj, "metadata": {}} + await self._run( + request_data, + original_exception=HTTPException( + status_code=LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED, detail="Client disconnected the request" + ), + ) + + assert request_data.get("response_cost", 0.0) == 0.0 + + @pytest.mark.asyncio + async def test_client_disconnect_with_a_claimed_but_deferred_success_log_is_still_priced(self): + """With a post_call guardrail registered the success log is claimed but parked in the deferred slot, + and a 499 raised before the flush means it never runs. Nothing else bills that request, so the + failure row keeps the estimated input cost.""" + from datetime import datetime + + from fastapi import HTTPException + + from litellm.constants import LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED + from litellm.litellm_core_utils.litellm_logging import Logging + + logging_obj = Logging( + model="gpt-3.5-turbo", + messages=[{"role": "user", "content": "count these input tokens please"}], + stream=False, + call_type="acompletion", + start_time=datetime(2026, 1, 1, 12, 0, 0), + litellm_call_id="deferred-success-never-flushed", + function_id="fn", + ) + logging_obj.model_call_details.update( + { + "first_api_call_start_time": datetime(2026, 1, 1, 12, 0, 1), + "model": "gpt-3.5-turbo", + "messages": [{"role": "user", "content": "count these input tokens please"}], + "call_type": "acompletion", + } + ) + logging_obj._defer_async_logging = True + logging_obj._enqueue_deferred_logging = lambda: None + request_data = {"litellm_logging_obj": logging_obj, "metadata": {}} + await self._run( + request_data, + original_exception=HTTPException( + status_code=LITELLM_HTTP_STATUS_CLIENT_DISCONNECTED, detail="Client disconnected the request" + ), + ) + + assert request_data["response_cost"] > 0.0 + @pytest.mark.asyncio async def test_client_disconnect_before_provider_handoff_is_not_priced(self): """A caller that hung up while the request was still in pre-call hooks never reached the From a8807fb0bb75034dcd86beed55625a4a1b5f2e7d Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 15:20:16 -0700 Subject: [PATCH 53/66] fix(router): price cost-based routing through model_info.base_model (#47617) * fix(router): price cost-based routing through model_info.base_model * fix(router): keep cost-based routing pricing helpers fully typed * fix(router): drop typing.cast from cost-based routing pricing helpers * fix(router): read the cost map through a typed accessor in cost-based routing * fix(router): avoid a Final rebind inside the cost-based routing loop * refactor(router): share deployment_pricing_models across spend, listing and cost-based routing * refactor(router): keep the /v1/models listing key inline, share pricing models for spend and routing * refactor(router): inline the deployment pricing-model wrapper in cost-based routing * refactor(router): read deployment pricing models through one shared helper deployment_pricing_models(deployment) now owns the model_info.base_model / litellm_params.base_model / litellm_params.model unpacking, used by cost-based routing and the /v1/models listing. pricing_models(base_model, model) stays for the failure-row spend estimate, which already holds the two names * refactor(router): share the str-keyed mapping validator with cost-based routing * ci: re-run after flaky test_aiohttp_transport read timeout in llms-providers --------- Backport of #47617 to stable/1.104.x Cherry-picked from 0c6731eb5c2cc2c07abddb177cffef3a5b273dfe (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/proxy/utils.py | 5 +- litellm/router.py | 17 ++---- litellm/router_strategy/lowest_cost.py | 33 ++++++++++-- litellm/router_utils/deployment_pricing.py | 37 +++++++++++++ .../unit/router_strategy/test_lowest_cost.py | 46 ++++++++++++++++ .../router_utils/test_deployment_pricing.py | 53 +++++++++++++++++++ 6 files changed, 172 insertions(+), 19 deletions(-) create mode 100644 litellm/router_utils/deployment_pricing.py create mode 100644 tests/unit/router_utils/test_deployment_pricing.py diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py index eb07c9e61c5..f34af11b3c6 100644 --- a/litellm/proxy/utils.py +++ b/litellm/proxy/utils.py @@ -239,6 +239,7 @@ from litellm.repositories.verification_token_repository import ( VerificationTokenRepository, ) from litellm.router_utils.common_utils import resolve_model_group_alias +from litellm.router_utils.deployment_pricing import pricing_models from litellm.secret_managers.main import str_to_bool from litellm.types.integrations.slack_alerting import DEFAULT_ALERT_TYPES from litellm.types.llms.openai import ResponsesAPIResponse @@ -1160,9 +1161,9 @@ def _estimated_input_cost( deployment_pricing: Final = deployment_pricing_model_info(model_id=deployment_id, deployment_model=model) if deployment_pricing is not None: return _deployment_priced_input_cost(model, custom_llm_provider, prompt_tokens, deployment_pricing) - pricing_models: Final = (base_model, model) if base_model is not None else (model,) + pricing_models_to_try: Final = pricing_models(base_model, model) candidate_costs: Final = ( - _priced_input_cost(pricing_model, custom_llm_provider, prompt_tokens) for pricing_model in pricing_models + _priced_input_cost(pricing_model, custom_llm_provider, prompt_tokens) for pricing_model in pricing_models_to_try ) return next((cost for cost in candidate_costs if cost is not None), 0.0) diff --git a/litellm/router.py b/litellm/router.py index 8539071d85f..06bc4007767 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -199,6 +199,7 @@ from litellm.router_utils.cooldown_handlers import ( is_background_response_cost_poll_not_found, is_caller_timeout_408, ) +from litellm.router_utils.deployment_pricing import deployment_pricing_models from litellm.router_utils.fallback_event_handlers import ( MID_STREAM_FALLBACK_CONTROLS_KEY, AttemptedFallbackTargets, @@ -10311,19 +10312,9 @@ class Router: ) for deployment in deployments ) - params: Final = tuple(deployment.get("litellm_params") or MappingProxyType({}) for deployment in deployments) - # base_model resolution mirrors get_router_model_info: unset or blank means the - # deployment's own model name is the cost-map key. - cost_map_keys: Final = tuple( - dict.fromkeys( # deduplicates while preserving config order - key - for key in ( - model_info.get("base_model") or litellm_params.get("base_model") or litellm_params.get("model") - for model_info, litellm_params in zip(model_infos, params) - ) - if isinstance(key, str) and key - ) - ) + raw_deployments: Final[tuple[object, ...]] = deployments + pricing_keys: Final = (deployment_pricing_models(deployment) for deployment in raw_deployments) + cost_map_keys: Final = tuple(dict.fromkeys(keys[0] for keys in pricing_keys if keys)) return DeploymentModelListingInfo( cost_map_keys=cost_map_keys, max_input_tokens=self._widest_configured_limit(model_infos, "max_input_tokens"), diff --git a/litellm/router_strategy/lowest_cost.py b/litellm/router_strategy/lowest_cost.py index 22c321c65fb..1659f959a14 100644 --- a/litellm/router_strategy/lowest_cost.py +++ b/litellm/router_strategy/lowest_cost.py @@ -1,5 +1,6 @@ #### What this does #### # picks based on response time (for streaming, this is time to first token) +from collections.abc import Mapping from datetime import datetime from typing import Final @@ -9,6 +10,30 @@ from litellm._logging import verbose_router_logger from litellm.caching.caching import DualCache from litellm.integrations.custom_logger import CustomLogger from litellm.router_utils.batch_utils import is_batch_retrieve_call_type +from litellm.router_utils.deployment_pricing import deployment_pricing_models, str_keyed + + +def _deployment_cost_map_rates(deployment: object) -> tuple[float | None, float | None]: + """Input and output per-token prices from the first cost-map row among the deployment's + pricing models that carries one; (None, None) when no row does, so the caller falls back to + its unmapped default.""" + rows: Final = (str_keyed(_cost_map().get(model)) for model in deployment_pricing_models(deployment)) + row: Final = next((row for row in rows if _declares_token_price(row)), None) + if row is None: + return None, None + return _as_rate(row.get("input_cost_per_token")), _as_rate(row.get("output_cost_per_token")) + + +def _cost_map() -> Mapping[str, object]: + return litellm.model_cost + + +def _declares_token_price(row: Mapping[str, object]) -> bool: + return row.get("input_cost_per_token") is not None or row.get("output_cost_per_token") is not None + + +def _as_rate(value: object) -> float | None: + return float(value) if isinstance(value, (int, float)) and not isinstance(value, bool) else None class LowestCostLoggingHandler(CustomLogger): @@ -239,8 +264,8 @@ class LowestCostLoggingHandler(CustomLogger): or _deployment.get("model_info", {}).get("rpm", None) or float("inf") ) - item_litellm_model_name = _deployment.get("litellm_params", {}).get("model") - item_litellm_model_cost_map = litellm.model_cost.get(item_litellm_model_name, {}) + deployment_view: object = _deployment + map_input_cost, map_output_cost = _deployment_cost_map_rates(deployment_view) # check if user provided input_cost_per_token and output_cost_per_token in litellm_params item_input_cost = None @@ -252,10 +277,10 @@ class LowestCostLoggingHandler(CustomLogger): item_output_cost = _deployment.get("litellm_params", {}).get("output_cost_per_token") if item_input_cost is None: - item_input_cost = item_litellm_model_cost_map.get("input_cost_per_token", 5.0) + item_input_cost = map_input_cost if map_input_cost is not None else 5.0 if item_output_cost is None: - item_output_cost = item_litellm_model_cost_map.get("output_cost_per_token", 5.0) + item_output_cost = map_output_cost if map_output_cost is not None else 5.0 # if litellm["model"] is not in model_cost map -> use item_cost = $10 diff --git a/litellm/router_utils/deployment_pricing.py b/litellm/router_utils/deployment_pricing.py new file mode 100644 index 00000000000..622cc91ab5e --- /dev/null +++ b/litellm/router_utils/deployment_pricing.py @@ -0,0 +1,37 @@ +from collections.abc import Iterator, Mapping +from types import MappingProxyType +from typing import Final + +from pydantic import TypeAdapter, ValidationError + +_EMPTY: Final[Mapping[str, object]] = MappingProxyType({}) +_STR_KEYED: Final = TypeAdapter(dict[str, object]) + + +def pricing_models(base_model: object, model: object) -> tuple[str, ...]: + """Cost-map keys to price a deployment under, ``model_info.base_model`` first, then the + deployment's own model, blanks and duplicates dropped. Every spend and routing surface that + prices a deployment walks this order, so a ``base_model`` the cost map does not know falls + through to the deployment model instead of billing or ranking at the unmapped default.""" + return tuple(dict.fromkeys(_named_models(base_model, model))) + + +def deployment_pricing_models(deployment: object) -> tuple[str, ...]: + """``pricing_models`` read off a raw deployment dict (``model_info.base_model``, then + ``litellm_params.base_model``, then ``litellm_params.model``); malformed blocks count as unset.""" + view: Final = str_keyed(deployment) + params: Final = str_keyed(view.get("litellm_params")) + info: Final = str_keyed(view.get("model_info")) + return pricing_models(info.get("base_model") or params.get("base_model"), params.get("model")) + + +def _named_models(*candidates: object) -> Iterator[str]: + return (candidate for candidate in candidates if isinstance(candidate, str) and candidate) + + +def str_keyed(value: object) -> Mapping[str, object]: + """``value`` as a read-only str-keyed mapping, empty when it is not a dict.""" + try: + return MappingProxyType(_STR_KEYED.validate_python(value)) + except ValidationError: + return _EMPTY diff --git a/tests/unit/router_strategy/test_lowest_cost.py b/tests/unit/router_strategy/test_lowest_cost.py index ab3ef099410..4f7259178f6 100644 --- a/tests/unit/router_strategy/test_lowest_cost.py +++ b/tests/unit/router_strategy/test_lowest_cost.py @@ -101,3 +101,49 @@ async def test_async_log_success_event_counts_a_response_with_no_completion_toke ) assert _recorded_minute_counters(cache) == {"tpm": 12, "rpm": 1} + + + + + + + + + +_TWO_DOLLARS_PER_TOKEN = {"input_cost_per_token": 1.0, "output_cost_per_token": 1.0} + + +@pytest.mark.asyncio +@pytest.mark.parametrize( + "azure_litellm_params, base_model", + [ + ({"model": "azure/my-gpt4-deploy"}, "azure/gpt-4.1"), + ({"model": "azure/gpt-4.1"}, "azure/not-a-real-model"), + ], + ids=["base_model_priced", "unmapped_base_model_falls_back_to_deployment_model"], +) +async def test_cost_based_routing_prices_an_azure_deployment_through_its_base_model( + azure_litellm_params: dict, base_model: str +): + handler = LowestCostLoggingHandler(router_cache=DualCache()) + healthy_deployments = [ + { + "model_name": "gpt-4.1", + "litellm_params": {"model": "openai/gpt-4.1", **_TWO_DOLLARS_PER_TOKEN}, + "model_info": {"id": "openai-two-dollars"}, + }, + { + "model_name": "gpt-4.1", + "litellm_params": azure_litellm_params, + "model_info": {"id": "azure-cost-map-priced", "base_model": base_model}, + }, + ] + + picked = await handler.async_get_available_deployments( + model_group="gpt-4.1", healthy_deployments=healthy_deployments + ) + + assert picked is not None and picked["model_info"]["id"] == "azure-cost-map-priced", ( + "a cost-map priced Azure deployment must beat a $2 per token deployment, " + "it loses only when it is scored at the $10 unmapped default" + ) diff --git a/tests/unit/router_utils/test_deployment_pricing.py b/tests/unit/router_utils/test_deployment_pricing.py new file mode 100644 index 00000000000..45cc211a89c --- /dev/null +++ b/tests/unit/router_utils/test_deployment_pricing.py @@ -0,0 +1,53 @@ +import pytest + +from litellm.router_utils.deployment_pricing import deployment_pricing_models, pricing_models + + +@pytest.mark.parametrize( + "base_model, model, expected", + [ + ("azure/gpt-4.1", "azure/my-gpt4-deploy", ("azure/gpt-4.1", "azure/my-gpt4-deploy")), + (None, "azure/my-gpt4-deploy", ("azure/my-gpt4-deploy",)), + ("", "azure/my-gpt4-deploy", ("azure/my-gpt4-deploy",)), + ("azure/gpt-4.1", "azure/gpt-4.1", ("azure/gpt-4.1",)), + (None, None, ()), + ], + ids=["base_model_first", "no_base_model", "blank_base_model", "same_name_once", "nothing_named"], +) +def test_pricing_models_walks_base_model_then_deployment_model(base_model, model, expected): + assert pricing_models(base_model, model) == expected + + +@pytest.mark.parametrize( + "deployment, expected", + [ + ( + {"litellm_params": {"model": "azure/my-gpt4-deploy"}, "model_info": {"base_model": "azure/gpt-4.1"}}, + ("azure/gpt-4.1", "azure/my-gpt4-deploy"), + ), + ( + {"litellm_params": {"model": "azure/my-gpt4-deploy", "base_model": "azure/gpt-4.1"}}, + ("azure/gpt-4.1", "azure/my-gpt4-deploy"), + ), + ( + { + "litellm_params": {"model": "azure/my-gpt4-deploy", "base_model": "azure/gpt-4o"}, + "model_info": {"base_model": "azure/gpt-4.1"}, + }, + ("azure/gpt-4.1", "azure/my-gpt4-deploy"), + ), + ({"litellm_params": {"model": "openai/gpt-4.1"}, "model_info": {}}, ("openai/gpt-4.1",)), + ({"litellm_params": "not-a-dict", "model_info": None}, ()), + ("not-a-deployment", ()), + ], + ids=[ + "model_info_base_model", + "params_base_model", + "model_info_wins", + "no_base_model", + "malformed_blocks", + "not_a_dict", + ], +) +def test_deployment_pricing_models_reads_the_deployment_dict(deployment, expected): + assert deployment_pricing_models(deployment) == expected From 5a34391482e1a5141df562a468a5737e6c91b4b5 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 15:26:09 -0700 Subject: [PATCH 54/66] fix(proxy): price earlier timed-out retry attempts at their own deployment's model rate (#47648) * fix(proxy): bill every earlier timed-out retry attempt at its own deployment's model rate * fix(router): read the retry record's base_model through the typed metadata helper * fix(router): keep the four-record retry breadcrumb cap * fix(router): carry a deployment's litellm_params base_model on its retry record * chore(router): place the cast-ok reason on the cast line and list the base_model helper as covered through log_retry --------- Backport of #47648 to stable/1.104.x Cherry-picked from 27efc387f7cc6bf36cacbf6eb88e39e488d240e7 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/proxy/utils.py | 56 +++++++++++---- litellm/router.py | 21 +++++- litellm/types/router.py | 2 + .../router_code_coverage.py | 1 + .../test_router_helper_utils.py | 41 ++++++++++- tests/test_litellm/proxy/test_proxy_utils.py | 68 +++++++++++++++++++ tests/unit/test_router/test_router.py | 2 +- 7 files changed, 174 insertions(+), 17 deletions(-) diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py index f34af11b3c6..6a03bc7ad83 100644 --- a/litellm/proxy/utils.py +++ b/litellm/proxy/utils.py @@ -1076,6 +1076,43 @@ def _timed_out_earlier_records( return tuple(record for identity, record in by_identity.items() if identity != final_identity) +def _record_pricing( + model_call_details: Mapping[str, object], record: Mapping[str, object], base_model: str | None +) -> tuple[Mapping[str, object], str | None]: + """The ``(model_call_details, base_model)`` to price one earlier attempt with: the record's own + deployment model and ``base_model`` when it served a different model than the final attempt + (the provider is then inferred from that model), else the final attempt's.""" + record_model: Final = record.get("model") + if not isinstance(record_model, str) or record_model == model_call_details.get("model"): + return model_call_details, base_model + record_base_model: Final = record.get("base_model") + return ( + {**model_call_details, "model": record_model, "custom_llm_provider": None}, + record_base_model if isinstance(record_base_model, str) else None, + ) + + +def _billed_earlier_attempt( + model_call_details: Mapping[str, object], + record: Mapping[str, object], + index: int, + estimated_usage: Usage, + base_model: str | None, +) -> BilledFailedAttempt: + pricing_details, pricing_base_model = _record_pricing(model_call_details, record, base_model) + return BilledFailedAttempt( + attempted_retries=_attempt_number(record, index), + deployment_id=_record_deployment_id(record), + usage=estimated_usage, + response_cost=_estimated_input_cost( + pricing_details, + estimated_usage.prompt_tokens, + deployment_id=_record_deployment_id(record), + base_model=pricing_base_model, + ), + ) + + def _billed_earlier_attempts( model_call_details: Mapping[str, object], litellm_params: Mapping[str, object] | None, @@ -1089,23 +1126,14 @@ def _billed_earlier_attempts( request's own deployment and retry count (``attempted_retries`` restarts at 0 after a fallback hop, so the count alone cannot tell the groups apart). An earlier attempt that ended in a ``Timeout`` had the same prompt accepted by its deployment, so it is billed like the final - attempt, at that deployment's input rate (else the cost map's rate for ``base_model`` or the - model). Only the exception class survives on the record, so an earlier connect timeout is - billed too; any other failure class is not.""" + attempt, at that deployment's input rate (else the cost map's rate for the record's own + ``base_model`` or model, which a fallback hop can make a different model than the final one). + Only the exception class survives on the record, so an earlier connect timeout is billed too; + any other failure class is not.""" final_attempt: Final = _retry_metadata_bucket(litellm_params).get("attempted_retries") final_identity: Final = (deployment_id, final_attempt if isinstance(final_attempt, int) else None) return tuple( - BilledFailedAttempt( - attempted_retries=_attempt_number(record, index), - deployment_id=_record_deployment_id(record), - usage=estimated_usage, - response_cost=_estimated_input_cost( - model_call_details, - estimated_usage.prompt_tokens, - deployment_id=_record_deployment_id(record), - base_model=base_model, - ), - ) + _billed_earlier_attempt(model_call_details, record, index, estimated_usage, base_model) for index, record in enumerate(_timed_out_earlier_records(litellm_params, final_identity)) ) diff --git a/litellm/router.py b/litellm/router.py index 06bc4007767..a164db71c97 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -8336,17 +8336,24 @@ class Router: When a retry or fallback happens, record which model group, deployment and attempt just failed and why, and count it toward the request-wide num_retries_per_request cap """ + from litellm.litellm_core_utils.get_litellm_params import _get_base_model_from_litellm_call_metadata from litellm.types.router import RetryAttemptRecord _metadata_var: Final = "litellm_metadata" if "litellm_metadata" in kwargs else "metadata" - request_metadata: Final[Mapping[str, object]] = kwargs[_metadata_var] + request_metadata: Final = cast("Mapping[str, object]", kwargs[_metadata_var]) # cast-ok: untyped kwargs model_group: Final = kwargs.get("model") model_info: Final = request_metadata.get("model_info") deployment_id: Final = model_info.get("id") if isinstance(model_info, Mapping) else None + base_model: Final = _get_base_model_from_litellm_call_metadata( + metadata=request_metadata + ) or self._deployment_params_base_model(deployment_id if isinstance(deployment_id, str) else None) + deployment_model: Final = request_metadata.get("deployment") attempted_retries: Final = request_metadata.get("attempted_retries") attempt_record: Final[RetryAttemptRecord] = { "model_group": model_group if isinstance(model_group, str) else None, "deployment_id": deployment_id if isinstance(deployment_id, str) else None, + "model": deployment_model if isinstance(deployment_model, str) else None, + "base_model": base_model if isinstance(base_model, str) else None, "exception_type": type(e).__name__, "exception_string": str(e), "attempted_retries": attempted_retries if type(attempted_retries) is int else None, @@ -8364,6 +8371,18 @@ class Router: kwargs[_metadata_var]["request_retry_count"] = request_retry_count # rebind-ok: same dict, read by the cap return kwargs + def _deployment_params_base_model(self, deployment_id: str | None) -> str | None: + """The ``base_model`` a deployment declares under ``litellm_params`` (the Azure named-deployment + shape), the same key the success path's ``get_base_model_from_metadata`` reads.""" + deployment: Final = self.get_deployment(model_id=deployment_id) if deployment_id is not None else None + if deployment is None: + return None + extra_params: Final = cast( # cast-ok: pydantic extras are untyped, base_model is isinstance-checked below + "Mapping[str, object]", deployment.litellm_params.model_extra or {} + ) + base_model: Final = extra_params.get("base_model") + return base_model if isinstance(base_model, str) else None + def _update_usage(self, deployment_id: str, parent_otel_span: Span | None) -> int: """ Update deployment rpm for that minute diff --git a/litellm/types/router.py b/litellm/types/router.py index b2464d83944..473f02058a3 100644 --- a/litellm/types/router.py +++ b/litellm/types/router.py @@ -1001,6 +1001,8 @@ class RouterModelGroupAliasItem(TypedDict): class RetryAttemptRecord(TypedDict): model_group: ReadOnly[str | None] deployment_id: ReadOnly[str | None] + model: ReadOnly[str | None] + base_model: ReadOnly[str | None] exception_type: ReadOnly[str] exception_string: ReadOnly[str] attempted_retries: ReadOnly[int | None] diff --git a/tests/code_coverage_tests/router_code_coverage.py b/tests/code_coverage_tests/router_code_coverage.py index 06e5b020836..9c841087b9a 100644 --- a/tests/code_coverage_tests/router_code_coverage.py +++ b/tests/code_coverage_tests/router_code_coverage.py @@ -87,6 +87,7 @@ ignored_function_names = [ "_resolve_claude_code_session_router", # Tested through Claude Code session routing in test_router.py "_get_claude_code_session_router_binding", # Tested through the two-worker session routing test in test_router.py "_apply_updated_routing_strategy_args", # Tested via update_settings in test_lowest_latency.py (file lacks "router" in name) + "_deployment_params_base_model", # Tested through log_retry in test_router_helper_utils.py ] diff --git a/tests/router_unit_tests/test_router_helper_utils.py b/tests/router_unit_tests/test_router_helper_utils.py index d3ad1d989c8..cabee3dcfd9 100644 --- a/tests/router_unit_tests/test_router_helper_utils.py +++ b/tests/router_unit_tests/test_router_helper_utils.py @@ -637,7 +637,12 @@ def test_log_retry(model_list: list[DeploymentTypedDict], metadata_key: str) -> "model": "gpt-3.5-turbo", "api_key": "sk-must-not-be-recorded", "messages": [{"role": "user", "content": "hi"}], - metadata_key: {"model_info": {"id": "deployment-1"}, "attempted_retries": 2, "user_api_key": "sk-proxy"}, + metadata_key: { + "model_info": {"id": "deployment-1", "base_model": "azure/gpt-3.5-turbo"}, + "deployment": "azure/my-35-deployment", + "attempted_retries": 2, + "user_api_key": "sk-proxy", + }, }, e=rate_limit_error, ) @@ -645,6 +650,8 @@ def test_log_retry(model_list: list[DeploymentTypedDict], metadata_key: str) -> { "model_group": "gpt-3.5-turbo", "deployment_id": "deployment-1", + "model": "azure/my-35-deployment", + "base_model": "azure/gpt-3.5-turbo", "exception_type": "RateLimitError", "exception_string": "litellm.RateLimitError: slow down", "attempted_retries": 2, @@ -656,6 +663,38 @@ def test_log_retry(model_list: list[DeploymentTypedDict], metadata_key: str) -> assert router.log_retry(kwargs=planted_kwargs, e=rate_limit_error)[metadata_key]["request_retry_count"] == 1 +def test_log_retry_reads_base_model_from_the_deployments_litellm_params() -> None: + """An Azure named deployment declares ``base_model`` under ``litellm_params``, not ``model_info``, and + that is the model the failure row is priced at, so the retry record has to carry it too""" + router = Router( + model_list=[ + { + "model_name": "azure-group", + "litellm_params": { + "model": "azure/my-named-deployment", + "api_key": "sk-fake", + "api_base": "https://example.openai.azure.com", + "base_model": "azure/gpt-4o-mini", + }, + "model_info": {"id": "dep-azure-named"}, + } + ] + ) + new_kwargs = router.log_retry( + kwargs={ + "model": "azure-group", + "metadata": { + "model_info": {"id": "dep-azure-named"}, + "deployment": "azure/my-named-deployment", + "attempted_retries": 0, + }, + }, + e=litellm.Timeout(message="slow", llm_provider="azure", model="azure/my-named-deployment"), + ) + record = new_kwargs["metadata"]["previous_models"][0] + assert (record["model"], record["base_model"]) == ("azure/my-named-deployment", "azure/gpt-4o-mini") + + def test_update_usage(model_list): """Test if the '_update_usage' function is working correctly""" router = Router(model_list=model_list) diff --git a/tests/test_litellm/proxy/test_proxy_utils.py b/tests/test_litellm/proxy/test_proxy_utils.py index f03c5f57808..5f9542cd3f8 100644 --- a/tests/test_litellm/proxy/test_proxy_utils.py +++ b/tests/test_litellm/proxy/test_proxy_utils.py @@ -2320,6 +2320,74 @@ def test_every_earlier_timed_out_attempt_is_billed_at_its_own_deployment_rate(mo assert all(a.usage is usage for a in attempts) +def test_an_earlier_attempt_on_another_model_is_priced_at_that_models_rate_not_the_final_models(monkeypatch): + """After a fallback hop the final attempt runs on another model group, so the records of the group + that timed out first name their own deployment model (and its ``base_model`` when the deployment + name is not in the cost map). Each is billed at that model's input rate, not at the final model's.""" + from litellm.proxy.utils import _billed_earlier_attempts + + for pricing_model, provider, input_rate in ( + ("lit145-final-model", "openai", 0.5), + ("lit145-first-model", "openai", 0.02), + ("azure/lit145-first-model", "azure", 0.02), + ): + monkeypatch.setitem( + litellm.model_cost, + pricing_model, + {"litellm_provider": provider, "mode": "chat", "input_cost_per_token": input_rate, "output_cost_per_token": 1.0}, + ) + usage = litellm.Usage(prompt_tokens=24, completion_tokens=0, total_tokens=24) + + attempts = _billed_earlier_attempts( + model_call_details={"model": "openai/lit145-final-model", "custom_llm_provider": "openai"}, + litellm_params={ + "metadata": { + "attempted_retries": 1, + "model_info": {"id": "dep-lit145-final"}, + "previous_models": ( + { + "deployment_id": "dep-lit145-first", + "model": "openai/lit145-first-model", + "base_model": None, + "exception_type": "Timeout", + "attempted_retries": 0, + }, + { + "deployment_id": "dep-lit145-first-azure", + "model": "azure/lit145-first-deployment", + "base_model": "azure/lit145-first-model", + "exception_type": "Timeout", + "attempted_retries": 1, + }, + { + "deployment_id": "dep-lit145-final", + "model": "openai/lit145-final-model", + "base_model": None, + "exception_type": "Timeout", + "attempted_retries": 0, + }, + { + "deployment_id": "dep-lit145-final", + "model": "openai/lit145-final-model", + "base_model": None, + "exception_type": "Timeout", + "attempted_retries": 1, + }, + ), + } + }, + estimated_usage=usage, + base_model=None, + deployment_id="dep-lit145-final", + ) + + assert [(a.attempted_retries, a.deployment_id, a.response_cost) for a in attempts] == [ + (0, "dep-lit145-first", pytest.approx(24 * 0.02)), + (1, "dep-lit145-first-azure", pytest.approx(24 * 0.02)), + (0, "dep-lit145-final", pytest.approx(24 * 0.5)), + ] + + def test_earlier_attempts_are_priced_from_the_prompt_estimate_not_the_final_streams_recovered_usage(): """A final attempt whose stream broke mid-flight lifts its recovered usage (prompt plus the chunks delivered); the earlier timed-out attempts never produced output, so they are priced from the diff --git a/tests/unit/test_router/test_router.py b/tests/unit/test_router/test_router.py index 1437f54cc68..c0266492b1e 100644 --- a/tests/unit/test_router/test_router.py +++ b/tests/unit/test_router/test_router.py @@ -11833,7 +11833,7 @@ async def test_cyclic_fallback_graph_does_not_amplify_one_request(): _FLAT_ATTEMPT_RECORD_KEYS = frozenset( - {"model_group", "deployment_id", "exception_type", "exception_string", "attempted_retries"} + {"model_group", "deployment_id", "model", "base_model", "exception_type", "exception_string", "attempted_retries"} ) _BREADCRUMB_CREDENTIAL_CANARY = "Bearer sk-ant-oat01-RETRY-BREADCRUMB-CANARY-doNotShip" From 2313d343ba17f2999340541bb76a2f0389a5c0bd Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Tue, 20 Oct 2026 15:28:19 -0700 Subject: [PATCH 55/66] fix(logging): spilled over PTU requests without base_model log the served model's rates (#47655) * fix(logging): report pay-as-you-go rates for spilled over PTU requests without base_model * fix(logging): keep the provider response model so spilled over PTU payloads price the served model * fix(logging): keep a provider_response_model the response already carries * fix(logging): read the carried provider_response_model through a typed adapter --------- Backport of #47655 to stable/1.104.x Cherry-picked from 6b1f4ed46f5fd81ed55a49ba61563587acc72bd7 (main) Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/litellm_core_utils/litellm_logging.py | 30 ++++++----- .../llm_response_utils/response_metadata.py | 29 +++++++++++ .../test_response_metadata.py | 36 +++++++++++++ .../test_litellm_logging.py | 51 ++++++++++++++++++- 4 files changed, 132 insertions(+), 14 deletions(-) diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py index 2304189b363..0f3cc84b126 100644 --- a/litellm/litellm_core_utils/litellm_logging.py +++ b/litellm/litellm_core_utils/litellm_logging.py @@ -2047,20 +2047,23 @@ class Logging(LiteLLMLoggingBaseClass): usage=usage, ) - def custom_pricing_for(self, result: object) -> bool: - litellm_params: Final = getattr(self, "litellm_params", None) + def spilled_over_ptu_for(self, result: object) -> bool: result_hidden_params: Final = getattr(result, "_hidden_params", None) or MappingProxyType({}) additional_headers: Final = ( result_hidden_params.get("additional_headers") if isinstance(result_hidden_params, dict) else getattr(result_hidden_params, "additional_headers", None) ) - spilled_over: Final = is_spilled_over_ptu_request( - model_info=_deployment_model_info(litellm_params), + return is_spilled_over_ptu_request( + model_info=_deployment_model_info(getattr(self, "litellm_params", None)), response_headers=self.model_call_details.get("response_headers"), additional_headers=additional_headers, ) - return False if spilled_over else use_custom_pricing_for_model(litellm_params=litellm_params) + + def custom_pricing_for(self, result: object) -> bool: + if self.spilled_over_ptu_for(result): + return False + return use_custom_pricing_for_model(litellm_params=getattr(self, "litellm_params", None)) def _prompt_for_cost_calculation(self) -> str: """ @@ -6530,13 +6533,16 @@ def get_standard_logging_object_payload( ) ## Get model cost information ## - base_model = _get_base_model_from_metadata(model_call_details=kwargs) - # The router overrides completion_response.model to the model-group alias before - # this payload is built, so cost-map lookup via that alias always misses. - # Fall back to the actual deployment model set by the router in metadata. - if base_model is None: - base_model = metadata.get("deployment") - custom_pricing: Final = logging_obj.custom_pricing_for(init_response_obj) + configured_base_model: Final = _get_base_model_from_metadata(model_call_details=kwargs) + spilled_over: Final = logging_obj.spilled_over_ptu_for(init_response_obj) + # The router overrides completion_response.model to the model-group alias before this payload is + # built, so cost-map lookup via that alias misses and the deployment model stands in for base_model. + # A PTU request Azure spilled onto pay-as-you-go capacity is billed at the served model's rates, + # which the deployment's zeroed PTU entry would misreport, so that fallback is skipped there. + base_model: Final = ( + metadata.get("deployment") if configured_base_model is None and not spilled_over else configured_base_model + ) + custom_pricing: Final = False if spilled_over else logging_obj.custom_pricing_for(init_response_obj) raw_response_cost: Final = kwargs.get("response_cost") llm_response_cost: Final[float] = raw_response_cost or 0.0 guardrail_cost: Final = guardrail_information_cost(metadata.get("standard_logging_guardrail_information")) diff --git a/litellm/litellm_core_utils/llm_response_utils/response_metadata.py b/litellm/litellm_core_utils/llm_response_utils/response_metadata.py index 503814cc143..6c38a6ba2d1 100644 --- a/litellm/litellm_core_utils/llm_response_utils/response_metadata.py +++ b/litellm/litellm_core_utils/llm_response_utils/response_metadata.py @@ -4,6 +4,7 @@ from functools import reduce from typing import Final import httpx +from pydantic import TypeAdapter, ValidationError from litellm.constants import LITELLM_DETAILED_TIMING from litellm.litellm_core_utils.core_helpers import get_litellm_metadata_from_kwargs, process_response_headers @@ -101,6 +102,32 @@ def response_timing_metrics( return {"_response_ms": total_response_time_ms, "litellm_overhead_time_ms": overhead_ms} +_HIDDEN_PARAMS_DICT: Final = TypeAdapter(dict[str, object]) + + +def _hidden_params_mapping(hidden_params: object) -> Mapping[str, object]: + try: + return _HIDDEN_PARAMS_DICT.validate_python(hidden_params) + except ValidationError: + return {} + + +def _existing_provider_response_model(result: object) -> str | None: + """The pricing model a response already carries, like the decisions path sets, wins over the response model.""" + hidden_params: Final[object] = getattr(result, "_hidden_params", None) + carried: Final[object] = _hidden_params_mapping(hidden_params).get("provider_response_model") or getattr( + hidden_params, "provider_response_model", None + ) + return carried if isinstance(carried, str) and carried else None + + +def _provider_response_model(result: object) -> str | None: + """The model the provider answered with, kept because the proxy later rewrites ``result.model`` to the alias the + client asked for and cost-map lookups for the standard logging payload would otherwise miss.""" + model: Final = getattr(result, "model", None) if isinstance(result, ModelResponse) else None + return model if isinstance(model, str) and model else None + + class ResponseMetadata: """ Handles setting and managing `_hidden_params`, `response_time_ms`, and `litellm_overhead_time_ms` for LiteLLM responses @@ -133,6 +160,8 @@ class ResponseMetadata: preserve_litellm_internal_headers=True, ), "litellm_model_name": model, + "provider_response_model": _existing_provider_response_model(self.result) + or _provider_response_model(self.result), } self._update_hidden_params(new_params) diff --git a/tests/unit/litellm_core_utils/llm_response_utils/test_response_metadata.py b/tests/unit/litellm_core_utils/llm_response_utils/test_response_metadata.py index 6f297e6e06a..3f63394b2f5 100644 --- a/tests/unit/litellm_core_utils/llm_response_utils/test_response_metadata.py +++ b/tests/unit/litellm_core_utils/llm_response_utils/test_response_metadata.py @@ -17,6 +17,7 @@ import pytest import litellm import litellm.litellm_core_utils.llm_response_utils.response_metadata as response_metadata_mod import litellm.proxy.common_request_processing as common_request_processing_mod +from litellm.cost_calculator import _select_model_name_for_cost_calc from litellm.litellm_core_utils.litellm_logging import Logging from litellm.litellm_core_utils.llm_response_utils.response_metadata import ( ResponseMetadata, @@ -651,3 +652,38 @@ def test_update_response_metadata_prices_per_second_deployment_from_its_stamped_ assert result._response_ms == pytest.approx(2000) assert result._hidden_params["response_cost"] == pytest.approx((0.02 + 0.04) * 2) + + +def test_update_response_metadata_keeps_the_provider_model_after_the_proxy_rewrites_response_model(): + start_time: Final = datetime.datetime(2026, 9, 21, 12, 0, 0) + logging_obj: Final = Logging( + model="azure/ptu-deployment", + messages=[{"role": "user", "content": "Hello"}], + stream=False, + call_type="completion", + start_time=start_time, + litellm_call_id="provider-model-response-metadata", + function_id="f", + ) + logging_obj.update_environment_variables( + model="azure/ptu-deployment", litellm_params={}, optional_params={}, custom_llm_provider="azure" + ) + result: Final = ModelResponse( + model="gpt-5.4-nano-2026-03-17", + usage=Usage(prompt_tokens=11, completion_tokens=7, total_tokens=18), + ) + + update_response_metadata( + result=result, + logging_obj=logging_obj, + model="azure/ptu-deployment", + kwargs={}, + start_time=start_time, + end_time=start_time + datetime.timedelta(seconds=2), + ) + result.model = "model-group-alias" + + assert ( + _select_model_name_for_cost_calc(model=None, completion_response=result, custom_llm_provider="azure") + == "azure/gpt-5.4-nano-2026-03-17" + ) diff --git a/tests/unit/litellm_core_utils/test_litellm_logging.py b/tests/unit/litellm_core_utils/test_litellm_logging.py index c6f624c26e6..17bc284cc50 100644 --- a/tests/unit/litellm_core_utils/test_litellm_logging.py +++ b/tests/unit/litellm_core_utils/test_litellm_logging.py @@ -8389,6 +8389,7 @@ class TestAzurePTUSpilloverCost: ROUTER_MODEL_ID: Final = "ptu-spill-router-model-id" SERVED_MODEL: Final = "azure/spill-served-model-ptu" + PTU_DEPLOYMENT: Final = "azure/spill-ptu-deployment" PTU_MODEL_INFO: Final = { "id": ROUTER_MODEL_ID, "team_id": "team-1", @@ -8424,7 +8425,9 @@ class TestAzurePTUSpilloverCost: litellm.model_cost.pop(TestAzurePTUSpilloverCost.ROUTER_MODEL_ID, None) litellm.model_cost.pop(TestAzurePTUSpilloverCost.SERVED_MODEL, None) - def _logging_obj(self, model_info: dict, *, flag: str, litellm_rate: float, monkeypatch) -> LitellmLogging: + def _logging_obj( + self, model_info: dict, *, flag: str, litellm_rate: float, monkeypatch, deployment: str | None = None + ) -> LitellmLogging: monkeypatch.setenv("LITELLM_ENABLE_PTU_COST_ATTRIBUTION", flag) obj = LitellmLogging( model=self.SERVED_MODEL, @@ -8441,7 +8444,7 @@ class TestAzurePTUSpilloverCost: optional_params={}, litellm_params={ "api_base": "", - "metadata": {"model_info": model_info}, + "metadata": {"model_info": model_info, "deployment": deployment}, "input_cost_per_token": litellm_rate, "output_cost_per_token": litellm_rate, }, @@ -8545,6 +8548,50 @@ class TestAzurePTUSpilloverCost: finally: self._unregister_models() + def test_spillover_without_base_model_reports_the_pay_as_you_go_rates_billing_used(self, monkeypatch) -> None: + self._register_models() + litellm.model_cost[self.PTU_DEPLOYMENT] = {"litellm_provider": "azure", "mode": "chat"} + try: + obj = self._logging_obj( + dict(self.PTU_MODEL_INFO), + flag="True", + litellm_rate=0.0, + monkeypatch=monkeypatch, + deployment=self.PTU_DEPLOYMENT, + ) + response = self._response() + response._hidden_params["additional_headers"] = {"llm_provider-x-ms-is-spilled-over": "true"} + response._hidden_params["provider_response_model"] = response.model + response_cost: Final = obj._response_cost_calculator(result=response) + response.model = "spill-model-group-alias" + + payload: Final = get_standard_logging_object_payload( + kwargs={ + "model": self.SERVED_MODEL, + "custom_llm_provider": "azure", + "litellm_params": obj.litellm_params, + "response_cost": response_cost, + }, + init_response_obj=response, + start_time=datetime.datetime.now(), + end_time=datetime.datetime.now(), + logging_obj=obj, + status="success", + ) + + assert response_cost == pytest.approx(self.EXPECTED_SPILL_COST) + assert payload is not None + model_map_information: Final = payload["model_map_information"] + assert model_map_information["model_map_key"] != self.PTU_DEPLOYMENT + model_map_value: Final = model_map_information["model_map_value"] + assert model_map_value is not None + assert response_cost == pytest.approx( + 100 * model_map_value["input_cost_per_token"] + 50 * model_map_value["output_cost_per_token"] + ) + finally: + litellm.model_cost.pop(self.PTU_DEPLOYMENT, None) + self._unregister_models() + def test_spillover_header_does_not_touch_non_ptu_custom_pricing(self, monkeypatch) -> None: self._register_models() custom_model_id: Final = "non-ptu-custom-router-model-id" From 97bcc92fadd077c24190aef56aa147d542675b0c Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 21 Oct 2026 00:50:12 +0000 Subject: [PATCH 56/66] chore(deps): bump aiohttp to 3.14.4 --- uv.lock | 477 +++++++++++++++++++++++++++----------------------------- 1 file changed, 227 insertions(+), 250 deletions(-) diff --git a/uv.lock b/uv.lock index fb9d8bbd9ac..232edd8cd3b 100644 --- a/uv.lock +++ b/uv.lock @@ -10,7 +10,7 @@ resolution-markers = [ ] [options] -exclude-newer = "2026-10-03T01:54:46.765163Z" +exclude-newer = "2026-10-18T00:49:54.67829083Z" exclude-newer-span = "P3D" [manifest] @@ -85,7 +85,7 @@ wheels = [ [[package]] name = "aiohttp" -version = "3.14.3" +version = "3.14.4" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "aiohappyeyeballs" }, @@ -98,126 +98,127 @@ dependencies = [ { name = "typing-extensions", marker = "python_full_version < '3.13'" }, { name = "yarl" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/58/d9/22ce5786ac0c1653ae8b6c23bded02c1686d11f0dbb45b31ce128e0df985/aiohttp-3.14.3.tar.gz", hash = "sha256:9491196535a88924a60afd5b5f434b5b203b6cc616250878dbdb223a8f7844bc", size = 7971213, upload-time = "2026-07-23T01:57:27.037Z" } +sdist = { url = "https://files.pythonhosted.org/packages/93/2f/6a91adaa2dc26877d6ed2f54c0370c8910f019db7d77c5c6a194611e93ea/aiohttp-3.14.4.tar.gz", hash = "sha256:831fc5bd39ec2517851e348f613ddb5447a47cf4b71cb09845af7ad7ed45d8f9", size = 8077839, upload-time = "2026-10-05T17:43:48.309Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/2d/4d/4a99fb425c5e0cad715eea7bd190aff46f38b959a0a2dadb993705d34b26/aiohttp-3.14.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:eb0495d778817619273c108784292be161a924b9f5ae5cbbc70a2caa6838250b", size = 765848, upload-time = "2026-07-23T01:52:08.217Z" }, - { url = "https://files.pythonhosted.org/packages/74/e8/43b85dc55b8e950dc644babe762add781319ea881b57b33d2cce12017d12/aiohttp-3.14.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c3c200cf9757edd785051dc699c7ecbec22110dbfcb3fefc7a9f9695eda8ea7a", size = 517476, upload-time = "2026-07-23T01:52:10.846Z" }, - { url = "https://files.pythonhosted.org/packages/7f/9e/73b582c4dbbc3c12ef4473822475effaabf1f934b56f14f5b03fe5d3a2af/aiohttp-3.14.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:fd51ebf9d3a00c074df4ede271023f4d2dba289bcc740b88191872716014e3c5", size = 515334, upload-time = "2026-07-23T01:52:12.636Z" }, - { url = "https://files.pythonhosted.org/packages/79/03/e98c3c9e05a5bdf97defe5ff9169baba4f0ec9a901f2d60e0f060c2f051e/aiohttp-3.14.3-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:134ac5ddcf61c6fad984b9a5727d83492ada43d63471db20fb73042c13fca62f", size = 1708830, upload-time = "2026-07-23T01:52:14.538Z" }, - { url = "https://files.pythonhosted.org/packages/d7/2c/26e60b694844dfd2176c57f913a22d0cd6a16f9ff202cbda7580d0328b98/aiohttp-3.14.3-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:70c987b27534f9ae1a723f47ae921571d616da21d3208282bf4c52af5164ac43", size = 1674012, upload-time = "2026-07-23T01:52:16.486Z" }, - { url = "https://files.pythonhosted.org/packages/38/65/672df92e3172cd876aacfa97a952ac560877eb169384b2991ac5b273de4c/aiohttp-3.14.3-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:1b59533861b70a2185c8f4f350f791f39d64358ef6944ce71c5240c9ec0982c9", size = 1767015, upload-time = "2026-07-23T01:52:18.28Z" }, - { url = "https://files.pythonhosted.org/packages/9e/c5/228dec7bfec1c373cc2217cdeb47d6456dcd7a13a4c55144930a75ae3851/aiohttp-3.14.3-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:1c5281acc88b92396f88c7e1e2748f8466689df22b80170e4f51efa712fb47a8", size = 1858700, upload-time = "2026-07-23T01:52:20.08Z" }, - { url = "https://files.pythonhosted.org/packages/bd/ff/cb36724e8c8d17f90ada567a9ff3efe1d6e9b549fba697a242aece180f21/aiohttp-3.14.3-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:48d67b87db6279c044760787eb01f6413032c2e6f3ba1cafaa492b1c8e578479", size = 1714075, upload-time = "2026-07-23T01:52:22.071Z" }, - { url = "https://files.pythonhosted.org/packages/9f/3a/296a4135c6366376263aeef54b15caca1f07676c2ae0c525d7832f2f808a/aiohttp-3.14.3-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f53bcd52f585e1ac3e590d61434eb61f9a88c38df041b4ea126d97144344a77b", size = 1588234, upload-time = "2026-07-23T01:52:23.757Z" }, - { url = "https://files.pythonhosted.org/packages/7d/81/9d5d853ef892dc066d1eb6db0e87a47348b920c1c879aa554612fdbd9d79/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:0fdea2281997af69da84c77ffa6f5938a0285f21fb3887c249d67419ca865b3d", size = 1677300, upload-time = "2026-07-23T01:52:25.861Z" }, - { url = "https://files.pythonhosted.org/packages/68/96/021d386ae32d9b26d4b88df2e794546232ff56bb6be952bf6be227c0bbc7/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:cda5fd5c95ad7a125a2e8464acc78b98b94c475a3780d6aa0aa157c93f470f4d", size = 1691501, upload-time = "2026-07-23T01:52:28Z" }, - { url = "https://files.pythonhosted.org/packages/29/9f/af66adce26a14af135c003cbd0f44ccaa68cebd30ff8ac99ca47fb4958f7/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:6debfa7312ff9d4c124dc71d72e9a0a4b9e0879e48ba6fcb42bef5c3300289e2", size = 1735113, upload-time = "2026-07-23T01:52:29.995Z" }, - { url = "https://files.pythonhosted.org/packages/2f/90/28c390d4c9851effe52ac25b5a2e1d92246acd00728b4fc7975dafb67484/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:f4e05329faa0ea1a404b37de4f034fd2c2defcca06a68dc6745e4e56c88e8a48", size = 1577486, upload-time = "2026-07-23T01:52:31.937Z" }, - { url = "https://files.pythonhosted.org/packages/db/c2/00e23a1bf2abb70dd353f6987db7e7f2491d0261f7363997738c71c98f95/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:a3a8296e7ab5c295f53f1041487cb088e1480775aafbf7fe545d93b770a0f96f", size = 1751353, upload-time = "2026-07-23T01:52:33.688Z" }, - { url = "https://files.pythonhosted.org/packages/6e/7d/d51a706a8cbfa57f0611127daf61ab3ae02ab8420b0407412079227d1c65/aiohttp-3.14.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:5373dc80ad1aa2fb9ad95c83f24eef418bbda3a61375f128e5b0192e4f3f9b32", size = 1698681, upload-time = "2026-07-23T01:52:38.167Z" }, - { url = "https://files.pythonhosted.org/packages/ec/b0/90bd5cd9fdd9787cb4211d284d1fb8401339a933cb0227a15b71e789232f/aiohttp-3.14.3-cp310-cp310-win32.whl", hash = "sha256:a3e22975f905b89a55a488c2a08f2fdb2186175349e917d48985cc468a3d4c6e", size = 456733, upload-time = "2026-07-23T01:52:41.823Z" }, - { url = "https://files.pythonhosted.org/packages/d8/15/fe5b8f6a71ae112bc677163d0b0701bda5dc15005249582258ede0eb88c7/aiohttp-3.14.3-cp310-cp310-win_amd64.whl", hash = "sha256:bdd0e2834dce1a26c1bbe26464861e16bbe217042cbff619247c11594472518c", size = 480460, upload-time = "2026-07-23T01:52:43.905Z" }, - { url = "https://files.pythonhosted.org/packages/54/00/45e98b6645cd7f00a4b78b749ebd309094b0eaeb2d2e96157eadbc0d0050/aiohttp-3.14.3-cp310-cp310-win_arm64.whl", hash = "sha256:eac645b09bcfdf73df7536331f0678c1086ea250981118ddb5199e17ccef72bb", size = 453479, upload-time = "2026-07-23T01:52:46.075Z" }, - { url = "https://files.pythonhosted.org/packages/f8/5c/b3e4ff8ad43a8afef9602c5e90285936da1beaea8b029016b793891f03c3/aiohttp-3.14.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:e568e14940c09955aa51f4e645b6daa18a581c5dcfcd73744dcc86a856e3ced3", size = 764250, upload-time = "2026-07-23T01:52:48.525Z" }, - { url = "https://files.pythonhosted.org/packages/0e/da/f1b384465e51449d844056b75070461da03a9a23e6c1747003695bf4172a/aiohttp-3.14.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:54cfcdee2770dac994417cbb0ee1f3eb0e7cb6b30c79bf44f2c02ff79ec5124a", size = 516281, upload-time = "2026-07-23T01:52:51.047Z" }, - { url = "https://files.pythonhosted.org/packages/b9/3f/01264f820ee2e3712a827892b1cd6ff80f3300c1fcbffbb45714a915d47a/aiohttp-3.14.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:21c016079415ed3fd676963e9793700a566d85dbbd6bfc564b9b2d209147dcc8", size = 514742, upload-time = "2026-07-23T01:52:53.779Z" }, - { url = "https://files.pythonhosted.org/packages/9e/8d/a71c6f2db52ac1ed142b133f7feddaa6b70539c3f4de24d7e226c95b794c/aiohttp-3.14.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d6088ec9894113802bddb3c09e974929aed2c7b3a8c456219b8aab4481f1a239", size = 1780613, upload-time = "2026-07-23T01:52:56.948Z" }, - { url = "https://files.pythonhosted.org/packages/a5/11/3dd9b3fb3a170f6ec9011b5291d876a6fab4086714c9e158600edf01b4fd/aiohttp-3.14.3-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:16ea7e24c309fb7c0bbd505d149abe4fe4dccfb8db911db7dbec0921bc889a6f", size = 1737688, upload-time = "2026-07-23T01:52:59.294Z" }, - { url = "https://files.pythonhosted.org/packages/6d/3e/834c26918be7d88068822b40e0db30fca50b5f4fe79104aa16a93f1d74e6/aiohttp-3.14.3-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:56f355e79f71aef2a85c80305cc915f894b170dba76de5fe84f6351939b83c06", size = 1845742, upload-time = "2026-07-23T01:53:01.641Z" }, - { url = "https://files.pythonhosted.org/packages/cc/c9/49ab8572df7d66bc13d11e31f781292badb04180dd87ba98733066c6aed7/aiohttp-3.14.3-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:18c441d0a8fca6de8d1f546849b9f0ab20d435993e2c5b59562b2fae6be2f929", size = 1928412, upload-time = "2026-07-23T01:53:04.018Z" }, - { url = "https://files.pythonhosted.org/packages/a5/b9/2b8f0c0ce09c87a1daf80fd483431b56b1435d3f62789bc86f572e1245de/aiohttp-3.14.3-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:53e7b4ce82b54a8bcc71b3b67a5cbd177ca1d7f592cbc92cd38b7349f73482db", size = 1786220, upload-time = "2026-07-23T01:53:06.481Z" }, - { url = "https://files.pythonhosted.org/packages/85/00/9c45f81de11710460edfa1dc81317b6e882703b160926c879a9d20da9fcc/aiohttp-3.14.3-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f55119f7bf25f49ed210f6096090715da24f2943c62102448915fde3c62877ce", size = 1637231, upload-time = "2026-07-23T01:53:10.258Z" }, - { url = "https://files.pythonhosted.org/packages/19/ce/967d628e910756f3539c6107cb7844a1b69440dcb3029a5ee7871b09ab63/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:9aa6e61fdf20105c4144e755bd586008ff450791d67b1c8146fdc15959c4d51c", size = 1753161, upload-time = "2026-07-23T01:53:13.817Z" }, - { url = "https://files.pythonhosted.org/packages/11/b2/0c3d4114f0aee4f580f5b3b4eb71b24d7a23b834ea506a4dfebe76513f35/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:ccd4893707b3e2a13e39c90d43cf80edf2e4d0457935bcc103bf2346214c3f15", size = 1756356, upload-time = "2026-07-23T01:53:16.211Z" }, - { url = "https://files.pythonhosted.org/packages/63/5d/99e7d91c82f1399d1ae2a854e080bd1493fbc31e5e959dbc4ec33dac3bec/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:b2466434105a4e03113c36ec775cc2ebe6676b62eae326fa670bb607ef788c1c", size = 1819846, upload-time = "2026-07-23T01:53:18.289Z" }, - { url = "https://files.pythonhosted.org/packages/ad/05/d5e1cb6480eeffd3f901d40a2c5e2d1e7effdc797837da3b490272699f13/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:ba59d59aba08ac02fc03b0c8983ccd5ee39a199d0552ce9e6d2b4845b34d59ae", size = 1628531, upload-time = "2026-07-23T01:53:23.86Z" }, - { url = "https://files.pythonhosted.org/packages/c9/90/b934682bcaefae18a9e04f3dff5b68522ba810906358ae5029b68110ea3b/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:ed099d105449c4f9e84f24af203cd131349d4761d8813fa7e02c32e7128cd910", size = 1832712, upload-time = "2026-07-23T01:53:27.551Z" }, - { url = "https://files.pythonhosted.org/packages/21/df/6061679faaf81fac746e7307c7adb71e858071a5d34c27583afefc64f543/aiohttp-3.14.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:152516815ef926786a0b6ae2b8f1fd2e0c71582dee0b435636865316fd4891b7", size = 1775014, upload-time = "2026-07-23T01:53:30.223Z" }, - { url = "https://files.pythonhosted.org/packages/8a/1d/f854878bbc69b88faefe924b619a34a6f59ec05fd387c77690667eaa75eb/aiohttp-3.14.3-cp311-cp311-win32.whl", hash = "sha256:a4af35c443e0b1a1bd6a8af3f3485d7fda15c142751a00f3ff8090f0b93346fa", size = 456006, upload-time = "2026-07-23T01:53:34.97Z" }, - { url = "https://files.pythonhosted.org/packages/73/0c/2af9d1674baccd1dbd47282a93d660a22e57ef6167c856deb24b4214fbab/aiohttp-3.14.3-cp311-cp311-win_amd64.whl", hash = "sha256:e1e74298bab6ee0d6e749ed4fd1901c7e604bdda32c03d787a2cc71c46d0433d", size = 481069, upload-time = "2026-07-23T01:53:39.673Z" }, - { url = "https://files.pythonhosted.org/packages/8e/76/88401ff3fc95e85c5fc38d588f36f55e61ecb64343b2bc8d69326f453cc0/aiohttp-3.14.3-cp311-cp311-win_arm64.whl", hash = "sha256:03cd2bde3d7f085b64e549c985f4bb928cad7e8ecf5323bfca320db548d81b39", size = 453021, upload-time = "2026-07-23T01:53:43.749Z" }, - { url = "https://files.pythonhosted.org/packages/18/d4/eb96299230e20acf2efae207cb8d69051f1f68e357e5ea5e479bf6fb097a/aiohttp-3.14.3-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:39aded8c7f3b935b54aab1d8d73c70ec0ee2d3ec3b943e0e86611bc150ba47f5", size = 754690, upload-time = "2026-07-23T01:53:47.332Z" }, - { url = "https://files.pythonhosted.org/packages/88/11/e7a70a209eb9a067c0d3212b518a0134e3484f5178c7533878b6b514d469/aiohttp-3.14.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:5bcb6ff3fdab1258a192679ff1a05d44f59626430aa05cd1a9d2447423599228", size = 509484, upload-time = "2026-07-23T01:53:51.159Z" }, - { url = "https://files.pythonhosted.org/packages/30/07/4bbc222cc8dbe31d4c3e8a5baad2286e4d42026ac0c570027b89afce6344/aiohttp-3.14.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:617105e2c3018ee38d0c8ce5ee3c84f621a6d8b9f723202aacaff28449ca91ee", size = 511949, upload-time = "2026-07-23T01:53:55.083Z" }, - { url = "https://files.pythonhosted.org/packages/54/b9/42e74c46b7b7c794b995bbc1f573fb48950c38b19d8600c62a6804ee2d67/aiohttp-3.14.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f631fe87a6f30df5fbe6d79640b25e4cffb38c31c7fb6f10871517b84b0f8c1a", size = 1765282, upload-time = "2026-07-23T01:53:59.662Z" }, - { url = "https://files.pythonhosted.org/packages/6b/ed/62bc4d74363ad346d518e0720363a949f63e2e23439a79eb5813d4d29bb3/aiohttp-3.14.3-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:a94dbaae5ae27bd849c93570669bff91e0510f33a80805738e3de72a7be0447b", size = 1741511, upload-time = "2026-07-23T01:54:04.063Z" }, - { url = "https://files.pythonhosted.org/packages/d0/9f/181e8a8bc79e47d13c7fc4540bd7a3b729d9505609c61f392a8dd2fbfe55/aiohttp-3.14.3-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:8f2f1c4c032c7cedd7d8da6f54c97b70266c6570c3108d3fdffee7188bb70529", size = 1810680, upload-time = "2026-07-23T01:54:09.882Z" }, - { url = "https://files.pythonhosted.org/packages/5c/9a/dec94d6ad694552fe3424e3f1928d7a606a5d9d9433a04e7ecdd9d38ae7f/aiohttp-3.14.3-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:ea05e1f97ceea523942d9b2a7d7c0359d781d683d6b043f5943a602b14da4787", size = 1905646, upload-time = "2026-07-23T01:54:13.475Z" }, - { url = "https://files.pythonhosted.org/packages/52/b7/7cd31f29d6055bd711ae6e669367fba6f5ae9de463910a793e30556a8db7/aiohttp-3.14.3-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:543906c127fb1d929b95076db19b83fa2d46751006ff1e23b093aa5ac4d8db42", size = 1792122, upload-time = "2026-07-23T01:54:15.752Z" }, - { url = "https://files.pythonhosted.org/packages/66/73/10b1ef93afa61f4963c746257b70ced619cf31a4798671de5fdb2608501d/aiohttp-3.14.3-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0a5ff2dfbb9ce645fa5b8ef3e02c6c0b9cc3f6030ff863d0c51fffc50cb5541b", size = 1591127, upload-time = "2026-07-23T01:54:19.489Z" }, - { url = "https://files.pythonhosted.org/packages/49/ed/3b203fa6de1b338c14acdc06bf6ca9b043b7944f005966958c2ced932cde/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:041badb8f84396357c4d3ad26de6afd7a32b112f43d3c63045c0c8278cfd2043", size = 1725210, upload-time = "2026-07-23T01:54:24.129Z" }, - { url = "https://files.pythonhosted.org/packages/28/b7/1c2aab8c706436dcc28598452488ac9cd7c409da815237c28c27d58993e6/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:530125ee1163c4219af35dc3aa1206e541e7b31b6efc1a3f93b70a136f65d427", size = 1764848, upload-time = "2026-07-23T01:54:27.973Z" }, - { url = "https://files.pythonhosted.org/packages/54/50/94c28f08b131c4bf10984ea2c7a536c9920608bb2d6e7f95642c30cc87b7/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:c8653fd547c93a61aadc612007790f5555cdd18946fa48cf45e26d8ea4ea473d", size = 1777102, upload-time = "2026-07-23T01:54:31.775Z" }, - { url = "https://files.pythonhosted.org/packages/13/d4/e7d09ba7d345fb2d74440fd2fa033c5e079fac05552927705986f41a364f/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:89176250f686cb9853c0fb7ead90e639e915b84a6f43eedc2a4e7ec21f1037f0", size = 1580205, upload-time = "2026-07-23T01:54:34.518Z" }, - { url = "https://files.pythonhosted.org/packages/a3/84/072a91d68e1e1eb587985b54baab94221277f877e8ef274fc213a0ceae28/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:3a26434dafe408229ff3403458ca58de24fb51936504decac49ce6755f77e59d", size = 1797219, upload-time = "2026-07-23T01:54:36.995Z" }, - { url = "https://files.pythonhosted.org/packages/e0/eb/aad34e897e668424d6e995da5dff8a4a09af93363d3392488772957a63aa/aiohttp-3.14.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:d1558173930a5a8d3069cee5c92fc91c87c4dbcb099debbb3622053717145a19", size = 1768629, upload-time = "2026-07-23T01:54:40.103Z" }, - { url = "https://files.pythonhosted.org/packages/b6/2b/6bb88ddba0fecd9122aa3ebcad25996cf6c083a4a7040dbb3a4f97972af6/aiohttp-3.14.3-cp312-cp312-win32.whl", hash = "sha256:16100ad3ab8d649fdfbee87602d9d2dcdca9df0b9eda8a1b5fdc0d41f96da559", size = 451481, upload-time = "2026-07-23T01:54:42.547Z" }, - { url = "https://files.pythonhosted.org/packages/76/9b/f2f8f108da17ecef2cc3efc424e8b7ad3782b1a8360f7b8eae8ced84f6ea/aiohttp-3.14.3-cp312-cp312-win_amd64.whl", hash = "sha256:33a2d7c28d33797a2e99923dffa63f83d908a19b6bf26cfe80fa790aa5e1a75a", size = 476845, upload-time = "2026-07-23T01:54:44.853Z" }, - { url = "https://files.pythonhosted.org/packages/3e/44/28dac80a8941b604f4da10ce21097614ca1bf905ce93dca28d8d7de9c1e7/aiohttp-3.14.3-cp312-cp312-win_arm64.whl", hash = "sha256:362a3fd481769cac1a824514bcd86fda51c65e8fe6e051099e008fddde6db17c", size = 448050, upload-time = "2026-07-23T01:54:47.087Z" }, - { url = "https://files.pythonhosted.org/packages/57/be/5afd201cc0ab139029aadb75392efe85a293403d9dd3a3226161c21ce00c/aiohttp-3.14.3-cp313-cp313-android_21_arm64_v8a.whl", hash = "sha256:2e9878ae68e4a5f1c0abe4dd497dbc3d51946f5837b56759e2a02e78fa90ef86", size = 506269, upload-time = "2026-07-23T01:54:49.075Z" }, - { url = "https://files.pythonhosted.org/packages/22/09/dec8189d62b45ade009f6792a2264b942a90cb88aeaf181239933cd72c3c/aiohttp-3.14.3-cp313-cp313-android_21_x86_64.whl", hash = "sha256:f3d2669fe7dec7fc359ecdb5984b29b50d85d5d00f8c1cb61de4f4a24ee42627", size = 515166, upload-time = "2026-07-23T01:54:51.894Z" }, - { url = "https://files.pythonhosted.org/packages/28/24/2854869d29ed8a8b19d74f9ec6629515f7e04d02dd329d9d179201e58e47/aiohttp-3.14.3-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:cc7cb243a68167172f48c1fd43cee91ec4b1d40cefd190edd43369d1a6bc9c82", size = 486263, upload-time = "2026-07-23T01:54:54.223Z" }, - { url = "https://files.pythonhosted.org/packages/d4/dd/57187c8be2a35aea65eaee3bd2c3dcbbcf0204f5106c89637e3610380cd1/aiohttp-3.14.3-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:78253b573e6ffab5028924fc98bc281aae05445969982a10864bc360dea2016c", size = 492299, upload-time = "2026-07-23T01:54:56.236Z" }, - { url = "https://files.pythonhosted.org/packages/b9/11/06ae6ed8f0d414edf4068861e233d8fe23ee699bfd4b3ceb8663db948a62/aiohttp-3.14.3-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:7041d52c3a7fa20c9e8c182b534704abb19502c8bdcbde7ab23bfda6f642394f", size = 502235, upload-time = "2026-07-23T01:54:58.377Z" }, - { url = "https://files.pythonhosted.org/packages/7e/a3/559639c34a345d2cf7c52dff6838119f2eaf29eb508227b5b83f573af813/aiohttp-3.14.3-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:ac74facc01463f138b0da5580329cfcc82818dea5656e83ddcd11268fc12ff80", size = 750883, upload-time = "2026-07-23T01:55:00.65Z" }, - { url = "https://files.pythonhosted.org/packages/91/cd/41e131f13afd1e7b0172a9d9eda085ef90eb8439f41f0d279db81ed3ae60/aiohttp-3.14.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:d6218d92e450824e9b4881f44e8c09f1853b490f9a64130801024a4793b1b3b0", size = 508473, upload-time = "2026-07-23T01:55:02.945Z" }, - { url = "https://files.pythonhosted.org/packages/bc/6b/e7f13410d391c6e55b4c007a8de024355389d7d459e3d64c42b2d33617e5/aiohttp-3.14.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:11fb37ef075669eee52ab1928fbf6e1741fada40409fa309ebde9607a962aebf", size = 509190, upload-time = "2026-07-23T01:55:05.173Z" }, - { url = "https://files.pythonhosted.org/packages/97/21/6464573e53d69672cc1eada3e5c5cb2d2efa82701e8305a0f2047a576967/aiohttp-3.14.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:55bdcc472aafe2de4a253045cc128007a64f1e0264fb675791e132ea5edaa3bd", size = 1761478, upload-time = "2026-07-23T01:55:07.383Z" }, - { url = "https://files.pythonhosted.org/packages/1a/81/d217043a4c17fbce360905e3b2bdd20139ebc9a2de836d035d179c4da006/aiohttp-3.14.3-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:c39846c3aad97a8530c89d7a3869a8f8e9e3762c6ac0504481e5c80948f7e807", size = 1735092, upload-time = "2026-07-23T01:55:09.803Z" }, - { url = "https://files.pythonhosted.org/packages/a1/66/e13a02d0eeb1a9a502402a977abb4e4abff9fe4051c26f80558c57a7c975/aiohttp-3.14.3-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:5895ef58c4620afe02fa16044f023dc4dafec08158f9d08874a46a7dbc0341b8", size = 1800546, upload-time = "2026-07-23T01:55:12.012Z" }, - { url = "https://files.pythonhosted.org/packages/26/5e/57d42fca1d18cb5acc1cad945d017fabc5d6ae71d8a08ad66be8dc3ee544/aiohttp-3.14.3-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:fa9467a8113aa69d3d7c55a70ef0b7c636010a40993f3df9d9d0d73b3eb7ef24", size = 1895250, upload-time = "2026-07-23T01:55:14.357Z" }, - { url = "https://files.pythonhosted.org/packages/ca/1c/7da8d08e74d56f00070822f9638ff3f1c563f8ad87d1efa996c87bfc8644/aiohttp-3.14.3-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d7d2deec16eeedf55f2c7cf75b521ea3856a5177e123844f8fd0f114ce252cb5", size = 1789289, upload-time = "2026-07-23T01:55:16.668Z" }, - { url = "https://files.pythonhosted.org/packages/cd/0f/cf16bcf56896981c1a0319f5d5db9337994b5165730c48a8fa07e9b34be6/aiohttp-3.14.3-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:dd54d0e8717de95939766febac482ac0474d8ac3b048115f9f2b1d23a16e7db4", size = 1586706, upload-time = "2026-07-23T01:55:18.913Z" }, - { url = "https://files.pythonhosted.org/packages/fe/6f/76eac12a7f2480e1e304f842efdb07db33256b0d9165b866b6ef0806c202/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:df82f3787c940c94986b34222d59c9e38843fba85139f36e85255a82ad5355a9", size = 1724652, upload-time = "2026-07-23T01:55:21.296Z" }, - { url = "https://files.pythonhosted.org/packages/39/b6/19c8c592baeeb94b75f966547d40c02ac7590902306ec5863d5c027cf506/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:42a67efc36300d052fb4508a53e8b6901b9284b599ae63945c377569c5fcc1e1", size = 1756239, upload-time = "2026-07-23T01:55:23.705Z" }, - { url = "https://files.pythonhosted.org/packages/dc/c9/4e9383150296f97f873b680c4de8fb2cd88608fb9f48c79edcb111611abc/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:7a75aa63cbf9b21cfaf60dc2657e19df2c2867d91707d653fee171ffeedd1371", size = 1769161, upload-time = "2026-07-23T01:55:26.082Z" }, - { url = "https://files.pythonhosted.org/packages/aa/1e/147bdc6cc5de5f3ab011be8bf5d6e786633249f22c20bae06f85e45f5387/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:e92eb8acc45eb6a9f4935071a77edf5b85cc6f8dfad5cd99e97653c26593cdde", size = 1578759, upload-time = "2026-07-23T01:55:28.846Z" }, - { url = "https://files.pythonhosted.org/packages/fd/31/78388a9d6040ece2e11df62ea229a822cf5e52d238374b220ae9975b2623/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:b014a6ed7cf912e787149fdc529166d3ceabac23f26efeea3158c9aba2354e7e", size = 1792025, upload-time = "2026-07-23T01:55:31.457Z" }, - { url = "https://files.pythonhosted.org/packages/03/51/a3d29fdf2c25d796746af8ad6fe56a45d6256c38b0a8a2ed752e1160b3a2/aiohttp-3.14.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:3d4f72af88ac2474bb5bca640030320e3d38a0163a1d7533500e87be458eef71", size = 1768477, upload-time = "2026-07-23T01:55:33.87Z" }, - { url = "https://files.pythonhosted.org/packages/29/a6/442e18b5afeade534d877a2dc3c3e392aff8d49787890b0cf84790410267/aiohttp-3.14.3-cp313-cp313-win32.whl", hash = "sha256:5f08ec777f35ee70720233b8b9811d3bb5d728137f30ac91b7457709c3261ac0", size = 451069, upload-time = "2026-07-23T01:55:36.121Z" }, - { url = "https://files.pythonhosted.org/packages/9d/69/3d876ac02659f271cf7f6769f14a8e3de5b6e888ed8b5a7e998086a4cec8/aiohttp-3.14.3-cp313-cp313-win_amd64.whl", hash = "sha256:dff9461ec275f22135650d5ba4b4931a11f3958df7dfbb8db630000d4dee0883", size = 476518, upload-time = "2026-07-23T01:55:38.303Z" }, - { url = "https://files.pythonhosted.org/packages/b2/0e/50d6e6471cd31edce8b282bdec59375a3a69124d8a989a0b1313355cae52/aiohttp-3.14.3-cp313-cp313-win_arm64.whl", hash = "sha256:ddcac3c6b382e81f1dd0499199d4136b877beb4cb5ef770bbbfba56c4b8f55d2", size = 447676, upload-time = "2026-07-23T01:55:40.451Z" }, - { url = "https://files.pythonhosted.org/packages/c8/20/887fdcf832326571b370ffc347b3e70abe101096f3720126aac161b1d872/aiohttp-3.14.3-cp314-cp314-android_24_arm64_v8a.whl", hash = "sha256:49f7325beb0f85ef4aef5f48f490269575f83e6e2acad00a1d80b807eb027062", size = 509067, upload-time = "2026-07-23T01:55:42.618Z" }, - { url = "https://files.pythonhosted.org/packages/ad/a3/92cec936f78cc4bf0fa5554ebe593b73459d94e3c62303e1902a4cccb6f7/aiohttp-3.14.3-cp314-cp314-android_24_x86_64.whl", hash = "sha256:e3be98a7c30b8c25d573dafba7171d66dfb05ee6a9070fc46535464ff97700a6", size = 514774, upload-time = "2026-07-23T01:55:44.937Z" }, - { url = "https://files.pythonhosted.org/packages/29/ba/2a0c38df3fc557620b6a5acd98364af050053b6285b4dc7ee74100c63c18/aiohttp-3.14.3-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:614c61d478b83953e261d02bb2df750f17227cd33ef8002945bf5aebbde21919", size = 488134, upload-time = "2026-07-23T01:55:47.135Z" }, - { url = "https://files.pythonhosted.org/packages/48/d6/d51b7d4bf309af3693940d8ffd2b9ed0b682434ef85959b7c9c137f60cf8/aiohttp-3.14.3-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:1caa7b0d05f3e3a36f87788c59e970a7ee1cefcfcbb924a9f138c4a6551c9cb7", size = 494201, upload-time = "2026-07-23T01:55:49.451Z" }, - { url = "https://files.pythonhosted.org/packages/3f/5a/8f624384e5f1efabb5229b94157eb966b021e97bdb188c62860c2ae243c2/aiohttp-3.14.3-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:dfa68deb2a443bdaa3ea5297b0699c1464f08aef3812b486d1348eee61b07dc0", size = 502766, upload-time = "2026-07-23T01:55:51.656Z" }, - { url = "https://files.pythonhosted.org/packages/a6/26/4ff0164370deec18fb19254ee4ab10b7a73304ac0c860b13f5f84663759b/aiohttp-3.14.3-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:e72ee89e28d907a18f46959b4eb0bb06701cc7f8cf4366e00029e2ccfaaf5924", size = 756557, upload-time = "2026-07-23T01:55:53.964Z" }, - { url = "https://files.pythonhosted.org/packages/97/a3/7056b86dc0d9ec709ea9777eae3b0161428f943372f8b98c01c11593b682/aiohttp-3.14.3-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:ad4c8b7488d745d2ca4838ebd8ae5ba9b56341d30b1da43640e4ce87f9f49646", size = 510168, upload-time = "2026-07-23T01:55:56.22Z" }, - { url = "https://files.pythonhosted.org/packages/85/ed/0357a015892fd68058bf2d39d3fd1958e459b997a7db30aaa6aaa434ae96/aiohttp-3.14.3-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:db332af25642007330fca8be5c4d194caf2bea7a7fc84415aff3497af5dfee6b", size = 512957, upload-time = "2026-07-23T01:55:58.437Z" }, - { url = "https://files.pythonhosted.org/packages/47/d1/8aba53f15ccb2238405f5e9d30e2a8ca44f93878c26e7165ade00d374b1c/aiohttp-3.14.3-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:25bd2708db6bdf6a6630dd37bdcdfcb47c4434d22ac69c64665b802910140b30", size = 1750149, upload-time = "2026-07-23T01:56:00.856Z" }, - { url = "https://files.pythonhosted.org/packages/49/bd/40c3fee327529284375c6701cbb0fa4600cc2e8432af1378f897e2ef7d3a/aiohttp-3.14.3-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:cef89a58e628c4efcac3275c2d68083f82426dcdc89c1492a6f654f9f7ea6ab9", size = 1707685, upload-time = "2026-07-23T01:56:03.371Z" }, - { url = "https://files.pythonhosted.org/packages/2a/a3/ca0cc6724cca8114b05694abd916060758c79894c3aa5b012cdadc1bc28e/aiohttp-3.14.3-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:c23ec8ee9d5ab2f5421f9c7fffce208435607af27fd46d4a44e031954352838f", size = 1803911, upload-time = "2026-07-23T01:56:05.817Z" }, - { url = "https://files.pythonhosted.org/packages/95/b5/85b099c299c3ffd38ad9b3e43694c8a346934e4a30c88c4fd5a841234f77/aiohttp-3.14.3-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:e2667f0bbe7eb6c74eae5e9691441ad186e5845ca3cff63230fc09c4e7514f5d", size = 1876929, upload-time = "2026-07-23T01:56:08.413Z" }, - { url = "https://files.pythonhosted.org/packages/d5/b7/1da684a04175473fa4cddbf9a2f572e79514c3fd27a74597f43057d4f3da/aiohttp-3.14.3-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:18cb43369747b2ae007bd2655fb8e63a099c2ff1d207962943636dac989b3147", size = 1761112, upload-time = "2026-07-23T01:56:10.918Z" }, - { url = "https://files.pythonhosted.org/packages/d1/16/bc4b55e3e5cb175fd69c53c90d60d2f47797cb343da5106e23863dc4dba4/aiohttp-3.14.3-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:d77640cc618c1d99fc4f8589c0f24a730adfa54eb1e57ef7bf0c8dfb78da898c", size = 1583500, upload-time = "2026-07-23T01:56:13.613Z" }, - { url = "https://files.pythonhosted.org/packages/2a/e8/13a9d957a1ee40837f46aa30f0f4c657e673ad86a2e6362a9f9be20d26d9/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:53e5179d8abb5710f8e83ba207c41c8d1261fcffd4616500e15ca2b7a33be10a", size = 1713940, upload-time = "2026-07-23T01:56:15.969Z" }, - { url = "https://files.pythonhosted.org/packages/38/05/d33c680c1bcf1c7e130f9cbfc1fc02fe8bb0c4af2a94a53dd5fb56131e5c/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:cd817772b2fcf2b8c0905795318485f9ec16eae60b29feb7f4c77085311637f0", size = 1724413, upload-time = "2026-07-23T01:56:18.591Z" }, - { url = "https://files.pythonhosted.org/packages/85/1d/af798d306f7a74b6a632dbcabcf62a4c91391b7582d2a8c6d7712e2cc54e/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:4e3ac92d90e92773b2362d506068e9a948192bd553e743c5b2429e28527c8661", size = 1770748, upload-time = "2026-07-23T01:56:21.074Z" }, - { url = "https://files.pythonhosted.org/packages/a8/92/ad720d472556a995049206867765e9410969684f86ee09423ff9969044c1/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:3f42e9b78301f11c8f861746175d8b9c1ccef713fcad9eab396e2f6db8ed4a22", size = 1577564, upload-time = "2026-07-23T01:56:23.475Z" }, - { url = "https://files.pythonhosted.org/packages/60/ad/0ed7586cbef7a884e23a752fa2bb987a122e6a5dd50dab109258d0a95193/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:9d9edccfe496b476db5f398d97b865e9a6752bcf8aec4eef8390ce20fb64bb41", size = 1782080, upload-time = "2026-07-23T01:56:25.994Z" }, - { url = "https://files.pythonhosted.org/packages/97/ea/dbaed0d73e8a69aad653b045dab451c67c2454bb731a37b45a86593e9422/aiohttp-3.14.3-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:1c5ec8fb1bcc31a8466f74aaf26c345d5c386fa4bd08a3f0eb9c7a4a3fe8b5bf", size = 1745813, upload-time = "2026-07-23T01:56:28.604Z" }, - { url = "https://files.pythonhosted.org/packages/81/1b/6893d4bc57e434fc93a6c9217c637d967a0b651d989f6e3265179375754a/aiohttp-3.14.3-cp314-cp314-win32.whl", hash = "sha256:38901a84da3ce22249f6e860bf8f90d141bcab7da090cc398f8bb58c0e44b7da", size = 455872, upload-time = "2026-07-23T01:56:31.031Z" }, - { url = "https://files.pythonhosted.org/packages/f5/8b/c7baa1ba1eda4db6989baefe5de6d99834921b84ebd7918624febcb9f290/aiohttp-3.14.3-cp314-cp314-win_amd64.whl", hash = "sha256:8b3b60de05f3dcb6f6a00f818bb2ec781cee4de0645f59ccaf99b1d1823b6100", size = 481030, upload-time = "2026-07-23T01:56:33.365Z" }, - { url = "https://files.pythonhosted.org/packages/22/8c/c29d067df825a2df88ca432db848aa2fe8199598359cc06c12b09320cac9/aiohttp-3.14.3-cp314-cp314-win_arm64.whl", hash = "sha256:1576145bdceeb92382d899751e12743a3a5b8e460a841e3e50543859e54864dc", size = 453669, upload-time = "2026-07-23T01:56:35.731Z" }, - { url = "https://files.pythonhosted.org/packages/6a/a4/9c033beb355d39b6147980597ec9645e4729243f686ee4dc73945de72030/aiohttp-3.14.3-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:8800c996b01c2772a783e3e46f3e1abd5823029adca0df54231960de9bfefa5b", size = 791403, upload-time = "2026-07-23T01:56:37.972Z" }, - { url = "https://files.pythonhosted.org/packages/80/ca/87c32a0a7704583cfc49660bd817889bae5b830bf53b5dcb4e92145ac2da/aiohttp-3.14.3-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:ebe8e504f058fe91223351cecd2d9d6946c9d241bb0250d898ffbdf584cc72b0", size = 526413, upload-time = "2026-07-23T01:56:40.523Z" }, - { url = "https://files.pythonhosted.org/packages/9e/d8/8ec0e471248c500acdce2be3f46db8fb62b5eb60efef072529cc85ee1d26/aiohttp-3.14.3-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:30402d03a7c0ff52bce290b57e564e9079fd9d0cb545c8aba73f86a103162d2e", size = 532135, upload-time = "2026-07-23T01:56:42.876Z" }, - { url = "https://files.pythonhosted.org/packages/fe/45/f8919fd936e8b79fcd9bda7b6d8e62613462a713f4f17987fd7c34399142/aiohttp-3.14.3-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9fc7b5bfec6573f3ae844f457fdde5adeb713f8b8e4a81ad64fc207b49383716", size = 1922742, upload-time = "2026-07-23T01:56:45.528Z" }, - { url = "https://files.pythonhosted.org/packages/f6/ec/9ca76b28a27525b0cc53e20842e0228b022f301ce1f436b7d814b4aaf2df/aiohttp-3.14.3-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:8a5fd34f7f7410d1730d5c2ba873cacb2eed3fede366feb268a70ba22581ed8f", size = 1787371, upload-time = "2026-07-23T01:56:48.045Z" }, - { url = "https://files.pythonhosted.org/packages/b1/04/6acdbf17315f7b55f1937e3387acb89a3cddeb4995689553d064af8e92ab/aiohttp-3.14.3-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:270d3dace9ca2f10f0da5d8ebe519b7a310fc6112ed916e32df5866df0888553", size = 1912623, upload-time = "2026-07-23T01:56:50.605Z" }, - { url = "https://files.pythonhosted.org/packages/86/e6/438b0c79ca6f45eb9fd9817dd4c01a91919a38c0de5ee9e05e2b4dc0ece7/aiohttp-3.14.3-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:3ae5b3a59436d089b5395d910121a390feed4d00578eb95a0fd1a329fe963100", size = 2005515, upload-time = "2026-07-23T01:56:53.153Z" }, - { url = "https://files.pythonhosted.org/packages/bb/6b/62cbd6577758699525f5c712d1ddef57d9875fbab0ae8d5f5a202fd598f8/aiohttp-3.14.3-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2498f0fe69ead802f9675beca44a7c21c62fdaa4ec5145ea1c3ad6edbee29f85", size = 1879906, upload-time = "2026-07-23T01:56:55.818Z" }, - { url = "https://files.pythonhosted.org/packages/00/95/18bcbf830a21dc3aae24d8f6b6feaf3db1d2090242d00a7868db2ffb0b67/aiohttp-3.14.3-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:a0dc483c00da8b673abbb367eb6f8d8f4bcec30eb58529ea13cb42e7fd2dfa33", size = 1675849, upload-time = "2026-07-23T01:56:58.861Z" }, - { url = "https://files.pythonhosted.org/packages/a9/19/47f4968659c5e23606c3790c80fc624e691c153d036148449ee84d31b287/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:c7d3a97c678d34fc5b59da671ee9cd630096ddc643e7b5a30d54a2a6f3574d3f", size = 1843496, upload-time = "2026-07-23T01:57:01.591Z" }, - { url = "https://files.pythonhosted.org/packages/64/af/38c33c4dd82fddcb4e56c4653b6f1072a8edbc6b7fa15809f14932c41e2d/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:f8fb78a83c9e5f741ca3a68cfb455c1f5bb83b4e7249a3848b3cd78d0a8563b0", size = 1827746, upload-time = "2026-07-23T01:57:05.131Z" }, - { url = "https://files.pythonhosted.org/packages/a1/9d/0537cda4885ac8f5b7053d164dd06312f4c483a4edcb8ee5b8aaf2a989bf/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:74ab5b6a9fb13e873e5a90946588baecaf488745e1db1a4a5c433f971f035098", size = 1853810, upload-time = "2026-07-23T01:57:08.043Z" }, - { url = "https://files.pythonhosted.org/packages/19/fe/26f9c5e6458385aa86497836b0dea6fb2f027827d63f37c7856cce9286ee/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:bd52f811e65f6fb634b1047159657c98f52b407f8efec907bcfc09da9a4c0a25", size = 1668895, upload-time = "2026-07-23T01:57:10.837Z" }, - { url = "https://files.pythonhosted.org/packages/ec/4c/618b1db9b9ba079b8875d2cdf78e7c4a3bf72903bd5850fee7dd9544600a/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:f0f177d1b195b9e06376cfd7d308d8a1b920909a609d03ac82a8c73bbb16d3b9", size = 1883833, upload-time = "2026-07-23T01:57:13.672Z" }, - { url = "https://files.pythonhosted.org/packages/94/c6/bd959bd1e4771f9fd944e9e436224c48c77b018b73b519b5aad346335bcc/aiohttp-3.14.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:498c6c623134f8e09a3c4e60bcd607a0b4590dd7dbf08dd40851b27cbb520ccb", size = 1844251, upload-time = "2026-07-23T01:57:16.593Z" }, - { url = "https://files.pythonhosted.org/packages/5e/19/08d41839658bdd44a0ed2480f3891705ecb487ce28c0dde62c9040c997e0/aiohttp-3.14.3-cp314-cp314t-win32.whl", hash = "sha256:b304db572b4368edd8dda8a2274f73156fe15558fca4a917cb8a09fc47af5963", size = 474180, upload-time = "2026-07-23T01:57:19.306Z" }, - { url = "https://files.pythonhosted.org/packages/99/5d/3cd6ef0a2b2851f7ab913b5b079334781bd50ff56a323e4454063377a080/aiohttp-3.14.3-cp314-cp314t-win_amd64.whl", hash = "sha256:b20032766aedf6261c7a566585a40867d092ac03a0d81592d5370ef9b054f99b", size = 500528, upload-time = "2026-07-23T01:57:21.762Z" }, - { url = "https://files.pythonhosted.org/packages/a4/37/cfd1ed540a4d318da025590d96b728e63713c09e9377950fc655dadeb856/aiohttp-3.14.3-cp314-cp314t-win_arm64.whl", hash = "sha256:2e1161602f45a54de2ce0905243a95f58cb42dcd378402f3697f5e0b21e9d2e7", size = 469280, upload-time = "2026-07-23T01:57:24.241Z" }, + { url = "https://files.pythonhosted.org/packages/b3/08/290e4be6e3ed239751c446505c324406a4ae8a82a15009a12a3c550f18d9/aiohttp-3.14.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:dea3b3653c1d0d6babd8ce09cb9e5a7776864315d9cfb1c569f926389874a261", size = 834853, upload-time = "2026-10-05T17:37:45.079Z" }, + { url = "https://files.pythonhosted.org/packages/81/81/ed5e04508ba1fcf9a34e0449c78009956e8256f62ebef708e2948594cf94/aiohttp-3.14.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:3099a389e5b5900fc79c6f613015ff3f8fa06a519744e6001cc68a31ba418cac", size = 560957, upload-time = "2026-10-05T17:37:47.497Z" }, + { url = "https://files.pythonhosted.org/packages/90/28/1a91411c53704db0481cc64b0f0c9465aa9d738856abdcaa3a5bbbe18180/aiohttp-3.14.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:70247156fc76e92919f9aacb820556cb30289a54784299a31714d030bb604d84", size = 553475, upload-time = "2026-10-05T17:37:49.099Z" }, + { url = "https://files.pythonhosted.org/packages/cf/2e/1038f3fa8832f9f4bed0f9f751f70dbc52bc4a09c66788f97bbfb0ce3d88/aiohttp-3.14.4-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:fdf2d2a6ad402797422949f4a200a60d43e3a021695c8a7804aa1d5bbef22652", size = 1845211, upload-time = "2026-10-05T17:37:50.728Z" }, + { url = "https://files.pythonhosted.org/packages/ea/54/e2253f17604c5c1c69a05e3c12400b51cd6a5fb32d7175592114d8c7a470/aiohttp-3.14.4-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:ba835fad8d4b5eaea0d34f9461cf499737a720a5f8bc6768d2f6d98a1d3ba8b5", size = 1814629, upload-time = "2026-10-05T17:37:52.481Z" }, + { url = "https://files.pythonhosted.org/packages/f1/ef/7bd1e45db925376720555d7268c2d642b113105263d37a522e41e1ba3a6c/aiohttp-3.14.4-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:0d4415ca5c9c8b24bc2f5733f870d4eab4929e680203559ba60131dd1a27852a", size = 1898528, upload-time = "2026-10-05T17:37:54.078Z" }, + { url = "https://files.pythonhosted.org/packages/5d/40/26d09668e7e0cadc16027566765aa4ce26e8a41276bad6764848c8b04d11/aiohttp-3.14.4-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:f6757e02c2c2b0d7985f57be87cf4a7c5b35708f849e1feaea3f77656ddb9dff", size = 2024385, upload-time = "2026-10-05T17:37:55.626Z" }, + { url = "https://files.pythonhosted.org/packages/73/38/0f1c4aab1cc9518e1bf874e2481e59e541b3e32330b9542e52bb2712f86f/aiohttp-3.14.4-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2a950bd8418ef54eccf5f9f517f08e37c1adab4bc50a470a0422ee1cc1032e29", size = 1859130, upload-time = "2026-10-05T17:37:57.342Z" }, + { url = "https://files.pythonhosted.org/packages/5f/98/09d5998ba4b5fe9f0cb97d794fab9d1b3d8245c5ec6a5fb84e41a8cec142/aiohttp-3.14.4-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:34cf6f2fe4fc1d7183e8cc0d8c48bbdda828a740bc372d8278126149714d343c", size = 1714768, upload-time = "2026-10-05T17:37:58.831Z" }, + { url = "https://files.pythonhosted.org/packages/c2/63/39d01a74d525d6443084d47ad4aa8c719f44a030149d03566f3761527465/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:bc0fbe4f79c3b156d754dd062718ffe404c3b31ca878d9d2b88ecdbc72ef8369", size = 1813228, upload-time = "2026-10-05T17:38:00.611Z" }, + { url = "https://files.pythonhosted.org/packages/39/6b/183d7b969bdb7892e86af74147b4afedbb4e03b8cad5006e41aa2034c288/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:d3d50a5a07a2b31a4369b86dd4a3acf3c2577c45091dbd5e884b198dec56480b", size = 1831844, upload-time = "2026-10-05T17:38:02.272Z" }, + { url = "https://files.pythonhosted.org/packages/2c/be/4c6df02b62083efd3f008974cf9016a4afd2023f5a9d2c3fd55499fcbac6/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:de15c46a63f46da881d219e44a04778c40114c756e5575b5ea38143b20eb3713", size = 1868738, upload-time = "2026-10-05T17:38:03.831Z" }, + { url = "https://files.pythonhosted.org/packages/86/21/406be8b0cf1105a35a6a6da16a95796be39b354e29bfca0d1626d822835f/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:caa4c0fc9b25e8c679baac68337e9c00deb6baf6601fe6f07e8511469cc1ceba", size = 1700006, upload-time = "2026-10-05T17:38:05.631Z" }, + { url = "https://files.pythonhosted.org/packages/4e/e6/beac98020ea0885ea1ee3b2ef59ec952405590fe2ccef2fa4ef7614c3c2b/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:3647f8c090632c70abb1e80826e4ee24faea3f895f0283b60e91a0b17aea5e34", size = 1889997, upload-time = "2026-10-05T17:38:07.578Z" }, + { url = "https://files.pythonhosted.org/packages/c4/89/d608dd9571988a529c7fead5bc79ad36b56fd52bad7941f40774acbc87e9/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:3f3e8030169843fb652a60a3d32c206e03f260198aa398985a48b41cd7e42f0a", size = 1844619, upload-time = "2026-10-05T17:38:10.003Z" }, + { url = "https://files.pythonhosted.org/packages/7e/7d/7f51e6338d2c74b75173ee66fcb50d778d5407c32f34e76ef1c4b25d0d75/aiohttp-3.14.4-cp310-cp310-win32.whl", hash = "sha256:a1205cbdddfca1428129bb6d23e0b292b09e681df951fa828145d83a63ffc0ca", size = 489598, upload-time = "2026-10-05T17:38:11.795Z" }, + { url = "https://files.pythonhosted.org/packages/33/2a/3434e450a4395fc07f3070d6ac24553f0b170b173e949216b1723395028c/aiohttp-3.14.4-cp310-cp310-win_amd64.whl", hash = "sha256:e90980e0454a043f81b435309a089ac5deab883779557eb58d004f33990f61e4", size = 512204, upload-time = "2026-10-05T17:38:13.309Z" }, + { url = "https://files.pythonhosted.org/packages/53/c0/1d89303cf1bea5418268c1cb82b872661bad027e5fd785c2d30d0a31ee6f/aiohttp-3.14.4-cp310-cp310-win_arm64.whl", hash = "sha256:e63eecf9a4b670a24055d5c0486128af16f83b02d9817abd685d3238940f8752", size = 492725, upload-time = "2026-10-05T17:38:14.825Z" }, + { url = "https://files.pythonhosted.org/packages/81/e3/998dc75634ecd2a24f33bab480b57313059d55bcadff8825a46b7c80a8af/aiohttp-3.14.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:eb0093ca0817019d539f0d27bdf98e823944e05bb7efd9d2337a45b92e4d1b06", size = 832892, upload-time = "2026-10-05T17:38:16.373Z" }, + { url = "https://files.pythonhosted.org/packages/58/c9/9bacc26397854440d169f70ae00ea51721f504611d3a64cf043643792c32/aiohttp-3.14.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f482dc9c8309801b4259dd218609d3dae0a7bcdedeac56d90500eabaa0c23465", size = 559893, upload-time = "2026-10-05T17:38:18.74Z" }, + { url = "https://files.pythonhosted.org/packages/fa/f3/90c5856014328a8b1e9a753de794edea282182b776ff65f0602ad4ffa520/aiohttp-3.14.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:aa800bb7c1d00e166493931f2ddacb982db913292503dc2f4884db1f2bc5f105", size = 552850, upload-time = "2026-10-05T17:38:20.385Z" }, + { url = "https://files.pythonhosted.org/packages/9b/88/e71c29ce6daa78fcee0feb1992f0fdc408f09f42c3311b1f1c68c36f16ea/aiohttp-3.14.4-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d90e4dae71b26597f6d1fd12af7d092ae67551edf0e524b73e0687214b79ee33", size = 1928941, upload-time = "2026-10-05T17:38:22.218Z" }, + { url = "https://files.pythonhosted.org/packages/3a/4f/f0f3bebfa521a2ce5fd4302c937701cbc50cd6d908beaa597388639b0b98/aiohttp-3.14.4-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:5b681054b8c3b86aa6a0384b6ad7f5cb78dccbabab1f4a3a6793f98ad1378959", size = 1882092, upload-time = "2026-10-05T17:38:24.016Z" }, + { url = "https://files.pythonhosted.org/packages/b5/0d/5df041fd25dceb4f4cafbbee49bb2c1e2d54a91aedecaf03b77cbb404c44/aiohttp-3.14.4-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6dfe80b41bcf8d80d2125fb99a171adeb86db2fcb35c1a68e0226acba0ba7f03", size = 1986051, upload-time = "2026-10-05T17:38:26.022Z" }, + { url = "https://files.pythonhosted.org/packages/1a/07/e95eddafffef7c3a74446f67ac4e477a49cec2c78f2ab6c86d1acfd90d2d/aiohttp-3.14.4-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:71e4a59c6a8c5a6ae8b0b696c32635913e8f526cc01448762eaf5a3c59df8a4f", size = 2107840, upload-time = "2026-10-05T17:38:28.112Z" }, + { url = "https://files.pythonhosted.org/packages/da/6c/1f83990fea249dcb10f48086726953546efc9199c96b6be7114532ac361f/aiohttp-3.14.4-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f887c3b7fb3058fc1ccd917f52078540c18d938d12018cb9edd64b6811d20c57", size = 1930721, upload-time = "2026-10-05T17:38:30.046Z" }, + { url = "https://files.pythonhosted.org/packages/6f/d1/48184a186ea26df4f81dd466144dcab7f9cdd1e131bfee0f0e41278c6f0d/aiohttp-3.14.4-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0da4525e9ba145a11617d2cd7e44fe1acaf471f9c72a0cad28e72879c1020fbb", size = 1774508, upload-time = "2026-10-05T17:38:31.8Z" }, + { url = "https://files.pythonhosted.org/packages/0f/ef/a9ec758c6d3850453838c31b56d1e4499eb47c80883753a12dcb203f9afa/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:f7e8d3c5caa44fdbee3eba1aa1417aa58c74c95d4089fe3c451911117fcbb2f3", size = 1902311, upload-time = "2026-10-05T17:38:33.791Z" }, + { url = "https://files.pythonhosted.org/packages/d6/49/9a2be54900f2dea6e63bbf9628fced604686a2e301130ccde0b1aa2e7e53/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:09092cf906c18c824b6b16881da5a89cc9cfa9b15344e496bcf880e9045bee33", size = 1912107, upload-time = "2026-10-05T17:38:35.614Z" }, + { url = "https://files.pythonhosted.org/packages/a2/2b/151254abfc0fe5cbb8e6c41ad04d52122db0af176fb31dbf3bc44e081bda/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:dfd144837e92264878bba6d3a7ffa8206668b21e87748740afd45d193e48c87e", size = 1960207, upload-time = "2026-10-05T17:38:37.322Z" }, + { url = "https://files.pythonhosted.org/packages/23/99/92c8dce336ac5784755a3144623528516f2e3b6b4871d02cad5a0642ae66/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:9413cffe4e0d654b9b524f9c99dde8cbdb37e0ed9a2c4edd2e63adbac6b374e8", size = 1760168, upload-time = "2026-10-05T17:38:39.214Z" }, + { url = "https://files.pythonhosted.org/packages/66/3e/f05fd8d1a9595730db8d522882eea76429b9be2ed5337609f7c6e3d9d49c/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:f50d719f97ba488dfb8e306cf8c8cc172ff0683ec0af53917b288229aa555ba5", size = 1979946, upload-time = "2026-10-05T17:38:40.927Z" }, + { url = "https://files.pythonhosted.org/packages/b9/14/8941aa73ffceabc2a0eb26878b4f1b2958fb7b5358f97cc49b1c00ed9258/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:68ed4824d96b7afec1f3a8d7fba190fe282718041c5772e20298003e1e3e5d66", size = 1923375, upload-time = "2026-10-05T17:38:43.184Z" }, + { url = "https://files.pythonhosted.org/packages/18/b5/ef275b63c8bfe0a21e7e8d3ef0e67c4745ed403f1894fe5205057cedd3b9/aiohttp-3.14.4-cp311-cp311-win32.whl", hash = "sha256:d7a41d1427136828e6b11d3f3fd194d4357d5205a5b610be7ae07b1ba52ab974", size = 488414, upload-time = "2026-10-05T17:38:44.978Z" }, + { url = "https://files.pythonhosted.org/packages/e7/0b/21bdd70a1e072222d9dbd96bed4fbed26f7c46c5a20af11b78d32fd049d6/aiohttp-3.14.4-cp311-cp311-win_amd64.whl", hash = "sha256:2efbdb87e79d596325c4eefaef0f4495d701145e882351310ebc538e854dc7a3", size = 512755, upload-time = "2026-10-05T17:38:47.036Z" }, + { url = "https://files.pythonhosted.org/packages/b7/4c/bb324a7d20a9598187bb028ca8d6bcf66c63589c8632420919dd576964ed/aiohttp-3.14.4-cp311-cp311-win_arm64.whl", hash = "sha256:ac6e6f90d9360e460c873f945f11dc8698db0a71fec6612823f1aaaab2c11faa", size = 492960, upload-time = "2026-10-05T17:38:49.006Z" }, + { url = "https://files.pythonhosted.org/packages/22/02/db5935d45347fa8ede56b777930740fb0e72bbb4473ddb6ff8541f6f2afa/aiohttp-3.14.4-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:55b0b335982b0db7117dff7f6a8e3aad43c4105f9e392ca04f9fc8d958a95cce", size = 817689, upload-time = "2026-10-05T17:38:50.69Z" }, + { url = "https://files.pythonhosted.org/packages/e6/56/f00aa46127e6342f019d567853eeeb932e04fb9b9424b5fb981ad68f4178/aiohttp-3.14.4-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:2d0d8e435582b0d53009dac99e26a3d2be932ed7c9dbfcfc70f3fce1cf943bd5", size = 549599, upload-time = "2026-10-05T17:38:52.525Z" }, + { url = "https://files.pythonhosted.org/packages/3f/bc/825c09b09962253a2103e4a88c04374ee939c0c8ea31c270daa0308efb07/aiohttp-3.14.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:bf734016932d68e1324cfb638cac7a0866a83933a33badf15e836a7e24efb8c0", size = 548132, upload-time = "2026-10-05T17:38:54.629Z" }, + { url = "https://files.pythonhosted.org/packages/40/80/8a1bc8036540fe7cb38219cc5c0aa67d32e9068165725e8199ea8200b08b/aiohttp-3.14.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:322e3d741b3133bcbb981a41d4f9b8ac3545c18de49c662c2b1f4e1c770b98ad", size = 1898485, upload-time = "2026-10-05T17:38:56.439Z" }, + { url = "https://files.pythonhosted.org/packages/3c/fe/65b464d8520ace0d65b4ca69bc9abe175f842c8ce8d1522d363d9669903f/aiohttp-3.14.4-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:15a3bb5f90a4e515071f3617a45dfe26560beb834a6b6e108cdf4bc9e9719ec3", size = 1875334, upload-time = "2026-10-05T17:38:58.536Z" }, + { url = "https://files.pythonhosted.org/packages/be/51/9c583be502720e927560a8414f4dfb7c7de41945e1a30ccf7003b93c6f85/aiohttp-3.14.4-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6c044e52df1a466af82cad3518c92ea80cc4ddcfea86966ff083bb34bab29bf4", size = 1937772, upload-time = "2026-10-05T17:39:00.376Z" }, + { url = "https://files.pythonhosted.org/packages/a2/3d/b56512df7ea9cbb5f59099a6b375088dd578356a5a3fb27198ab82e19832/aiohttp-3.14.4-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d613d7d51bf06fe9a5e3aab86ce06d835bb0ceb1a31ea9e8766df4a403ae62a6", size = 2066220, upload-time = "2026-10-05T17:39:02.54Z" }, + { url = "https://files.pythonhosted.org/packages/11/6c/a7a42701d9ea319140a3d44a24ec72a00b0b46d1b899b26d8a705e65bdd8/aiohttp-3.14.4-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c5e93ab6e6330dce40f5b43996f1fc5f2543296d263a5e4b59ff09e73870b7d8", size = 1922895, upload-time = "2026-10-05T17:39:04.638Z" }, + { url = "https://files.pythonhosted.org/packages/77/04/f8337bd824ca3fe3968d34dc5037ace1c4872551c4621f8266239311d301/aiohttp-3.14.4-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:20134dc8e68c67e7478124d516449428684c0545b2d3faa575691c8bcbd56678", size = 1712589, upload-time = "2026-10-05T17:39:06.671Z" }, + { url = "https://files.pythonhosted.org/packages/fe/a6/d20e2c940b592d7c4a21690889dbff64fe0ca3facd9190696368694e1488/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:f0daef5ef012369dddc391c61f604111424aa9a96313a69fb899018b09d1b01e", size = 1862251, upload-time = "2026-10-05T17:39:08.523Z" }, + { url = "https://files.pythonhosted.org/packages/f5/e4/d50edd5ae5d024b380a8e892e333840bb22967a9eb9c8492108a403f678a/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:19290a108de0718b73bc69b86e788975c6a59855c671ebe2a98a07a6f968328f", size = 1895155, upload-time = "2026-10-05T17:39:10.305Z" }, + { url = "https://files.pythonhosted.org/packages/c3/d3/f36f2931f807ccf8437ec15e8f8bfaa4748d4792639401cc767a866abaa0/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:1494877625baeffab669f4a25a09ec4eea721b49e35363081a2a8e4231fe141f", size = 1906623, upload-time = "2026-10-05T17:39:12.411Z" }, + { url = "https://files.pythonhosted.org/packages/5d/0a/94821b711493142bf5e11c27b0d7502776778f7792c77ecc6647357d20c1/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:a779ce4bf099ce4ad2cdfed62f1ca536d435f53237c54ff40172fddada24d1b5", size = 1698932, upload-time = "2026-10-05T17:39:14.446Z" }, + { url = "https://files.pythonhosted.org/packages/d9/76/3d5a0d28362f0053c1c457024749911932481e8fd105fddf8305b1f93c81/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:0b4cec9fca876e2d4f4c6cb32b177390132d04618867689f43fefabf3f5c3980", size = 1934528, upload-time = "2026-10-05T17:39:16.354Z" }, + { url = "https://files.pythonhosted.org/packages/a7/51/9784a21dc05d2e0f6acaf864f16db53dab0fbd7b0753cef168601eacb012/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:217707313e23aedde9bea67cf8365c7b138b549ae179121ef3f476cf67e3173a", size = 1901984, upload-time = "2026-10-05T17:39:18.299Z" }, + { url = "https://files.pythonhosted.org/packages/44/4f/f98c88703e6d620243aa08473a946ca4e3756b6288690e38f0d9f9c1d007/aiohttp-3.14.4-cp312-cp312-win32.whl", hash = "sha256:18a9fb9a3f6e6e63f4d27f9adeef313a2d3c69a84d31170a844623824e722534", size = 480278, upload-time = "2026-10-05T17:39:20.206Z" }, + { url = "https://files.pythonhosted.org/packages/b7/bc/8555013f84b53e4fdde423131b641af50e822c6d7d9118b24c52b31f6900/aiohttp-3.14.4-cp312-cp312-win_amd64.whl", hash = "sha256:69dcb02d33dfe415d5ee342cc63b7d320efcaf4b761701c7bd7bfb91c715481a", size = 506317, upload-time = "2026-10-05T17:39:22.706Z" }, + { url = "https://files.pythonhosted.org/packages/21/3f/ca5bad7bfdaa7ddca053a044a1c7c0d4f3ad9d1f12f96dcab10bfb9c50e7/aiohttp-3.14.4-cp312-cp312-win_arm64.whl", hash = "sha256:d36b0263e7c2fbf1750b9f35d4e7e48b0442d8c45e4a89e3e74168821fb014bb", size = 487683, upload-time = "2026-10-05T17:39:24.482Z" }, + { url = "https://files.pythonhosted.org/packages/23/ec/7fee140da700ec3f5aa5e0fd2319f67be5e86de197e2384d27e5e6209e0e/aiohttp-3.14.4-cp313-cp313-android_24_arm64_v8a.whl", hash = "sha256:264b5a7568306590c44ae4a0237ad1715e35d447ea44ebf324e4c8fd9f78f67a", size = 539114, upload-time = "2026-10-05T17:39:26.322Z" }, + { url = "https://files.pythonhosted.org/packages/4e/04/930c01ce9e186e787046433d7dc5b45b188885f8406c14b58435b4431974/aiohttp-3.14.4-cp313-cp313-android_24_x86_64.whl", hash = "sha256:17e5d7c7775d8dd8e894c7ef6ebfa26509de36868a9a6c7c4fcfaf6a1bf43d60", size = 553514, upload-time = "2026-10-05T17:39:28.104Z" }, + { url = "https://files.pythonhosted.org/packages/2c/d7/983e3cea81c07e95f35d34da4d1e182b5c05489c49b7560b198a83f0da79/aiohttp-3.14.4-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:e91dc8fe9cbd052d16f7f1267e285cf8bbac4d2194bd5741f05ef201c77ed09e", size = 521381, upload-time = "2026-10-05T17:39:30.419Z" }, + { url = "https://files.pythonhosted.org/packages/0e/2d/80baed11659093883f51245755105557d3253e45bd0b693d70df0059d68b/aiohttp-3.14.4-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:8df6157d31703972aec9e3b93963f039ff06318301e30b007c3e941ff8a7ac42", size = 528347, upload-time = "2026-10-05T17:39:32.344Z" }, + { url = "https://files.pythonhosted.org/packages/c8/18/bfda255c311096c08dab26dc65f3d219f090df37dc5f5f6345f8c3aefc1f/aiohttp-3.14.4-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:220912b351549dc736c59d104dc443fa615753102bb778a4e98f86e4d94bff6a", size = 539914, upload-time = "2026-10-05T17:39:34.265Z" }, + { url = "https://files.pythonhosted.org/packages/51/fc/3b6ca6117c0c42481d719411fff7b5d3970ebd906543d3dc1ba40fe2462f/aiohttp-3.14.4-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:2efa42b39bb3f524d5eca3760639b584afdd1143a6b047fda29910ffb75e4993", size = 813997, upload-time = "2026-10-05T17:39:36.061Z" }, + { url = "https://files.pythonhosted.org/packages/b5/f6/86e3e02a9712aadc1ae0a1076bb2d1adf3d9addfe5542a28190c8f9b6d9b/aiohttp-3.14.4-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:7e7356059c8262d2c1fd95242e2b7b70fbc6eee3135bf470049cbec3e968b5b0", size = 548058, upload-time = "2026-10-05T17:39:38.109Z" }, + { url = "https://files.pythonhosted.org/packages/85/7e/6b9c2e271419d40ca76589613b3c7ab185fd3050a407bd2565b6aa46f695/aiohttp-3.14.4-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:fac247d0cc956d732df1211ac2d8a9999ec8dc1a92a90401de9d52e4ead546f7", size = 545933, upload-time = "2026-10-05T17:39:40.193Z" }, + { url = "https://files.pythonhosted.org/packages/14/fc/33d6e24a5f8ac32423230088c415e2a1c6efee23d902b62f20506631e40b/aiohttp-3.14.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6e2eb0f8b03b4f2bd154ed8cf7c1a119a1ad04808c258bf58f90138c83b8c6d5", size = 1888265, upload-time = "2026-10-05T17:39:42.182Z" }, + { url = "https://files.pythonhosted.org/packages/8d/e8/2eca1d468d83a514621d1280f9992d08649191db2028c9236b4edfa7c723/aiohttp-3.14.4-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7fbe827d27e0e369fd7bb88ceeaa5b46ea006e73e015b9dd77e3723a53162293", size = 1872300, upload-time = "2026-10-05T17:39:44.195Z" }, + { url = "https://files.pythonhosted.org/packages/d6/f6/5872983de71b0214acdfb86822f5cca295b39be4832ec589fa224aee0f6c/aiohttp-3.14.4-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a70387146d03af9f047c629b71aa27d9594b3b31ec4c9c91e1a73d0d8bf38e0e", size = 1926213, upload-time = "2026-10-05T17:39:46.199Z" }, + { url = "https://files.pythonhosted.org/packages/ee/65/ebfefa11a546c33c717af63c67868408ecf0b33b23a9d75669af95485407/aiohttp-3.14.4-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0d0934926fc65744e2fdd44ce68b2d79d5ee608a1e23f0596b35dd696519bb7c", size = 2056609, upload-time = "2026-10-05T17:39:48.221Z" }, + { url = "https://files.pythonhosted.org/packages/69/c0/70667e82ec041f4122a17afce711bbcf94a71bec5888b69a49aed8817be2/aiohttp-3.14.4-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ff4b366510c733974adb7a4102c094e4a6308e6f369315a4cf14d2d0a619cf82", size = 1914740, upload-time = "2026-10-05T17:39:50.304Z" }, + { url = "https://files.pythonhosted.org/packages/bf/86/559e9dfea676206b20737d7ccb5b3716bff5e58d2a8d53682e5301724cd1/aiohttp-3.14.4-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:85fac7c99e0ac3dcbd6ae1c33774e0603bfc732ddb967a6fce4a731103c1888e", size = 1703390, upload-time = "2026-10-05T17:39:52.385Z" }, + { url = "https://files.pythonhosted.org/packages/fc/91/c98897d4cf23e120b2f3980042835cb34c86bbe3c653f3eaacf4bf986349/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ef1e9c3b4a2300023a5dc865889ce532cfaf6798ba4ef78fbbefe738a9d23efa", size = 1852642, upload-time = "2026-10-05T17:39:54.391Z" }, + { url = "https://files.pythonhosted.org/packages/14/13/0258f352cb2c236f358a5b57d138e15fa2566e17accc0758d968dbf2ceb6/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:97e65916588be0f952b3307aaa8460c0771fa98dbea2dd27dabc9f5d84d53c3b", size = 1890616, upload-time = "2026-10-05T17:39:56.466Z" }, + { url = "https://files.pythonhosted.org/packages/64/3c/f43e294ce1a06d1234a97bd862c1aa31acfa1a0eea3786c22fd0dc1ea731/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:840775cb39a9424f9edf142133a1192263ac5bd79117ad2a16602cef6a0c1e9d", size = 1896638, upload-time = "2026-10-05T17:39:58.585Z" }, + { url = "https://files.pythonhosted.org/packages/9f/f7/ce1e3a85b73d05037d729d3d32da7d6959b9e433435e9abd46c2fb38410f/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:54f9256430ca040d58affbd551513de13a5cff7d065204fc52b9a1b0af09a049", size = 1693003, upload-time = "2026-10-05T17:40:00.698Z" }, + { url = "https://files.pythonhosted.org/packages/1d/72/45eb900d6a9ee046728f5589f3d07f5d78f049b5fb84f48881fa4174d5df/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:6112d5931bf12c776188cab81b82bbb17d86e2e1381f2ade6edc43e6b240f0cb", size = 1927730, upload-time = "2026-10-05T17:40:02.943Z" }, + { url = "https://files.pythonhosted.org/packages/b2/43/a83ff79dc8375953a1f00b808a21c82590f4e68304fecccdcc42a25fb7d8/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:facc6df39047c4732cbd885bb62e40df20885fcd709fc399e11f81b45ce0fff9", size = 1891177, upload-time = "2026-10-05T17:40:04.989Z" }, + { url = "https://files.pythonhosted.org/packages/5c/ba/fbdc41608d4e2fb6084d960a41b392fa82beb5b126c2466de549b5c67fc8/aiohttp-3.14.4-cp313-cp313-win32.whl", hash = "sha256:7968634fa3a967a2bc0b9aeba1d5a1955501dcd7d0de44b96f7ebfb662797735", size = 479943, upload-time = "2026-10-05T17:40:07.402Z" }, + { url = "https://files.pythonhosted.org/packages/35/51/d75629750e705832fd5cd52516a82943ed58b6e09c30e14830f5d87452fa/aiohttp-3.14.4-cp313-cp313-win_amd64.whl", hash = "sha256:c0a894b0265d139cd4c2c8bd4643822cc289a4a5331e21e810881bd000ffb2dc", size = 506209, upload-time = "2026-10-05T17:40:09.49Z" }, + { url = "https://files.pythonhosted.org/packages/02/64/66452d2ffcc13e5e5ee4ba4a968656fa4a98c29ed5ff0205d4fde02b2943/aiohttp-3.14.4-cp313-cp313-win_arm64.whl", hash = "sha256:da16c3037178e72589d91de59536d271dffc92c2be2b47c38a45538cba54fd29", size = 487163, upload-time = "2026-10-05T17:40:11.526Z" }, + { url = "https://files.pythonhosted.org/packages/d2/fd/b653b1f969e2e949fe4726af7a8043e8ef117f202bed7757ac8564e077a1/aiohttp-3.14.4-cp314-cp314-android_24_arm64_v8a.whl", hash = "sha256:749bfc43bb1df71bbe6ed215044d5412d786698fc5771d2037436ca49622f3c9", size = 540738, upload-time = "2026-10-05T17:40:14.109Z" }, + { url = "https://files.pythonhosted.org/packages/90/b5/eea49a0bb697deffac5165d707ec53a24748d6720b3af77a544107b49573/aiohttp-3.14.4-cp314-cp314-android_24_x86_64.whl", hash = "sha256:c113e4b489d711f606ca278cd8dc89179746244ea841aa0638b1b134600afad0", size = 554494, upload-time = "2026-10-05T17:40:16.231Z" }, + { url = "https://files.pythonhosted.org/packages/11/ea/cf8f4efbbfa8572d9965cd43b3c6c84c581aa006772e5ce3ab4020027e9b/aiohttp-3.14.4-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:50969522bc7022026a2c7968e67da5c789f6b716b988edac55dc630390efd5df", size = 522653, upload-time = "2026-10-05T17:40:18.879Z" }, + { url = "https://files.pythonhosted.org/packages/a3/24/9f6721f0b52323789cb1041ffc3afa729462d9925607e733a065b6fc5e17/aiohttp-3.14.4-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:cbf92cd7a1c800cee244558dd5630abb45c1c1093ef7b0d546a99f526ff7a9eb", size = 529697, upload-time = "2026-10-05T17:40:21.296Z" }, + { url = "https://files.pythonhosted.org/packages/9c/a4/399debc3c2ca0ab88a08e3082b4c4f62d0f66978af60243c63f2345ef337/aiohttp-3.14.4-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:fc76be08ff407fba717a769aff04ca1b4bf9ecfdcb5caadef84a563fdbbd146d", size = 540526, upload-time = "2026-10-05T17:40:23.548Z" }, + { url = "https://files.pythonhosted.org/packages/a2/97/90379813b18b795bccdeb3a5a85e9b93ac2c69f9c2a5d0faba59da3ad6d1/aiohttp-3.14.4-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:9b416f995b68a921069e6ec61fa07f2ac3ff033d92e97a69f673af89f5bb954d", size = 818866, upload-time = "2026-10-05T17:40:25.842Z" }, + { url = "https://files.pythonhosted.org/packages/78/70/824fd0dac819652f1df895b3f621a75bf0a3050c30e38d8d2316e34ab821/aiohttp-3.14.4-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:2c9585101cfca10e74a07cc0ef2bdc6d90616e6750926b20456f429d0608f740", size = 549666, upload-time = "2026-10-05T17:40:28.523Z" }, + { url = "https://files.pythonhosted.org/packages/8c/45/eafb2dd200dd2b770ed25a2dc5731c4ba5d58ab3fa8e2e82494bb946808e/aiohttp-3.14.4-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:3c4dcf611b095e7983421f49d01ffbed7ed574891533d606ea115fc23e7c4e90", size = 548961, upload-time = "2026-10-05T17:40:30.613Z" }, + { url = "https://files.pythonhosted.org/packages/a7/bc/6c733a1c71300293471ac7ef1dffd12b5b4dc9a43c53461224b2b8a7f667/aiohttp-3.14.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f8f61a9b5fa56c58e3441f9dc64137f786232d40fb89127190d0e0f84e1e5865", size = 1883165, upload-time = "2026-10-05T17:40:33.062Z" }, + { url = "https://files.pythonhosted.org/packages/37/34/885ddbd351679a31141b25e0d1a5e4f67738806e564c858b399709b61239/aiohttp-3.14.4-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:d43e538dfc85b705fd832620d050970ef5613b3869a7169b44a554b9dab9eee9", size = 1844119, upload-time = "2026-10-05T17:40:35.266Z" }, + { url = "https://files.pythonhosted.org/packages/cc/ef/0a64dac53c11d569851efb3e7eddb43551df72b2c172ebb34cccc93bcd3f/aiohttp-3.14.4-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:4135c4bb4b7682a7633fadc7170ea969d843f83aa7224e70111a20675105c985", size = 1930222, upload-time = "2026-10-05T17:40:37.527Z" }, + { url = "https://files.pythonhosted.org/packages/69/5f/774792ed8f973e0d234fcb06b0f0bc9f29e9a0a0dd847f6418c2904be7d9/aiohttp-3.14.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:9055324f156a94fdf6dc9a825ae60f9a2947b88f591ea81ee80826633de62ae7", size = 2038842, upload-time = "2026-10-05T17:40:39.815Z" }, + { url = "https://files.pythonhosted.org/packages/cb/05/e00f35581c97656d9e864edaa03292382c620dd1d9c836a4f73a2279acc4/aiohttp-3.14.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fb22c8e4b60385a9b414c70c6e8b2d0f4b23ff7fc4bb572ceb58297b228169f1", size = 1887845, upload-time = "2026-10-05T17:40:42.359Z" }, + { url = "https://files.pythonhosted.org/packages/ca/2e/07e3eff5b4c1b082a2eaf0ffb508b409b21ea1ddc9fdc57f3eabb51469a1/aiohttp-3.14.4-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:3b6945559a260112742ed58cde2165488d2fc51aeea34afbaa99d9371b43e1b5", size = 1702533, upload-time = "2026-10-05T17:40:44.569Z" }, + { url = "https://files.pythonhosted.org/packages/75/44/816844b7f876e6f8fee4ecb088269fcd92241da712e4814a4d624eda13a9/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:8f4078a90b174f15efb2c8725e8720c40dbd3b2cf6350dbc085c964a938d9de7", size = 1849058, upload-time = "2026-10-05T17:40:47.818Z" }, + { url = "https://files.pythonhosted.org/packages/ae/bd/163242e12464a1f3e58a77e28beca949652ddce84abdd5500a91c70a1e0d/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:f433c5654e32f72de3ef074d715eb5c7604eb6d28a5c2f3c9e5056f20fe6b306", size = 1854600, upload-time = "2026-10-05T17:40:50.401Z" }, + { url = "https://files.pythonhosted.org/packages/f2/59/5c1ae708a89524eddfd9c727b87cae26b5c50c3c76683b910ac06151ead0/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:871035fe79c636b6bc126ed78df37d72b830dfc751612cb4b1040360edf2719f", size = 1896565, upload-time = "2026-10-05T17:40:52.625Z" }, + { url = "https://files.pythonhosted.org/packages/37/45/95300a7de69241fe47d3f838f3fb582c712782e172d447ff650a013ea673/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:2617132524f66338f6c1d218cd16081576aefc40df4f2bcba338a99fbf67fec1", size = 1693092, upload-time = "2026-10-05T17:40:54.862Z" }, + { url = "https://files.pythonhosted.org/packages/ff/33/01a8e61d48d0094121092c74125df14c0f8f10ee3149bfe68b6f869409a9/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:d8bc326133272deee8ef337581550450e4bb735c0520be893b950a1f5baaf41a", size = 1917073, upload-time = "2026-10-05T17:40:57.656Z" }, + { url = "https://files.pythonhosted.org/packages/9e/d6/1a4f24624cda6686d5b927e26d5d1ae3ebb692faf88e93017fab4b391fd0/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:3ec57223e261b7fa9979c12dbce009ca53439be76cac3af27f860d3e4b1d6f7a", size = 1872656, upload-time = "2026-10-05T17:41:00.123Z" }, + { url = "https://files.pythonhosted.org/packages/be/be/ed286fcfa2d22061ae021b568c790123505cd482df35e23023339ecaed96/aiohttp-3.14.4-cp314-cp314-win32.whl", hash = "sha256:7242043e71fc449a19a47d92f4e9fd1e0ae8d3f88488982381f422bf6d651218", size = 485461, upload-time = "2026-10-05T17:41:02.686Z" }, + { url = "https://files.pythonhosted.org/packages/c0/74/e040e6f65f4da305777f1adb3023d47401693489e4a337c983b52d2a0a6b/aiohttp-3.14.4-cp314-cp314-win_amd64.whl", hash = "sha256:019587c7b3a44917dd61bcb312fd5c034f341dc9851b83e7b41b65e08b68ca0f", size = 512147, upload-time = "2026-10-05T17:41:04.98Z" }, + { url = "https://files.pythonhosted.org/packages/2e/5e/bddb33ae15fdd5a68a10a986587aa9916c418a712fdd110d3b3ae9b51407/aiohttp-3.14.4-cp314-cp314-win_arm64.whl", hash = "sha256:60dc71d38db0988f37e78f6ad4a010a2f6355cfac3fff5f130cf5ef2231f3f0d", size = 494685, upload-time = "2026-10-05T17:41:07.366Z" }, + { url = "https://files.pythonhosted.org/packages/22/2e/7b884014b40573f919fc3a528e5028bc37b249e31a93928ba61bdd25c960/aiohttp-3.14.4-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:674f53ab9d2794e2dd767619a3384bf1006f8d075e43c19d449a645f8ff641c2", size = 855696, upload-time = "2026-10-05T17:41:09.514Z" }, + { url = "https://files.pythonhosted.org/packages/5f/e6/b6e2b4f580ab6ae39241bb9182aca60e6e1915cdad0148faaa04db3f366b/aiohttp-3.14.4-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:6d243221f73e5ac546c2ed9255100423e4bc092b08b944f23498e8cf3096c26c", size = 567931, upload-time = "2026-10-05T17:41:11.685Z" }, + { url = "https://files.pythonhosted.org/packages/63/99/ae8e3a1a18adcbf636839d18b3cccc51007836ccdae5209381c5cf82d1ae/aiohttp-3.14.4-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:0daa016eb74e7888ed5f9ceec6eea3158999c1c4a115ef5cbe88baa8d924f94c", size = 567421, upload-time = "2026-10-05T17:41:13.836Z" }, + { url = "https://files.pythonhosted.org/packages/63/38/c5d4bb58be72b967a4090d2deeb38571f8c992852936c51dbbbeae49db1c/aiohttp-3.14.4-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:70c031a622aa20add05ebd234b90adaf6bf51c1c88cc305ec760721af83308c3", size = 2054173, upload-time = "2026-10-05T17:41:16.098Z" }, + { url = "https://files.pythonhosted.org/packages/eb/87/3c8a9c7670f56d478a75c5bb84b336fb61a67b908e36c30a4a96ed8c8e86/aiohttp-3.14.4-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7df363fa7c38945a896e12c69af4a1a56cbd4152791d9e41fd0bac396b72de38", size = 1918296, upload-time = "2026-10-05T17:41:18.478Z" }, + { url = "https://files.pythonhosted.org/packages/49/97/bd00e499c0a1505b44f5e23b9739034ea9be792ad42537f2894211ba1c07/aiohttp-3.14.4-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:02a508ba5ad91c4d730523584c0adc65882274bba5e37c33bc2f475e37577256", size = 2027513, upload-time = "2026-10-05T17:41:20.874Z" }, + { url = "https://files.pythonhosted.org/packages/23/1d/a3666a7c224f86a881f18d673a8ffdc92fa4c35274fb4361822f8f0dc566/aiohttp-3.14.4-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0cb3edece6fe6a944eaf97d803b88f606da6bc1600b1894c2969e78ffdc1fc29", size = 2152686, upload-time = "2026-10-05T17:41:23.181Z" }, + { url = "https://files.pythonhosted.org/packages/46/7e/f4204b8c4959c46f6367c182afbbacef08a1b53874281912c52fbd80151c/aiohttp-3.14.4-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:21ce1223b461bcc5fb389a7204001578f1c0b85c2da60a84d915ebb021294245", size = 2006431, upload-time = "2026-10-05T17:41:25.776Z" }, + { url = "https://files.pythonhosted.org/packages/33/43/091e69d42967cbea833ceb355c5457f8f70748fe08b88c9d91491b3fafb8/aiohttp-3.14.4-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:35d5432f0dc1c8b71307e9112461b52f336da225e344283eec4779222c0a1dff", size = 1789101, upload-time = "2026-10-05T17:41:28.095Z" }, + { url = "https://files.pythonhosted.org/packages/47/7b/b57cbe533c01098c5d30471f057e7c3c19f281122f756acc9c716b636e2c/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:d6ec364493057c118d08292f7cd60865965c209167d8657b45643a26aef77495", size = 1974472, upload-time = "2026-10-05T17:41:30.499Z" }, + { url = "https://files.pythonhosted.org/packages/9f/44/79acce03611450e4ed8594f96f1cea40d70bc84fb4e918f94d7d9454a4af/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:70492983b7aed9e61bda82fe1ce80bcba9199610886443133783a288638923c0", size = 1956340, upload-time = "2026-10-05T17:41:33.009Z" }, + { url = "https://files.pythonhosted.org/packages/da/bb/36e6cbd6720e3377a02f8709aec6fe80de729ef41e78ba01f13d50363c73/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:a77776673331577147e9d25cd7833a72e8891b47556336cff06ba1569e488b99", size = 1965771, upload-time = "2026-10-05T17:41:35.506Z" }, + { url = "https://files.pythonhosted.org/packages/69/0f/879735ac70ce5e6852916eed51c706a517b205150a8d384f9fa60933a3fc/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:73799000dd6fd5247094fd8e6d3e1eb871e41aab5cc35dff9d9f654cd230bc24", size = 1780297, upload-time = "2026-10-05T17:41:38.284Z" }, + { url = "https://files.pythonhosted.org/packages/01/5d/7c030ca5b6baf3b02eccd11afc3d58f0b35e407031d5cc78cae9c24921c0/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:27b370fb532e707e8c96d04fa0c96301fb7dba2d50aaca57f6c456cdfffec5bd", size = 2001374, upload-time = "2026-10-05T17:41:40.888Z" }, + { url = "https://files.pythonhosted.org/packages/80/1e/ddacbb8141d727034c51dd192d17749521d5b30b03f84aa034325396089e/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:884e0d1c707b6217fee3080b9b4029eee7551af788ee761010df19be158414b7", size = 1968531, upload-time = "2026-10-05T17:41:43.62Z" }, + { url = "https://files.pythonhosted.org/packages/3a/08/2214f823701eebc3e57db141faeae76df7bfd415f254cc7c1692258f228d/aiohttp-3.14.4-cp314-cp314t-win32.whl", hash = "sha256:f2e3d34edb151d3e27f93a8338e2da33e2c7261cd4c879ce5f5fe280cc190ea5", size = 504126, upload-time = "2026-10-05T17:41:46.321Z" }, + { url = "https://files.pythonhosted.org/packages/91/a1/90e9b6fd23310b4e82d0c0a37b5ecc2944053350473c57533c1da9647235/aiohttp-3.14.4-cp314-cp314t-win_amd64.whl", hash = "sha256:88cf889e51092537fe44adfbff96c2a22d6479d6f92b97b3d413fbfd0a4decf4", size = 531494, upload-time = "2026-10-05T17:41:48.849Z" }, + { url = "https://files.pythonhosted.org/packages/97/ab/5b501472c92b9b1dc53742591d6210dccb262962f4721299300d3a9f664b/aiohttp-3.14.4-cp314-cp314t-win_arm64.whl", hash = "sha256:ca450c6d42fda7c0bfaf0e200f32f77c5f2c960a33be1e14d197c84588b7f5f6", size = 510544, upload-time = "2026-10-05T17:41:51.358Z" }, + { url = "https://files.pythonhosted.org/packages/2b/27/5e1f8446545be98e9416af59c396b1ed1f9f3294afb0a40ee3a709889273/aiohttp-3.14.4-py3-none-any.whl", hash = "sha256:5c6758ba62aea282c537179cfc8474a90f2b5f7b089cc5ff66d8920d86a9bfdd", size = 279487, upload-time = "2026-10-05T17:43:44.905Z" }, ] [[package]] @@ -10779,142 +10780,118 @@ wheels = [ [[package]] name = "yarl" -version = "1.23.0" +version = "1.25.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "idna" }, { name = "multidict" }, { name = "propcache" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/23/6e/beb1beec874a72f23815c1434518bfc4ed2175065173fb138c3705f658d4/yarl-1.23.0.tar.gz", hash = "sha256:53b1ea6ca88ebd4420379c330aea57e258408dd0df9af0992e5de2078dc9f5d5", size = 194676, upload-time = "2026-03-01T22:07:53.373Z" } +sdist = { url = "https://files.pythonhosted.org/packages/75/16/e8be8e2fb175bbf41a0680381a319f1199fae256588241a2ac8677eafb49/yarl-1.25.1.tar.gz", hash = "sha256:03dd38de09bc213e9a8b29761eec33ee1d5318dac0e49d8af36e4d27830e23a7", size = 246245, upload-time = "2026-09-15T19:35:02.264Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/8b/0d/9cc638702f6fc3c7a3685bcc8cf2a9ed7d6206e932a49f5242658047ef51/yarl-1.23.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:cff6d44cb13d39db2663a22b22305d10855efa0fa8015ddeacc40bc59b9d8107", size = 123764, upload-time = "2026-03-01T22:04:09.7Z" }, - { url = "https://files.pythonhosted.org/packages/7a/35/5a553687c5793df5429cd1db45909d4f3af7eee90014888c208d086a44f0/yarl-1.23.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e4c53f8347cd4200f0d70a48ad059cabaf24f5adc6ba08622a23423bc7efa10d", size = 86282, upload-time = "2026-03-01T22:04:11.892Z" }, - { url = "https://files.pythonhosted.org/packages/68/2e/c5a2234238f8ce37a8312b52801ee74117f576b1539eec8404a480434acc/yarl-1.23.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2a6940a074fb3c48356ed0158a3ca5699c955ee4185b4d7d619be3c327143e05", size = 86053, upload-time = "2026-03-01T22:04:13.292Z" }, - { url = "https://files.pythonhosted.org/packages/74/3f/bbd8ff36fb038622797ffbaf7db314918bb4d76f1cc8a4f9ca7a55fe5195/yarl-1.23.0-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ed5f69ce7be7902e5c70ea19eb72d20abf7d725ab5d49777d696e32d4fc1811d", size = 99395, upload-time = "2026-03-01T22:04:15.133Z" }, - { url = "https://files.pythonhosted.org/packages/77/04/9516bc4e269d2a3ec9c6779fcdeac51ce5b3a9b0156f06ac7152e5bba864/yarl-1.23.0-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:389871e65468400d6283c0308e791a640b5ab5c83bcee02a2f51295f95e09748", size = 92143, upload-time = "2026-03-01T22:04:16.829Z" }, - { url = "https://files.pythonhosted.org/packages/c7/63/88802d1f6b1cb1fc67d67a58cd0cf8a1790de4ce7946e434240f1d60ab4a/yarl-1.23.0-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:dda608c88cf709b1d406bdfcd84d8d63cff7c9e577a403c6108ce8ce9dcc8764", size = 107643, upload-time = "2026-03-01T22:04:18.519Z" }, - { url = "https://files.pythonhosted.org/packages/8e/db/4f9b838f4d8bdd6f0f385aed8bbf21c71ed11a0b9983305c302cbd557815/yarl-1.23.0-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:8c4fe09e0780c6c3bf2b7d4af02ee2394439d11a523bbcf095cf4747c2932007", size = 108700, upload-time = "2026-03-01T22:04:20.373Z" }, - { url = "https://files.pythonhosted.org/packages/50/12/95a1d33f04a79c402664070d43b8b9f72dc18914e135b345b611b0b1f8cc/yarl-1.23.0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:31c9921eb8bd12633b41ad27686bbb0b1a2a9b8452bfdf221e34f311e9942ed4", size = 102769, upload-time = "2026-03-01T22:04:23.055Z" }, - { url = "https://files.pythonhosted.org/packages/86/65/91a0285f51321369fd1a8308aa19207520c5f0587772cfc2e03fc2467e90/yarl-1.23.0-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:5f10fd85e4b75967468af655228fbfd212bdf66db1c0d135065ce288982eda26", size = 101114, upload-time = "2026-03-01T22:04:25.031Z" }, - { url = "https://files.pythonhosted.org/packages/58/80/c7c8244fc3e5bc483dc71a09560f43b619fab29301a0f0a8f936e42865c7/yarl-1.23.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:dbf507e9ef5688bada447a24d68b4b58dd389ba93b7afc065a2ba892bea54769", size = 98883, upload-time = "2026-03-01T22:04:27.281Z" }, - { url = "https://files.pythonhosted.org/packages/86/e7/71ca9cc9ca79c0b7d491216177d1aed559d632947b8ffb0ee60f7d8b23e3/yarl-1.23.0-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:85e9beda1f591bc73e77ea1c51965c68e98dafd0fec72cdd745f77d727466716", size = 94172, upload-time = "2026-03-01T22:04:28.554Z" }, - { url = "https://files.pythonhosted.org/packages/6a/3f/6c6c8a0fe29c26fb2db2e8d32195bb84ec1bfb8f1d32e7f73b787fcf349b/yarl-1.23.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:0e1fdaa14ef51366d7757b45bde294e95f6c8c049194e793eedb8387c86d5993", size = 107010, upload-time = "2026-03-01T22:04:30.385Z" }, - { url = "https://files.pythonhosted.org/packages/56/38/12730c05e5ad40a76374d440ed8b0899729a96c250516d91c620a6e38fc2/yarl-1.23.0-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:75e3026ab649bf48f9a10c0134512638725b521340293f202a69b567518d94e0", size = 100285, upload-time = "2026-03-01T22:04:31.752Z" }, - { url = "https://files.pythonhosted.org/packages/34/92/6a7be9239f2347234e027284e7a5f74b1140cc86575e7b469d13fba1ebfe/yarl-1.23.0-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:80e6d33a3d42a7549b409f199857b4fb54e2103fc44fb87605b6663b7a7ff750", size = 108230, upload-time = "2026-03-01T22:04:33.844Z" }, - { url = "https://files.pythonhosted.org/packages/5e/81/4aebccfa9376bd98b9d8bfad20621a57d3e8cfc5b8631c1fa5f62cdd03f4/yarl-1.23.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:5ec2f42d41ccbd5df0270d7df31618a8ee267bfa50997f5d720ddba86c4a83a6", size = 103008, upload-time = "2026-03-01T22:04:35.856Z" }, - { url = "https://files.pythonhosted.org/packages/38/0f/0b4e3edcec794a86b853b0c6396c0a888d72dfce19b2d88c02ac289fb6c1/yarl-1.23.0-cp310-cp310-win32.whl", hash = "sha256:debe9c4f41c32990771be5c22b56f810659f9ddf3d63f67abfdcaa2c6c9c5c1d", size = 83073, upload-time = "2026-03-01T22:04:38.268Z" }, - { url = "https://files.pythonhosted.org/packages/a0/71/ad95c33da18897e4c636528bbc24a1dd23fe16797de8bc4ec667b8db0ba4/yarl-1.23.0-cp310-cp310-win_amd64.whl", hash = "sha256:ab5f043cb8a2d71c981c09c510da013bc79fd661f5c60139f00dd3c3cc4f2ffb", size = 87328, upload-time = "2026-03-01T22:04:39.558Z" }, - { url = "https://files.pythonhosted.org/packages/e2/14/dfa369523c79bccf9c9c746b0a63eb31f65db9418ac01275f7950962e504/yarl-1.23.0-cp310-cp310-win_arm64.whl", hash = "sha256:263cd4f47159c09b8b685890af949195b51d1aa82ba451c5847ca9bc6413c220", size = 82463, upload-time = "2026-03-01T22:04:41.454Z" }, - { url = "https://files.pythonhosted.org/packages/a2/aa/60da938b8f0997ba3a911263c40d82b6f645a67902a490b46f3355e10fae/yarl-1.23.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:b35d13d549077713e4414f927cdc388d62e543987c572baee613bf82f11a4b99", size = 123641, upload-time = "2026-03-01T22:04:42.841Z" }, - { url = "https://files.pythonhosted.org/packages/24/84/e237607faf4e099dbb8a4f511cfd5efcb5f75918baad200ff7380635631b/yarl-1.23.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cbb0fef01f0c6b38cb0f39b1f78fc90b807e0e3c86a7ff3ce74ad77ce5c7880c", size = 86248, upload-time = "2026-03-01T22:04:44.757Z" }, - { url = "https://files.pythonhosted.org/packages/b2/0d/71ceabc14c146ba8ee3804ca7b3d42b1664c8440439de5214d366fec7d3a/yarl-1.23.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:dc52310451fc7c629e13c4e061cbe2dd01684d91f2f8ee2821b083c58bd72432", size = 85988, upload-time = "2026-03-01T22:04:46.365Z" }, - { url = "https://files.pythonhosted.org/packages/8c/6c/4a90d59c572e46b270ca132aca66954f1175abd691f74c1ef4c6711828e2/yarl-1.23.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b2c6b50c7b0464165472b56b42d4c76a7b864597007d9c085e8b63e185cf4a7a", size = 100566, upload-time = "2026-03-01T22:04:47.639Z" }, - { url = "https://files.pythonhosted.org/packages/49/fb/c438fb5108047e629f6282a371e6e91cf3f97ee087c4fb748a1f32ceef55/yarl-1.23.0-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:aafe5dcfda86c8af00386d7781d4c2181b5011b7be3f2add5e99899ea925df05", size = 92079, upload-time = "2026-03-01T22:04:48.925Z" }, - { url = "https://files.pythonhosted.org/packages/d9/13/d269aa1aed3e4f50a5a103f96327210cc5fa5dd2d50882778f13c7a14606/yarl-1.23.0-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:9ee33b875f0b390564c1fb7bc528abf18c8ee6073b201c6ae8524aca778e2d83", size = 108741, upload-time = "2026-03-01T22:04:50.838Z" }, - { url = "https://files.pythonhosted.org/packages/85/fb/115b16f22c37ea4437d323e472945bea97301c8ec6089868fa560abab590/yarl-1.23.0-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:4c41e021bc6d7affb3364dc1e1e5fa9582b470f283748784bd6ea0558f87f42c", size = 108099, upload-time = "2026-03-01T22:04:52.499Z" }, - { url = "https://files.pythonhosted.org/packages/9a/64/c53487d9f4968045b8afa51aed7ca44f58b2589e772f32745f3744476c82/yarl-1.23.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:99c8a9ed30f4164bc4c14b37a90208836cbf50d4ce2a57c71d0f52c7fb4f7598", size = 102678, upload-time = "2026-03-01T22:04:55.176Z" }, - { url = "https://files.pythonhosted.org/packages/85/59/cd98e556fbb2bf8fab29c1a722f67ad45c5f3447cac798ab85620d1e70af/yarl-1.23.0-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:f2af5c81a1f124609d5f33507082fc3f739959d4719b56877ab1ee7e7b3d602b", size = 100803, upload-time = "2026-03-01T22:04:56.588Z" }, - { url = "https://files.pythonhosted.org/packages/9e/c0/b39770b56d4a9f0bb5f77e2f1763cd2d75cc2f6c0131e3b4c360348fcd65/yarl-1.23.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:6b41389c19b07c760c7e427a3462e8ab83c4bb087d127f0e854c706ce1b9215c", size = 100163, upload-time = "2026-03-01T22:04:58.492Z" }, - { url = "https://files.pythonhosted.org/packages/e7/64/6980f99ab00e1f0ff67cb84766c93d595b067eed07439cfccfc8fb28c1a6/yarl-1.23.0-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:1dc702e42d0684f42d6519c8d581e49c96cefaaab16691f03566d30658ee8788", size = 93859, upload-time = "2026-03-01T22:05:00.268Z" }, - { url = "https://files.pythonhosted.org/packages/38/69/912e6c5e146793e5d4b5fe39ff5b00f4d22463dfd5a162bec565ac757673/yarl-1.23.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:0e40111274f340d32ebcc0a5668d54d2b552a6cca84c9475859d364b380e3222", size = 108202, upload-time = "2026-03-01T22:05:02.273Z" }, - { url = "https://files.pythonhosted.org/packages/59/97/35ca6767524687ad64e5f5c31ad54bc76d585585a9fcb40f649e7e82ffed/yarl-1.23.0-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:4764a6a7588561a9aef92f65bda2c4fb58fe7c675c0883862e6df97559de0bfb", size = 99866, upload-time = "2026-03-01T22:05:03.597Z" }, - { url = "https://files.pythonhosted.org/packages/d3/1c/1a3387ee6d73589f6f2a220ae06f2984f6c20b40c734989b0a44f5987308/yarl-1.23.0-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:03214408cfa590df47728b84c679ae4ef00be2428e11630277be0727eba2d7cc", size = 107852, upload-time = "2026-03-01T22:05:04.986Z" }, - { url = "https://files.pythonhosted.org/packages/a4/b8/35c0750fcd5a3f781058bfd954515dd4b1eab45e218cbb85cf11132215f1/yarl-1.23.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:170e26584b060879e29fac213e4228ef063f39128723807a312e5c7fec28eff2", size = 102919, upload-time = "2026-03-01T22:05:06.397Z" }, - { url = "https://files.pythonhosted.org/packages/e5/1c/9a1979aec4a81896d597bcb2177827f2dbee3f5b7cc48b2d0dadb644b41d/yarl-1.23.0-cp311-cp311-win32.whl", hash = "sha256:51430653db848d258336cfa0244427b17d12db63d42603a55f0d4546f50f25b5", size = 82602, upload-time = "2026-03-01T22:05:08.444Z" }, - { url = "https://files.pythonhosted.org/packages/93/22/b85eca6fa2ad9491af48c973e4c8cf6b103a73dbb271fe3346949449fca0/yarl-1.23.0-cp311-cp311-win_amd64.whl", hash = "sha256:bf49a3ae946a87083ef3a34c8f677ae4243f5b824bfc4c69672e72b3d6719d46", size = 87461, upload-time = "2026-03-01T22:05:10.145Z" }, - { url = "https://files.pythonhosted.org/packages/93/95/07e3553fe6f113e6864a20bdc53a78113cda3b9ced8784ee52a52c9f80d8/yarl-1.23.0-cp311-cp311-win_arm64.whl", hash = "sha256:b39cb32a6582750b6cc77bfb3c49c0f8760dc18dc96ec9fb55fbb0f04e08b928", size = 82336, upload-time = "2026-03-01T22:05:11.554Z" }, - { url = "https://files.pythonhosted.org/packages/88/8a/94615bc31022f711add374097ad4144d569e95ff3c38d39215d07ac153a0/yarl-1.23.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:1932b6b8bba8d0160a9d1078aae5838a66039e8832d41d2992daa9a3a08f7860", size = 124737, upload-time = "2026-03-01T22:05:12.897Z" }, - { url = "https://files.pythonhosted.org/packages/e3/6f/c6554045d59d64052698add01226bc867b52fe4a12373415d7991fdca95d/yarl-1.23.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:411225bae281f114067578891bc75534cfb3d92a3b4dfef7a6ca78ba354e6069", size = 87029, upload-time = "2026-03-01T22:05:14.376Z" }, - { url = "https://files.pythonhosted.org/packages/19/2a/725ecc166d53438bc88f76822ed4b1e3b10756e790bafd7b523fe97c322d/yarl-1.23.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:13a563739ae600a631c36ce096615fe307f131344588b0bc0daec108cdb47b25", size = 86310, upload-time = "2026-03-01T22:05:15.71Z" }, - { url = "https://files.pythonhosted.org/packages/99/30/58260ed98e6ff7f90ba84442c1ddd758c9170d70327394a6227b310cd60f/yarl-1.23.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9cbf44c5cb4a7633d078788e1b56387e3d3cf2b8139a3be38040b22d6c3221c8", size = 97587, upload-time = "2026-03-01T22:05:17.384Z" }, - { url = "https://files.pythonhosted.org/packages/76/0a/8b08aac08b50682e65759f7f8dde98ae8168f72487e7357a5d684c581ef9/yarl-1.23.0-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:53ad387048f6f09a8969631e4de3f1bf70c50e93545d64af4f751b2498755072", size = 92528, upload-time = "2026-03-01T22:05:18.804Z" }, - { url = "https://files.pythonhosted.org/packages/52/07/0b7179101fe5f8385ec6c6bb5d0cb9f76bd9fb4a769591ab6fb5cdbfc69a/yarl-1.23.0-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:4a59ba56f340334766f3a4442e0efd0af895fae9e2b204741ef885c446b3a1a8", size = 105339, upload-time = "2026-03-01T22:05:20.235Z" }, - { url = "https://files.pythonhosted.org/packages/d3/8a/36d82869ab5ec829ca8574dfcb92b51286fcfb1e9c7a73659616362dc880/yarl-1.23.0-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:803a3c3ce4acc62eaf01eaca1208dcf0783025ef27572c3336502b9c232005e7", size = 105061, upload-time = "2026-03-01T22:05:22.268Z" }, - { url = "https://files.pythonhosted.org/packages/66/3e/868e5c3364b6cee19ff3e1a122194fa4ce51def02c61023970442162859e/yarl-1.23.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a3d2bff8f37f8d0f96c7ec554d16945050d54462d6e95414babaa18bfafc7f51", size = 100132, upload-time = "2026-03-01T22:05:23.638Z" }, - { url = "https://files.pythonhosted.org/packages/cf/26/9c89acf82f08a52cb52d6d39454f8d18af15f9d386a23795389d1d423823/yarl-1.23.0-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:c75eb09e8d55bceb4367e83496ff8ef2bc7ea6960efb38e978e8073ea59ecb67", size = 99289, upload-time = "2026-03-01T22:05:25.749Z" }, - { url = "https://files.pythonhosted.org/packages/6f/54/5b0db00d2cb056922356104468019c0a132e89c8d3ab67d8ede9f4483d2a/yarl-1.23.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:877b0738624280e34c55680d6054a307aa94f7d52fa0e3034a9cc6e790871da7", size = 96950, upload-time = "2026-03-01T22:05:27.318Z" }, - { url = "https://files.pythonhosted.org/packages/f6/40/10fa93811fd439341fad7e0718a86aca0de9548023bbb403668d6555acab/yarl-1.23.0-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:b5405bb8f0e783a988172993cfc627e4d9d00432d6bbac65a923041edacf997d", size = 93960, upload-time = "2026-03-01T22:05:28.738Z" }, - { url = "https://files.pythonhosted.org/packages/bc/d2/8ae2e6cd77d0805f4526e30ec43b6f9a3dfc542d401ac4990d178e4bf0cf/yarl-1.23.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:1c3a3598a832590c5a3ce56ab5576361b5688c12cb1d39429cf5dba30b510760", size = 104703, upload-time = "2026-03-01T22:05:30.438Z" }, - { url = "https://files.pythonhosted.org/packages/2f/0c/b3ceacf82c3fe21183ce35fa2acf5320af003d52bc1fcf5915077681142e/yarl-1.23.0-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:8419ebd326430d1cbb7efb5292330a2cf39114e82df5cc3d83c9a0d5ebeaf2f2", size = 98325, upload-time = "2026-03-01T22:05:31.835Z" }, - { url = "https://files.pythonhosted.org/packages/9d/e0/12900edd28bdab91a69bd2554b85ad7b151f64e8b521fe16f9ad2f56477a/yarl-1.23.0-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:be61f6fff406ca40e3b1d84716fde398fc08bc63dd96d15f3a14230a0973ed86", size = 105067, upload-time = "2026-03-01T22:05:33.358Z" }, - { url = "https://files.pythonhosted.org/packages/15/61/74bb1182cf79c9bbe4eb6b1f14a57a22d7a0be5e9cedf8e2d5c2086474c3/yarl-1.23.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:3ceb13c5c858d01321b5d9bb65e4cf37a92169ea470b70fec6f236b2c9dd7e34", size = 100285, upload-time = "2026-03-01T22:05:35.4Z" }, - { url = "https://files.pythonhosted.org/packages/69/7f/cd5ef733f2550de6241bd8bd8c3febc78158b9d75f197d9c7baa113436af/yarl-1.23.0-cp312-cp312-win32.whl", hash = "sha256:fffc45637bcd6538de8b85f51e3df3223e4ad89bccbfca0481c08c7fc8b7ed7d", size = 82359, upload-time = "2026-03-01T22:05:36.811Z" }, - { url = "https://files.pythonhosted.org/packages/f5/be/25216a49daeeb7af2bec0db22d5e7df08ed1d7c9f65d78b14f3b74fd72fc/yarl-1.23.0-cp312-cp312-win_amd64.whl", hash = "sha256:f69f57305656a4852f2a7203efc661d8c042e6cc67f7acd97d8667fb448a426e", size = 87674, upload-time = "2026-03-01T22:05:38.171Z" }, - { url = "https://files.pythonhosted.org/packages/d2/35/aeab955d6c425b227d5b7247eafb24f2653fedc32f95373a001af5dfeb9e/yarl-1.23.0-cp312-cp312-win_arm64.whl", hash = "sha256:6e87a6e8735b44816e7db0b2fbc9686932df473c826b0d9743148432e10bb9b9", size = 81879, upload-time = "2026-03-01T22:05:40.006Z" }, - { url = "https://files.pythonhosted.org/packages/9a/4b/a0a6e5d0ee8a2f3a373ddef8a4097d74ac901ac363eea1440464ccbe0898/yarl-1.23.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:16c6994ac35c3e74fb0ae93323bf8b9c2a9088d55946109489667c510a7d010e", size = 123796, upload-time = "2026-03-01T22:05:41.412Z" }, - { url = "https://files.pythonhosted.org/packages/67/b6/8925d68af039b835ae876db5838e82e76ec87b9782ecc97e192b809c4831/yarl-1.23.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:4a42e651629dafb64fd5b0286a3580613702b5809ad3f24934ea87595804f2c5", size = 86547, upload-time = "2026-03-01T22:05:42.841Z" }, - { url = "https://files.pythonhosted.org/packages/ae/50/06d511cc4b8e0360d3c94af051a768e84b755c5eb031b12adaaab6dec6e5/yarl-1.23.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:7c6b9461a2a8b47c65eef63bb1c76a4f1c119618ffa99ea79bc5bb1e46c5821b", size = 85854, upload-time = "2026-03-01T22:05:44.85Z" }, - { url = "https://files.pythonhosted.org/packages/c4/f4/4e30b250927ffdab4db70da08b9b8d2194d7c7b400167b8fbeca1e4701ca/yarl-1.23.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:2569b67d616eab450d262ca7cb9f9e19d2f718c70a8b88712859359d0ab17035", size = 98351, upload-time = "2026-03-01T22:05:46.836Z" }, - { url = "https://files.pythonhosted.org/packages/86/fc/4118c5671ea948208bdb1492d8b76bdf1453d3e73df051f939f563e7dcc5/yarl-1.23.0-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:e9d9a4d06d3481eab79803beb4d9bd6f6a8e781ec078ac70d7ef2dcc29d1bea5", size = 92711, upload-time = "2026-03-01T22:05:48.316Z" }, - { url = "https://files.pythonhosted.org/packages/56/11/1ed91d42bd9e73c13dc9e7eb0dd92298d75e7ac4dd7f046ad0c472e231cd/yarl-1.23.0-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f514f6474e04179d3d33175ed3f3e31434d3130d42ec153540d5b157deefd735", size = 106014, upload-time = "2026-03-01T22:05:50.028Z" }, - { url = "https://files.pythonhosted.org/packages/ce/c9/74e44e056a23fbc33aca71779ef450ca648a5bc472bdad7a82339918f818/yarl-1.23.0-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:fda207c815b253e34f7e1909840fd14299567b1c0eb4908f8c2ce01a41265401", size = 105557, upload-time = "2026-03-01T22:05:51.416Z" }, - { url = "https://files.pythonhosted.org/packages/66/fe/b1e10b08d287f518994f1e2ff9b6d26f0adeecd8dd7d533b01bab29a3eda/yarl-1.23.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:34b6cf500e61c90f305094911f9acc9c86da1a05a7a3f5be9f68817043f486e4", size = 101559, upload-time = "2026-03-01T22:05:52.872Z" }, - { url = "https://files.pythonhosted.org/packages/72/59/c5b8d94b14e3d3c2a9c20cb100119fd534ab5a14b93673ab4cc4a4141ea5/yarl-1.23.0-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:d7504f2b476d21653e4d143f44a175f7f751cd41233525312696c76aa3dbb23f", size = 100502, upload-time = "2026-03-01T22:05:54.954Z" }, - { url = "https://files.pythonhosted.org/packages/77/4f/96976cb54cbfc5c9fd73ed4c51804f92f209481d1fb190981c0f8a07a1d7/yarl-1.23.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:578110dd426f0d209d1509244e6d4a3f1a3e9077655d98c5f22583d63252a08a", size = 98027, upload-time = "2026-03-01T22:05:56.409Z" }, - { url = "https://files.pythonhosted.org/packages/63/6e/904c4f476471afdbad6b7e5b70362fb5810e35cd7466529a97322b6f5556/yarl-1.23.0-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:609d3614d78d74ebe35f54953c5bbd2ac647a7ddb9c30a5d877580f5e86b22f2", size = 95369, upload-time = "2026-03-01T22:05:58.141Z" }, - { url = "https://files.pythonhosted.org/packages/9d/40/acfcdb3b5f9d68ef499e39e04d25e141fe90661f9d54114556cf83be8353/yarl-1.23.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:4966242ec68afc74c122f8459abd597afd7d8a60dc93d695c1334c5fd25f762f", size = 105565, upload-time = "2026-03-01T22:06:00.286Z" }, - { url = "https://files.pythonhosted.org/packages/5e/c6/31e28f3a6ba2869c43d124f37ea5260cac9c9281df803c354b31f4dd1f3c/yarl-1.23.0-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:e0fd068364a6759bc794459f0a735ab151d11304346332489c7972bacbe9e72b", size = 99813, upload-time = "2026-03-01T22:06:01.712Z" }, - { url = "https://files.pythonhosted.org/packages/08/1f/6f65f59e72d54aa467119b63fc0b0b1762eff0232db1f4720cd89e2f4a17/yarl-1.23.0-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:39004f0ad156da43e86aa71f44e033de68a44e5a31fc53507b36dd253970054a", size = 105632, upload-time = "2026-03-01T22:06:03.188Z" }, - { url = "https://files.pythonhosted.org/packages/a3/c4/18b178a69935f9e7a338127d5b77d868fdc0f0e49becd286d51b3a18c61d/yarl-1.23.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:e5723c01a56c5028c807c701aa66722916d2747ad737a046853f6c46f4875543", size = 101895, upload-time = "2026-03-01T22:06:04.651Z" }, - { url = "https://files.pythonhosted.org/packages/8f/54/f5b870b5505663911dba950a8e4776a0dbd51c9c54c0ae88e823e4b874a0/yarl-1.23.0-cp313-cp313-win32.whl", hash = "sha256:1b6b572edd95b4fa8df75de10b04bc81acc87c1c7d16bcdd2035b09d30acc957", size = 82356, upload-time = "2026-03-01T22:06:06.04Z" }, - { url = "https://files.pythonhosted.org/packages/7a/84/266e8da36879c6edcd37b02b547e2d9ecdfea776be49598e75696e3316e1/yarl-1.23.0-cp313-cp313-win_amd64.whl", hash = "sha256:baaf55442359053c7d62f6f8413a62adba3205119bcb6f49594894d8be47e5e3", size = 87515, upload-time = "2026-03-01T22:06:08.107Z" }, - { url = "https://files.pythonhosted.org/packages/00/fd/7e1c66efad35e1649114fa13f17485f62881ad58edeeb7f49f8c5e748bf9/yarl-1.23.0-cp313-cp313-win_arm64.whl", hash = "sha256:fb4948814a2a98e3912505f09c9e7493b1506226afb1f881825368d6fb776ee3", size = 81785, upload-time = "2026-03-01T22:06:10.181Z" }, - { url = "https://files.pythonhosted.org/packages/9c/fc/119dd07004f17ea43bb91e3ece6587759edd7519d6b086d16bfbd3319982/yarl-1.23.0-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:aecfed0b41aa72b7881712c65cf764e39ce2ec352324f5e0837c7048d9e6daaa", size = 130719, upload-time = "2026-03-01T22:06:11.708Z" }, - { url = "https://files.pythonhosted.org/packages/e6/0d/9f2348502fbb3af409e8f47730282cd6bc80dec6630c1e06374d882d6eb2/yarl-1.23.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:a41bcf68efd19073376eb8cf948b8d9be0af26256403e512bb18f3966f1f9120", size = 89690, upload-time = "2026-03-01T22:06:13.429Z" }, - { url = "https://files.pythonhosted.org/packages/50/93/e88f3c80971b42cfc83f50a51b9d165a1dbf154b97005f2994a79f212a07/yarl-1.23.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:cde9a2ecd91668bcb7f077c4966d8ceddb60af01b52e6e3e2680e4cf00ad1a59", size = 89851, upload-time = "2026-03-01T22:06:15.53Z" }, - { url = "https://files.pythonhosted.org/packages/1c/07/61c9dd8ba8f86473263b4036f70fb594c09e99c0d9737a799dfd8bc85651/yarl-1.23.0-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5023346c4ee7992febc0068e7593de5fa2bf611848c08404b35ebbb76b1b0512", size = 95874, upload-time = "2026-03-01T22:06:17.553Z" }, - { url = "https://files.pythonhosted.org/packages/9e/e9/f9ff8ceefba599eac6abddcfb0b3bee9b9e636e96dbf54342a8577252379/yarl-1.23.0-cp313-cp313t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:d1009abedb49ae95b136a8904a3f71b342f849ffeced2d3747bf29caeda218c4", size = 88710, upload-time = "2026-03-01T22:06:19.004Z" }, - { url = "https://files.pythonhosted.org/packages/eb/78/0231bfcc5d4c8eec220bc2f9ef82cb4566192ea867a7c5b4148f44f6cbcd/yarl-1.23.0-cp313-cp313t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a8d00f29b42f534cc8aa3931cfe773b13b23e561e10d2b26f27a8d309b0e82a1", size = 101033, upload-time = "2026-03-01T22:06:21.203Z" }, - { url = "https://files.pythonhosted.org/packages/cd/9b/30ea5239a61786f18fd25797151a17fbb3be176977187a48d541b5447dd4/yarl-1.23.0-cp313-cp313t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:95451e6ce06c3e104556d73b559f5da6c34a069b6b62946d3ad66afcd51642ea", size = 100817, upload-time = "2026-03-01T22:06:22.738Z" }, - { url = "https://files.pythonhosted.org/packages/62/e2/a4980481071791bc83bce2b7a1a1f7adcabfa366007518b4b845e92eeee3/yarl-1.23.0-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:531ef597132086b6cf96faa7c6c1dcd0361dd5f1694e5cc30375907b9b7d3ea9", size = 97482, upload-time = "2026-03-01T22:06:24.21Z" }, - { url = "https://files.pythonhosted.org/packages/e5/1e/304a00cf5f6100414c4b5a01fc7ff9ee724b62158a08df2f8170dfc72a2d/yarl-1.23.0-cp313-cp313t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:88f9fb0116fbfcefcab70f85cf4b74a2b6ce5d199c41345296f49d974ddb4123", size = 95949, upload-time = "2026-03-01T22:06:25.697Z" }, - { url = "https://files.pythonhosted.org/packages/68/03/093f4055ed4cae649ac53bca3d180bd37102e9e11d048588e9ab0c0108d0/yarl-1.23.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:e7b0460976dc75cb87ad9cc1f9899a4b97751e7d4e77ab840fc9b6d377b8fd24", size = 95839, upload-time = "2026-03-01T22:06:27.309Z" }, - { url = "https://files.pythonhosted.org/packages/b9/28/4c75ebb108f322aa8f917ae10a8ffa4f07cae10a8a627b64e578617df6a0/yarl-1.23.0-cp313-cp313t-musllinux_1_2_armv7l.whl", hash = "sha256:115136c4a426f9da976187d238e84139ff6b51a20839aa6e3720cd1026d768de", size = 90696, upload-time = "2026-03-01T22:06:29.048Z" }, - { url = "https://files.pythonhosted.org/packages/23/9c/42c2e2dd91c1a570402f51bdf066bfdb1241c2240ba001967bad778e77b7/yarl-1.23.0-cp313-cp313t-musllinux_1_2_ppc64le.whl", hash = "sha256:ead11956716a940c1abc816b7df3fa2b84d06eaed8832ca32f5c5e058c65506b", size = 100865, upload-time = "2026-03-01T22:06:30.525Z" }, - { url = "https://files.pythonhosted.org/packages/74/05/1bcd60a8a0a914d462c305137246b6f9d167628d73568505fce3f1cb2e65/yarl-1.23.0-cp313-cp313t-musllinux_1_2_riscv64.whl", hash = "sha256:fe8f8f5e70e6dbdfca9882cd9deaac058729bcf323cf7a58660901e55c9c94f6", size = 96234, upload-time = "2026-03-01T22:06:32.692Z" }, - { url = "https://files.pythonhosted.org/packages/90/b2/f52381aac396d6778ce516b7bc149c79e65bfc068b5de2857ab69eeea3b7/yarl-1.23.0-cp313-cp313t-musllinux_1_2_s390x.whl", hash = "sha256:a0e317df055958a0c1e79e5d2aa5a5eaa4a6d05a20d4b0c9c3f48918139c9fc6", size = 100295, upload-time = "2026-03-01T22:06:34.268Z" }, - { url = "https://files.pythonhosted.org/packages/e5/e8/638bae5bbf1113a659b2435d8895474598afe38b4a837103764f603aba56/yarl-1.23.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:6f0fd84de0c957b2d280143522c4f91a73aada1923caee763e24a2b3fda9f8a5", size = 97784, upload-time = "2026-03-01T22:06:35.864Z" }, - { url = "https://files.pythonhosted.org/packages/80/25/a3892b46182c586c202629fc2159aa13975d3741d52ebd7347fd501d48d5/yarl-1.23.0-cp313-cp313t-win32.whl", hash = "sha256:93a784271881035ab4406a172edb0faecb6e7d00f4b53dc2f55919d6c9688595", size = 88313, upload-time = "2026-03-01T22:06:37.39Z" }, - { url = "https://files.pythonhosted.org/packages/43/68/8c5b36aa5178900b37387937bc2c2fe0e9505537f713495472dcf6f6fccc/yarl-1.23.0-cp313-cp313t-win_amd64.whl", hash = "sha256:dd00607bffbf30250fe108065f07453ec124dbf223420f57f5e749b04295e090", size = 94932, upload-time = "2026-03-01T22:06:39.579Z" }, - { url = "https://files.pythonhosted.org/packages/c6/cc/d79ba8292f51f81f4dc533a8ccfb9fc6992cabf0998ed3245de7589dc07c/yarl-1.23.0-cp313-cp313t-win_arm64.whl", hash = "sha256:ac09d42f48f80c9ee1635b2fcaa819496a44502737660d3c0f2ade7526d29144", size = 84786, upload-time = "2026-03-01T22:06:41.988Z" }, - { url = "https://files.pythonhosted.org/packages/90/98/b85a038d65d1b92c3903ab89444f48d3cee490a883477b716d7a24b1a78c/yarl-1.23.0-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:21d1b7305a71a15b4794b5ff22e8eef96ff4a6d7f9657155e5aa419444b28912", size = 124455, upload-time = "2026-03-01T22:06:43.615Z" }, - { url = "https://files.pythonhosted.org/packages/39/54/bc2b45559f86543d163b6e294417a107bb87557609007c007ad889afec18/yarl-1.23.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:85610b4f27f69984932a7abbe52703688de3724d9f72bceb1cca667deff27474", size = 86752, upload-time = "2026-03-01T22:06:45.425Z" }, - { url = "https://files.pythonhosted.org/packages/24/f9/e8242b68362bffe6fb536c8db5076861466fc780f0f1b479fc4ffbebb128/yarl-1.23.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:23f371bd662cf44a7630d4d113101eafc0cfa7518a2760d20760b26021454719", size = 86291, upload-time = "2026-03-01T22:06:46.974Z" }, - { url = "https://files.pythonhosted.org/packages/ea/d8/d1cb2378c81dd729e98c716582b1ccb08357e8488e4c24714658cc6630e8/yarl-1.23.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c4a80f77dc1acaaa61f0934176fccca7096d9b1ff08c8ba9cddf5ae034a24319", size = 99026, upload-time = "2026-03-01T22:06:48.459Z" }, - { url = "https://files.pythonhosted.org/packages/0a/ff/7196790538f31debe3341283b5b0707e7feb947620fc5e8236ef28d44f72/yarl-1.23.0-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:bd654fad46d8d9e823afbb4f87c79160b5a374ed1ff5bde24e542e6ba8f41434", size = 92355, upload-time = "2026-03-01T22:06:50.306Z" }, - { url = "https://files.pythonhosted.org/packages/c1/56/25d58c3eddde825890a5fe6aa1866228377354a3c39262235234ab5f616b/yarl-1.23.0-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:682bae25f0a0dd23a056739f23a134db9f52a63e2afd6bfb37ddc76292bbd723", size = 106417, upload-time = "2026-03-01T22:06:52.1Z" }, - { url = "https://files.pythonhosted.org/packages/51/8a/882c0e7bc8277eb895b31bce0138f51a1ba551fc2e1ec6753ffc1e7c1377/yarl-1.23.0-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:a82836cab5f197a0514235aaf7ffccdc886ccdaa2324bc0aafdd4ae898103039", size = 106422, upload-time = "2026-03-01T22:06:54.424Z" }, - { url = "https://files.pythonhosted.org/packages/42/2b/fef67d616931055bf3d6764885990a3ac647d68734a2d6a9e1d13de437a2/yarl-1.23.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1c57676bdedc94cd3bc37724cf6f8cd2779f02f6aba48de45feca073e714fe52", size = 101915, upload-time = "2026-03-01T22:06:55.895Z" }, - { url = "https://files.pythonhosted.org/packages/18/6a/530e16aebce27c5937920f3431c628a29a4b6b430fab3fd1c117b26ff3f6/yarl-1.23.0-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:c7f8dc16c498ff06497c015642333219871effba93e4a2e8604a06264aca5c5c", size = 100690, upload-time = "2026-03-01T22:06:58.21Z" }, - { url = "https://files.pythonhosted.org/packages/88/08/93749219179a45e27b036e03260fda05190b911de8e18225c294ac95bbc9/yarl-1.23.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:5ee586fb17ff8f90c91cf73c6108a434b02d69925f44f5f8e0d7f2f260607eae", size = 98750, upload-time = "2026-03-01T22:06:59.794Z" }, - { url = "https://files.pythonhosted.org/packages/d9/cf/ea424a004969f5d81a362110a6ac1496d79efdc6d50c2c4b2e3ea0fc2519/yarl-1.23.0-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:17235362f580149742739cc3828b80e24029d08cbb9c4bda0242c7b5bc610a8e", size = 94685, upload-time = "2026-03-01T22:07:01.375Z" }, - { url = "https://files.pythonhosted.org/packages/e2/b7/14341481fe568e2b0408bcf1484c652accafe06a0ade9387b5d3fd9df446/yarl-1.23.0-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:0793e2bd0cf14234983bbb371591e6bea9e876ddf6896cdcc93450996b0b5c85", size = 106009, upload-time = "2026-03-01T22:07:03.151Z" }, - { url = "https://files.pythonhosted.org/packages/0a/e6/5c744a9b54f4e8007ad35bce96fbc9218338e84812d36f3390cea616881a/yarl-1.23.0-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:3650dc2480f94f7116c364096bc84b1d602f44224ef7d5c7208425915c0475dd", size = 100033, upload-time = "2026-03-01T22:07:04.701Z" }, - { url = "https://files.pythonhosted.org/packages/0c/23/e3bfc188d0b400f025bc49d99793d02c9abe15752138dcc27e4eaf0c4a9e/yarl-1.23.0-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:f40e782d49630ad384db66d4d8b73ff4f1b8955dc12e26b09a3e3af064b3b9d6", size = 106483, upload-time = "2026-03-01T22:07:06.231Z" }, - { url = "https://files.pythonhosted.org/packages/72/42/f0505f949a90b3f8b7a363d6cbdf398f6e6c58946d85c6d3a3bc70595b26/yarl-1.23.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:94f8575fbdf81749008d980c17796097e645574a3b8c28ee313931068dad14fe", size = 102175, upload-time = "2026-03-01T22:07:08.4Z" }, - { url = "https://files.pythonhosted.org/packages/aa/65/b39290f1d892a9dd671d1c722014ca062a9c35d60885d57e5375db0404b5/yarl-1.23.0-cp314-cp314-win32.whl", hash = "sha256:c8aa34a5c864db1087d911a0b902d60d203ea3607d91f615acd3f3108ac32169", size = 83871, upload-time = "2026-03-01T22:07:09.968Z" }, - { url = "https://files.pythonhosted.org/packages/a9/5b/9b92f54c784c26e2a422e55a8d2607ab15b7ea3349e28359282f84f01d43/yarl-1.23.0-cp314-cp314-win_amd64.whl", hash = "sha256:63e92247f383c85ab00dd0091e8c3fa331a96e865459f5ee80353c70a4a42d70", size = 89093, upload-time = "2026-03-01T22:07:11.501Z" }, - { url = "https://files.pythonhosted.org/packages/e0/7d/8a84dc9381fd4412d5e7ff04926f9865f6372b4c2fd91e10092e65d29eb8/yarl-1.23.0-cp314-cp314-win_arm64.whl", hash = "sha256:70efd20be968c76ece7baa8dafe04c5be06abc57f754d6f36f3741f7aa7a208e", size = 83384, upload-time = "2026-03-01T22:07:13.069Z" }, - { url = "https://files.pythonhosted.org/packages/dd/8d/d2fad34b1c08aa161b74394183daa7d800141aaaee207317e82c790b418d/yarl-1.23.0-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:9a18d6f9359e45722c064c97464ec883eb0e0366d33eda61cb19a244bf222679", size = 131019, upload-time = "2026-03-01T22:07:14.903Z" }, - { url = "https://files.pythonhosted.org/packages/19/ff/33009a39d3ccf4b94d7d7880dfe17fb5816c5a4fe0096d9b56abceea9ac7/yarl-1.23.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:2803ed8b21ca47a43da80a6fd1ed3019d30061f7061daa35ac54f63933409412", size = 89894, upload-time = "2026-03-01T22:07:17.372Z" }, - { url = "https://files.pythonhosted.org/packages/0c/f1/dab7ac5e7306fb79c0190766a3c00b4cb8d09a1f390ded68c85a5934faf5/yarl-1.23.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:394906945aa8b19fc14a61cf69743a868bb8c465efe85eee687109cc540b98f4", size = 89979, upload-time = "2026-03-01T22:07:19.361Z" }, - { url = "https://files.pythonhosted.org/packages/aa/b1/08e95f3caee1fad6e65017b9f26c1d79877b502622d60e517de01e72f95d/yarl-1.23.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:71d006bee8397a4a89f469b8deb22469fe7508132d3c17fa6ed871e79832691c", size = 95943, upload-time = "2026-03-01T22:07:21.266Z" }, - { url = "https://files.pythonhosted.org/packages/c0/cc/6409f9018864a6aa186c61175b977131f373f1988e198e031236916e87e4/yarl-1.23.0-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:62694e275c93d54f7ccedcfef57d42761b2aad5234b6be1f3e3026cae4001cd4", size = 88786, upload-time = "2026-03-01T22:07:23.129Z" }, - { url = "https://files.pythonhosted.org/packages/76/40/cc22d1d7714b717fde2006fad2ced5efe5580606cb059ae42117542122f3/yarl-1.23.0-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a31de1613658308efdb21ada98cbc86a97c181aa050ba22a808120bb5be3ab94", size = 101307, upload-time = "2026-03-01T22:07:24.689Z" }, - { url = "https://files.pythonhosted.org/packages/8f/0d/476c38e85ddb4c6ec6b20b815bdd779aa386a013f3d8b85516feee55c8dc/yarl-1.23.0-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:fb1e8b8d66c278b21d13b0a7ca22c41dd757a7c209c6b12c313e445c31dd3b28", size = 100904, upload-time = "2026-03-01T22:07:26.287Z" }, - { url = "https://files.pythonhosted.org/packages/72/32/0abe4a76d59adf2081dcb0397168553ece4616ada1c54d1c49d8936c74f8/yarl-1.23.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:50f9d8d531dfb767c565f348f33dd5139a6c43f5cbdf3f67da40d54241df93f6", size = 97728, upload-time = "2026-03-01T22:07:27.906Z" }, - { url = "https://files.pythonhosted.org/packages/b7/35/7b30f4810fba112f60f5a43237545867504e15b1c7647a785fbaf588fac2/yarl-1.23.0-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:575aa4405a656e61a540f4a80eaa5260f2a38fff7bfdc4b5f611840d76e9e277", size = 95964, upload-time = "2026-03-01T22:07:30.198Z" }, - { url = "https://files.pythonhosted.org/packages/2d/86/ed7a73ab85ef00e8bb70b0cb5421d8a2a625b81a333941a469a6f4022828/yarl-1.23.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:041b1a4cefacf65840b4e295c6985f334ba83c30607441ae3cf206a0eed1a2e4", size = 95882, upload-time = "2026-03-01T22:07:32.132Z" }, - { url = "https://files.pythonhosted.org/packages/19/90/d56967f61a29d8498efb7afb651e0b2b422a1e9b47b0ab5f4e40a19b699b/yarl-1.23.0-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:d38c1e8231722c4ce40d7593f28d92b5fc72f3e9774fe73d7e800ec32299f63a", size = 90797, upload-time = "2026-03-01T22:07:34.404Z" }, - { url = "https://files.pythonhosted.org/packages/72/00/8b8f76909259f56647adb1011d7ed8b321bcf97e464515c65016a47ecdf0/yarl-1.23.0-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:d53834e23c015ee83a99377db6e5e37d8484f333edb03bd15b4bc312cc7254fb", size = 101023, upload-time = "2026-03-01T22:07:35.953Z" }, - { url = "https://files.pythonhosted.org/packages/ac/e2/cab11b126fb7d440281b7df8e9ddbe4851e70a4dde47a202b6642586b8d9/yarl-1.23.0-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:2e27c8841126e017dd2a054a95771569e6070b9ee1b133366d8b31beb5018a41", size = 96227, upload-time = "2026-03-01T22:07:37.594Z" }, - { url = "https://files.pythonhosted.org/packages/c2/9b/2c893e16bfc50e6b2edf76c1a9eb6cb0c744346197e74c65e99ad8d634d0/yarl-1.23.0-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:76855800ac56f878847a09ce6dba727c93ca2d89c9e9d63002d26b916810b0a2", size = 100302, upload-time = "2026-03-01T22:07:39.334Z" }, - { url = "https://files.pythonhosted.org/packages/28/ec/5498c4e3a6d5f1003beb23405671c2eb9cdbf3067d1c80f15eeafe301010/yarl-1.23.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:e09fd068c2e169a7070d83d3bde728a4d48de0549f975290be3c108c02e499b4", size = 98202, upload-time = "2026-03-01T22:07:41.717Z" }, - { url = "https://files.pythonhosted.org/packages/fe/c3/cd737e2d45e70717907f83e146f6949f20cc23cd4bf7b2688727763aa458/yarl-1.23.0-cp314-cp314t-win32.whl", hash = "sha256:73309162a6a571d4cbd3b6a1dcc703c7311843ae0d1578df6f09be4e98df38d4", size = 90558, upload-time = "2026-03-01T22:07:43.433Z" }, - { url = "https://files.pythonhosted.org/packages/e1/19/3774d162f6732d1cfb0b47b4140a942a35ca82bb19b6db1f80e9e7bdc8f8/yarl-1.23.0-cp314-cp314t-win_amd64.whl", hash = "sha256:4503053d296bc6e4cbd1fad61cf3b6e33b939886c4f249ba7c78b602214fabe2", size = 97610, upload-time = "2026-03-01T22:07:45.773Z" }, - { url = "https://files.pythonhosted.org/packages/51/47/3fa2286c3cb162c71cdb34c4224d5745a1ceceb391b2bd9b19b668a8d724/yarl-1.23.0-cp314-cp314t-win_arm64.whl", hash = "sha256:44bb7bef4ea409384e3f8bc36c063d77ea1b8d4a5b2706956c0d6695f07dcc25", size = 86041, upload-time = "2026-03-01T22:07:49.026Z" }, - { url = "https://files.pythonhosted.org/packages/69/68/c8739671f5699c7dc470580a4f821ef37c32c4cb0b047ce223a7f115757f/yarl-1.23.0-py3-none-any.whl", hash = "sha256:a2df6afe50dea8ae15fa34c9f824a3ee958d785fd5d089063d960bae1daa0a3f", size = 48288, upload-time = "2026-03-01T22:07:51.388Z" }, + { url = "https://files.pythonhosted.org/packages/85/92/55fa9ee84cb8ec9930a910b5753936a926f918d8cc8965bdac571479c095/yarl-1.25.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:142c06c4d6a35ee3ec5da08499805e879cb3ca7c1fbfbecb0140fe72403818d6", size = 144695, upload-time = "2026-09-15T19:29:53.114Z" }, + { url = "https://files.pythonhosted.org/packages/16/b4/9edc8e605b16b2eb5bd0c2ccc73e2b15aab583862460767fb43f91f11839/yarl-1.25.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:24ce942011a61953e7d313438038f4d32ff21387b775f58a957f7a07dd55ef95", size = 104332, upload-time = "2026-09-15T19:29:55.443Z" }, + { url = "https://files.pythonhosted.org/packages/ae/de/4204e6646e278b1cd4a9cf73ebe8b7cfcf16693f1249b324eb273d67602a/yarl-1.25.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9e23c82b63cd7652fc24d33ed6cc17099d607aa3b4fc4ddc75e95062f3d82df4", size = 104449, upload-time = "2026-09-15T19:29:57.239Z" }, + { url = "https://files.pythonhosted.org/packages/1d/fc/21d74789198ad68a23a209ab0d73fe5a52d39ebbd9945041e72827acdd77/yarl-1.25.1-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8ee202350cf57abf0e9502a41601841019c25d3db7ff52d980aaf31446254059", size = 116828, upload-time = "2026-09-15T19:29:59.031Z" }, + { url = "https://files.pythonhosted.org/packages/8f/31/90891ddb61848c067ebd1fb505ab5902a6e7d4707c2f3823f67ff37883d3/yarl-1.25.1-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:5df89f769cc8ff94c3d7e7603386fba309d25ce5240132d26c15baa8d0e96c4c", size = 107150, upload-time = "2026-09-15T19:30:00.868Z" }, + { url = "https://files.pythonhosted.org/packages/a1/15/f3d18743d3688b5f01aa83034b6c00665692ab20e1d0c89a29000d4979ea/yarl-1.25.1-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:83e9f4a25085bd4b7214701a0794ff1f50fc633ffb8bdfebf07abdd81c2db126", size = 124704, upload-time = "2026-09-15T19:30:03.128Z" }, + { url = "https://files.pythonhosted.org/packages/99/37/718789d8004775d6a2db86b2afc72b1d156e0590b88a1b8634ddd4bdb8ee/yarl-1.25.1-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:e636b64d24fd9c38053c5e389a1174c66361fa49dcfd220f4dd35b4abde7cb89", size = 129246, upload-time = "2026-09-15T19:30:05.014Z" }, + { url = "https://files.pythonhosted.org/packages/28/b9/7818ac6dec7fbcd16be2d19495807c01e2c38834e57d41c63356a75e786b/yarl-1.25.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e5637ca8d0bd7fb72648a6c7934af4baaccb697657f7438c9d264fc2abb8b0b1", size = 118071, upload-time = "2026-09-15T19:30:06.977Z" }, + { url = "https://files.pythonhosted.org/packages/b2/e3/8d098cafb30a64df7283b5a5dd0d32d22a71b18a1b9ec071d0776ffe5c2a/yarl-1.25.1-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:683e362b8ba453080f7489c66f4ea794e751c35b72e7eab3575ef784c2fbc7fb", size = 116180, upload-time = "2026-09-15T19:30:08.836Z" }, + { url = "https://files.pythonhosted.org/packages/20/9c/fbe9432478d87e00eef80242e15179639df162cb3d5d8d978fc56dcb6c51/yarl-1.25.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:df23df54b5114a17c2d0ef192433e2e5a9f0c5178c32375e90b7cfc965f349d0", size = 116578, upload-time = "2026-09-15T19:30:10.782Z" }, + { url = "https://files.pythonhosted.org/packages/b1/8e/b3dfd03732236b86b0bcf06a72a37de412ff6f82e719a947c3c651d4dece/yarl-1.25.1-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:f53dcd26694f148f738edc052b5a69234833e739f10f4c3287bdfd8ec0f7b326", size = 108886, upload-time = "2026-09-15T19:30:12.951Z" }, + { url = "https://files.pythonhosted.org/packages/83/e1/94dacb650d4963d5f844bc3df7ba70288cb7b68ed5a4d070da71acb19b14/yarl-1.25.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:b8075fe90bc08e40b8b8a1874fab42ee4c7b56af05c5886e9cc841397f916908", size = 124098, upload-time = "2026-09-15T19:30:14.963Z" }, + { url = "https://files.pythonhosted.org/packages/d6/3f/c93f76a218258c7bfc60dd27fd56e9102bdbc625517f4a6ee673295fe4e4/yarl-1.25.1-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:a8c2b841478068440d8b733005d13a5ef535b9928cbc05f17182d410f32ba449", size = 115768, upload-time = "2026-09-15T19:30:16.736Z" }, + { url = "https://files.pythonhosted.org/packages/a8/79/4d93f13c3b05cda3c962805dec28cbc255c50239b3457808abc5633a00c2/yarl-1.25.1-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:ca32926d7d77bcc8838425c4c95e040a3ace1cb7dfdae599013458dcda2607ca", size = 122461, upload-time = "2026-09-15T19:30:18.901Z" }, + { url = "https://files.pythonhosted.org/packages/c5/8e/e2ba83b3a9bfc1d3b882ad35fa8abc04a7af4d9356f2e329a23d0c8d889d/yarl-1.25.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:192a866877a49993949ef1975864ad8728bea28ee810f6abe1a0729c2b500426", size = 118295, upload-time = "2026-09-15T19:30:21.07Z" }, + { url = "https://files.pythonhosted.org/packages/42/67/cb5ea1baa0c0ac60bda44ce59f601133154af2a2e67722d3517f8793855d/yarl-1.25.1-cp310-cp310-win_amd64.whl", hash = "sha256:3f4d48a6112712973e676bd792121fee470e432d749177162d9949d5c9460a1b", size = 102929, upload-time = "2026-09-15T19:30:23.122Z" }, + { url = "https://files.pythonhosted.org/packages/2f/85/9a1e98de10fc0e738d517efd2a9984c3e7db6cf35fa72b2b373988a9e9b7/yarl-1.25.1-cp310-cp310-win_arm64.whl", hash = "sha256:48796ea00a303961507dc6c8437c4b325a6fc3f95f7c36c71b91ea9a8150963c", size = 98854, upload-time = "2026-09-15T19:30:25.102Z" }, + { url = "https://files.pythonhosted.org/packages/83/b3/2cea721d495ca57f8f414aa4867ee263f486b274e07463158cf52f02ba7f/yarl-1.25.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:9d693bf4bf534e9ba3ae2780cfd577f5135629f7b5ac653490859d0b77864865", size = 143794, upload-time = "2026-09-15T19:30:26.946Z" }, + { url = "https://files.pythonhosted.org/packages/55/e6/cd145cff8e5cf60b8b3c41fbecfa2a45028a8dec3fbc52bec03595ff3d3b/yarl-1.25.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ab2054c5531af2a9ba7b69b8ec91e4f884420e83a8c5e579b013084cb57e5e5d", size = 103993, upload-time = "2026-09-15T19:30:28.661Z" }, + { url = "https://files.pythonhosted.org/packages/ce/7c/fbb40fe2d53747c40aa36a9e2bd2178a202f942bda0b670f3306d4aefbce/yarl-1.25.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:564fdc7085d2245ab84f88882fdb1d6ac0723124bff6ded35bfb1c00f812630d", size = 104010, upload-time = "2026-09-15T19:30:31.069Z" }, + { url = "https://files.pythonhosted.org/packages/f0/0b/5a516f70641092283f57cf3670bdb75e7327bcc0dcb5038697e4dfbfd569/yarl-1.25.1-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:acae6b45d1ace09b6ba3876da43b88366ef368f73b988c7f57e14231753d4420", size = 116444, upload-time = "2026-09-15T19:30:32.894Z" }, + { url = "https://files.pythonhosted.org/packages/b6/8a/d1a627f827b0a404ae0f5647cab0534959081cde13b0756a783469fb3b5e/yarl-1.25.1-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:1fb2a01ba8cd9c5d2c5dc1ec35e0fc951d04b4f037541d4ac090c993ce58b3d7", size = 107565, upload-time = "2026-09-15T19:30:35.188Z" }, + { url = "https://files.pythonhosted.org/packages/aa/cf/c8e0aaec886840a6c4480fe44eaec7cd4319f79a563b79321473be79c56f/yarl-1.25.1-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:e92b6bcc741b86d67606c40d3cb9c7cc8e6c737f81e31f4a94efc204456c92e3", size = 125006, upload-time = "2026-09-15T19:30:37.1Z" }, + { url = "https://files.pythonhosted.org/packages/50/26/0cce366d54a93cdc8342965dc7663385e4db161625cc1e8b18e786753d24/yarl-1.25.1-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:72c34ac7ad4314c19362d5ce27626dcc8429bd30bbf8c179f4234078851f9492", size = 128717, upload-time = "2026-09-15T19:30:38.904Z" }, + { url = "https://files.pythonhosted.org/packages/95/0c/a71501bbc1a674ff72c4d6c2b75f4d9a5af819f5244c3a7558080a8802c5/yarl-1.25.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d5add7b4ca7afeea91d52e4d4e4db3b1fe9885b71f07054560d8c4296b7441a2", size = 117728, upload-time = "2026-09-15T19:30:40.809Z" }, + { url = "https://files.pythonhosted.org/packages/e7/6f/c3267ca01defeed9ed9c4ff9b17bd54915432c405945233265b707475d1c/yarl-1.25.1-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:def538065f9e4d4cf1ae164bd59aba00dfa84f03923e0de4c3788f252d6bcd17", size = 116224, upload-time = "2026-09-15T19:30:42.818Z" }, + { url = "https://files.pythonhosted.org/packages/8f/69/fad57ee52d648431718ee0f1f68966a99c1352c3924688ffbdcc9d3fe51a/yarl-1.25.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:0a191bfdb30a79b98e5d175d75285f9fcb78bf0e46ba5efda042e1c72071a0de", size = 116299, upload-time = "2026-09-15T19:30:44.966Z" }, + { url = "https://files.pythonhosted.org/packages/2a/d4/6a8c1e29f33338687ca278cba0a8fbf6525a322c2c02a9a500ccbe041152/yarl-1.25.1-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:71f42c5b9a948c113bbdebfa544598321431d064ff959d32e99b1feb61d68345", size = 108625, upload-time = "2026-09-15T19:30:46.874Z" }, + { url = "https://files.pythonhosted.org/packages/e8/d2/3a35ae791c9cb6522c106923ff25c3230d999091e5e65511bca23bbd9914/yarl-1.25.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:72849d892954be4d09e569b8b831ac39ce58417fedc767d4308a0fe542018a40", size = 124515, upload-time = "2026-09-15T19:30:49.082Z" }, + { url = "https://files.pythonhosted.org/packages/be/fd/2b022109a6b4af0f7dc371cf7500af380b0d4f034010243e1b0ce218dc93/yarl-1.25.1-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:efb01a106f971cb3752856bca2318bbdf7f01bd8823779c461586cbe5ffd5258", size = 115711, upload-time = "2026-09-15T19:30:51.208Z" }, + { url = "https://files.pythonhosted.org/packages/18/59/f7586271136c3ddb0126bbfe661844699369b76b555fe38c4efe86870b2e/yarl-1.25.1-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:a1daf47cd95a7c3a63456336bc5aaa8c86dd3a47d07ed3d0e76132ae4666a5a1", size = 122751, upload-time = "2026-09-15T19:30:53.535Z" }, + { url = "https://files.pythonhosted.org/packages/a0/0b/07f7a2d881f7e16c385b47fc1753382600847cad305dcc7fa0c25828acf8/yarl-1.25.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:9489e6abf47ba37f332075a91444c7cfedb03e6ce99fbb2f116bfe1ce810da3b", size = 117983, upload-time = "2026-09-15T19:30:55.277Z" }, + { url = "https://files.pythonhosted.org/packages/aa/9d/8cdceec66a9b940700cb45931741403f045b162afd79bcb93c41cadd0972/yarl-1.25.1-cp311-cp311-win_amd64.whl", hash = "sha256:d7306dee25b8a0e737363f347362b875094b4dc4e367311470656ae420fdbf8e", size = 102894, upload-time = "2026-09-15T19:30:57.606Z" }, + { url = "https://files.pythonhosted.org/packages/17/f1/7ec357db1d3ad2863542d71e8fe64a126bbec17b134cd7d30951196809a5/yarl-1.25.1-cp311-cp311-win_arm64.whl", hash = "sha256:abb1384477f5901d436b5d2e5465954de46ea6098f59163d243660b5c4461d35", size = 98609, upload-time = "2026-09-15T19:30:59.705Z" }, + { url = "https://files.pythonhosted.org/packages/75/b3/cd32ac66ae622b854c2df0ac52106dda220d361b65a64fde7d5b3684aa3f/yarl-1.25.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:94d7aa6debf92a1dd14cb5280b083a764169a13cfb23a452111160274ed989f4", size = 144798, upload-time = "2026-09-15T19:31:01.821Z" }, + { url = "https://files.pythonhosted.org/packages/61/fb/a2c52a8007c2051ba74662afb112ecf3d00346af4c25e33df9d80fd14fb8/yarl-1.25.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:83d4a37e4b95da4d8bda930d6d35b75b4cdadbacbb4980cae290ea3100b5d51d", size = 104583, upload-time = "2026-09-15T19:31:04.05Z" }, + { url = "https://files.pythonhosted.org/packages/be/dd/ee38aec8e09fdf957e50d4085453fbe202f56c6c3b4cf07b81cdb4f09ee9/yarl-1.25.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:e029648f9c951db30e98a7d7ec90835db88ec4b32820efe2a9bdc2287e032eb6", size = 104325, upload-time = "2026-09-15T19:31:06.338Z" }, + { url = "https://files.pythonhosted.org/packages/1e/b3/058dbfb1857b484c9cf9cc135659f50b85ce66e03c99e44dc2f7b6161f55/yarl-1.25.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4d781294bb815ecb5ea57ff6bbf8038e0a31a95fdf3e1788f66e0dc100d64b58", size = 115358, upload-time = "2026-09-15T19:31:08.593Z" }, + { url = "https://files.pythonhosted.org/packages/db/39/29693446cf0cf6b15a0e2f75a5d40f93c56819b05b0622196f45e95b5cc0/yarl-1.25.1-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:e12c538e00e7c1b286a07061046b90e8124e6a9793efae2c70db6a4aad07faad", size = 107658, upload-time = "2026-09-15T19:31:10.802Z" }, + { url = "https://files.pythonhosted.org/packages/86/b3/3c4dd7e1af43b931fba95e0a722737f2ea94a6d199c802585282831d7abd/yarl-1.25.1-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:7e4de3ac4adbad3d0bc7c6f4360a7dbff5de2f15e3b723be3198074e17fd9c40", size = 122660, upload-time = "2026-09-15T19:31:12.84Z" }, + { url = "https://files.pythonhosted.org/packages/bd/b5/1b60dbc3cfc9c5712b15148c206748f2bc93953ffdbe25ea75b63dfc89c9/yarl-1.25.1-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:419f392a1da624877975709e3864dfe833af6cc7671b39318086d456e288380c", size = 126506, upload-time = "2026-09-15T19:31:15.088Z" }, + { url = "https://files.pythonhosted.org/packages/bc/7b/ca212cbe170ac8b96e45317ecbcf9c3c3ecf0cdec98d5b088a9c4088929b/yarl-1.25.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c6f117789d22dce188e5754e8bc65b7e6ebf8cb73963b9fa761f672a5883769d", size = 117050, upload-time = "2026-09-15T19:31:17.241Z" }, + { url = "https://files.pythonhosted.org/packages/cb/c3/72b4938cdbe619ad71ac156182faef4908846b84dc3ca4dbb4c4e6f84014/yarl-1.25.1-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:80e47012e730da131c9f059c80936783f9659aae22dc31c03c0595590d11ed54", size = 114174, upload-time = "2026-09-15T19:31:19.294Z" }, + { url = "https://files.pythonhosted.org/packages/e8/43/268717870f9ba0cc9701a95181587f6dc8c5f387aab4aeecc83158f38a79/yarl-1.25.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e80f557716fd765439577131e526b8942ffc2c07bdbc5e39fa62f660ba1e963f", size = 114944, upload-time = "2026-09-15T19:31:21.414Z" }, + { url = "https://files.pythonhosted.org/packages/da/84/baa5bf504d51fe062c4bcaf62936da97fffb43285978d0b39984824231fd/yarl-1.25.1-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:f61964f235a43738bfac50da46fc4254943a7eea3051aeb0b6fc7c992c29fadc", size = 108263, upload-time = "2026-09-15T19:31:23.388Z" }, + { url = "https://files.pythonhosted.org/packages/a4/28/779a2ed9e0152a601a27039bed9aead3f0b79797a67e2c44bfa444622dd8/yarl-1.25.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:e546fe1d4a93ebc2910f0d768baff19faa09843ab3f2036a67ed6e69fae4419d", size = 122184, upload-time = "2026-09-15T19:31:25.343Z" }, + { url = "https://files.pythonhosted.org/packages/f8/1f/118e9e5b8f07694d63fd3222e801d7782270003f1a222aa798df3f8d5933/yarl-1.25.1-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:cce0727fd5ac04d372fa9bbfde9febc2bcf209aadfcf0468e45dec72719895d1", size = 114001, upload-time = "2026-09-15T19:31:27.465Z" }, + { url = "https://files.pythonhosted.org/packages/0f/ae/a4cf1cf372313734b17996d4007f9f73596e7a178b9485802e5494ecf484/yarl-1.25.1-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:af4ea5b37403ef4e30f3927eaed540db942bde01d8d3ff083527c0704d1c9c68", size = 120565, upload-time = "2026-09-15T19:31:29.47Z" }, + { url = "https://files.pythonhosted.org/packages/05/79/ad94f93ca731bc9e44d321833ab96b82a4f9f5f63cf773f81a4aeea5ecc1/yarl-1.25.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:68782fdb4027b8d1eee25ec35e9a6db05e863b899eb0310b3a33b6c3fef55707", size = 117060, upload-time = "2026-09-15T19:31:31.367Z" }, + { url = "https://files.pythonhosted.org/packages/bb/cc/51a7b4abf4ac593b8e7eb3794b28e5a35ae26eed8bc04787628d215af82f/yarl-1.25.1-cp312-cp312-win_amd64.whl", hash = "sha256:7d575b54cb3863ef9bc290ea4b009999d55dc237326131e4853cf33e888fee03", size = 102593, upload-time = "2026-09-15T19:31:33.329Z" }, + { url = "https://files.pythonhosted.org/packages/9d/21/0941a6b93a58b59a1ec75e5333bf06929b671309c43c0cd201c172d9c39f/yarl-1.25.1-cp312-cp312-win_arm64.whl", hash = "sha256:bc3ac7bf569f6b64dad04dd7808c7872dae8a97df657856eac05e9b7e3614a85", size = 97697, upload-time = "2026-09-15T19:31:35.855Z" }, + { url = "https://files.pythonhosted.org/packages/7b/ed/2f3129bbcc9a5c8ba12cc2b29d8060a3bab9c8043c456cfd4b5ca3188890/yarl-1.25.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:25868beca8b6765f8f7d0e11fe6dd7c66dd4b0793b9500286d20cc92352126a5", size = 143623, upload-time = "2026-09-15T19:31:37.966Z" }, + { url = "https://files.pythonhosted.org/packages/17/e1/f1bc3390fdca352826676b531d0712736f156919090206700421d46b2c37/yarl-1.25.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:10b2fd95332f0d716d5eee3c9fb2ce8eada19082de7fee83d32e37992fd75c26", size = 104011, upload-time = "2026-09-15T19:31:40.25Z" }, + { url = "https://files.pythonhosted.org/packages/a8/aa/50acc5c3e5da04172ae3c281c75405af4d2ca911e16120ab0563f4dffb66/yarl-1.25.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:0f12afda4eea8c8994a76d4df1875c765194f5fbe8a9d197929ea303caee29ec", size = 103677, upload-time = "2026-09-15T19:31:42.46Z" }, + { url = "https://files.pythonhosted.org/packages/30/d2/7d1e0ab9f8390e1fbcede5a6dbf70d23c96ad09b8c5567f3a514d1ddb0e2/yarl-1.25.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:14b79a30a93a3ce2e8832603fd0ab780ada281b0ba5110b519a634f2d7d7d1fc", size = 115392, upload-time = "2026-09-15T19:31:44.371Z" }, + { url = "https://files.pythonhosted.org/packages/71/e1/5ba1e3a2a22139213655e760919038e8ed7e2d4a99826d0bbddb3beb96e5/yarl-1.25.1-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:4bd6340d20ae2c7ca719b87b426e808e90743b676d05d4c26c4fb5ca71f41184", size = 107493, upload-time = "2026-09-15T19:31:46.273Z" }, + { url = "https://files.pythonhosted.org/packages/f5/53/780653d5e0f73831f467cf13548912e5eec97f21dc49fc8daf21da027df4/yarl-1.25.1-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:126a2533570c554719ca40a1288fdee1700b6bc82e7131aa69fa85252d92e651", size = 122537, upload-time = "2026-09-15T19:31:48.654Z" }, + { url = "https://files.pythonhosted.org/packages/03/92/d54fa70236c6036271c9c9c09fd978df5cbe3ef49ef6c46e9b833476d215/yarl-1.25.1-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:a3faadac7d812ddac258feb57b9846b60c1b437c4f4b9ad42595c6f6fe4390df", size = 126170, upload-time = "2026-09-15T19:31:50.872Z" }, + { url = "https://files.pythonhosted.org/packages/0e/b7/a82a49bf88340b837ef6972b508a1604ae377b9e6904b46b10cf5f1cf925/yarl-1.25.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:be80550d9bfe83d9b62398a37081a90434e6df2d978ec345c3d2820de6beddab", size = 117012, upload-time = "2026-09-15T19:31:53.189Z" }, + { url = "https://files.pythonhosted.org/packages/ef/78/5d684b411e3f3602464ee9b538db48205038f8605872985f61efb809ced0/yarl-1.25.1-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:e07595c7d6f4db270ceede356a1bd1c07a34f1c26f958d1ed0cd7b48e0d2bba3", size = 114950, upload-time = "2026-09-15T19:31:55.694Z" }, + { url = "https://files.pythonhosted.org/packages/2f/11/51d82b852c64f7fad0fc7a7ff3031517204887e874c722bbca839c0b23ac/yarl-1.25.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:eb96ed1ae6c7d072d60840c0434aef07a2df611812810807fbc54263a6053e9a", size = 115428, upload-time = "2026-09-15T19:31:57.966Z" }, + { url = "https://files.pythonhosted.org/packages/e4/49/9d1978049bf646b9ea918313926453c6901b71c92f097467777d47d36a88/yarl-1.25.1-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:3feb99222553a8cbedfa52c2f59dd84c3f50d5b582c728d522caf8d72769a54b", size = 108428, upload-time = "2026-09-15T19:32:00.048Z" }, + { url = "https://files.pythonhosted.org/packages/43/35/7b8f1ebb45d7ec3dda7d1909bf44f458de41ef91e2937f107733582a5166/yarl-1.25.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:a2ed0ba415ccdf08f14bf544cb78346d0f76086707ffee24921a2c84dbf1305a", size = 121961, upload-time = "2026-09-15T19:32:02.436Z" }, + { url = "https://files.pythonhosted.org/packages/63/d6/d8b689ab7ca26edeb85f6ff28812aac7a25376eefc1780e303a7bfbaceff/yarl-1.25.1-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:2b49375d22299b0a834c2bca72f39aaecc270d96fb24c30424899676f487b22a", size = 114961, upload-time = "2026-09-15T19:32:04.456Z" }, + { url = "https://files.pythonhosted.org/packages/cf/d5/1a1798ea4dc6b7ee3260010a27907ebc697c95dae99817d817ed446d24aa/yarl-1.25.1-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:ef74070ac553c59eb4f04258722066d6c6135b7baa03b2e9f2da65c096e96d98", size = 120036, upload-time = "2026-09-15T19:32:06.5Z" }, + { url = "https://files.pythonhosted.org/packages/91/8d/b1b35ed7903da6669b1d367cb2c09436acd4ff508029b4f39a0c0c2058fc/yarl-1.25.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:0a66db89ea473abeac4b70523cafd94db3772380e565f9d28af7a179b7af71fa", size = 117276, upload-time = "2026-09-15T19:32:09.401Z" }, + { url = "https://files.pythonhosted.org/packages/3a/8f/4db01cef62caff0d7a4593ed694fb8a41a27a11158cab80d290221f13e57/yarl-1.25.1-cp313-cp313-win_amd64.whl", hash = "sha256:1f51020b2eb8a003c84925638ec63c21a750a4bddd3a22ec8eac6a742dadf1b9", size = 101945, upload-time = "2026-09-15T19:32:11.545Z" }, + { url = "https://files.pythonhosted.org/packages/c0/5e/3ce00497c5c0babb74d4130c10c3828ccd215b4819d12020c42429f991ac/yarl-1.25.1-cp313-cp313-win_arm64.whl", hash = "sha256:b10dd0557ba422715b5206b3743192135a6022acca8baec51aa127d0a75db8fe", size = 97270, upload-time = "2026-09-15T19:32:14.127Z" }, + { url = "https://files.pythonhosted.org/packages/80/cf/54023edfab7aa773b860503db0c56e962ccab0922803ee97988c176ea090/yarl-1.25.1-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:a9ca696eb02e5c02a8afd872ada510eba9b7fe6e68b9572c2e9a9b1941e31e2e", size = 143975, upload-time = "2026-09-15T19:32:16.416Z" }, + { url = "https://files.pythonhosted.org/packages/d7/a8/e6c1be0e6761d0f2d10bbf33a3e1e02b99dc83874d92945d7b461a72481e/yarl-1.25.1-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:a5877f2255aab518ebe528289037699201d5dc5f045f2396cb30aa02db22f57f", size = 104018, upload-time = "2026-09-15T19:32:18.364Z" }, + { url = "https://files.pythonhosted.org/packages/6e/bb/dda344765ffd3430afe1a1c66c866a57fae67786537d4f14607df6505ac1/yarl-1.25.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:7a5c3115595995779ee21f2567035793911c3802a43c74f3fbb0314929ec67ac", size = 104156, upload-time = "2026-09-15T19:32:20.459Z" }, + { url = "https://files.pythonhosted.org/packages/e5/5f/ed1538bcd06009fe990d6d283dd7667f639e62a81e35c6d8c6ef6c08fb3c/yarl-1.25.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:77e5099b99b37f3cf79c246998ca9f7313a78054cd1809ec46bc1afad47e1c4c", size = 116025, upload-time = "2026-09-15T19:32:22.766Z" }, + { url = "https://files.pythonhosted.org/packages/a2/af/2185daf56b99830d3356ecfada46faaa49945de6626e842b7728088d4980/yarl-1.25.1-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:6efaf45df6a849cef613a03a94c845647456662f85438c886bb67a9c027c8c2c", size = 106985, upload-time = "2026-09-15T19:32:24.749Z" }, + { url = "https://files.pythonhosted.org/packages/c1/65/bc1ae564fb4b04a30b6a8f250e787772581c57e4c3d5cf07ac3359de3103/yarl-1.25.1-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:d5f90e44653c4e0f78501ed9bb7d3fce835a8d62b7c6ed0cb16557534087e743", size = 123030, upload-time = "2026-09-15T19:32:27.084Z" }, + { url = "https://files.pythonhosted.org/packages/6a/3e/e2afcde10d74e53b3fa889960991efb3019beda2b1682a01de720a302056/yarl-1.25.1-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:632da579b2d879f6bad20f2cfa35ded1efe2f4f77f8abb26a6234a5b236acd2f", size = 126765, upload-time = "2026-09-15T19:32:29.332Z" }, + { url = "https://files.pythonhosted.org/packages/a2/be/415b00c0fe5a0615b062a456b26623d7ec91c2bee20faea1a14045aa0469/yarl-1.25.1-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:30eec96e8a91bd588ce897c9543f6d5d8d34b28fbcba28a4dedf20ebeae9fe57", size = 117199, upload-time = "2026-09-15T19:32:31.49Z" }, + { url = "https://files.pythonhosted.org/packages/97/27/3d8c63ddd3e8bcfd033748ab93876678ce59bacd66e4cb1ed851c9c5b37e/yarl-1.25.1-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:12b6bc4906e11f5e1a1cdcb12296e7afbd366c783cc8073403cd2fb74334e453", size = 115187, upload-time = "2026-09-15T19:32:34.137Z" }, + { url = "https://files.pythonhosted.org/packages/39/b7/7a81d0be1a502a26a0d4326c6f2ecb736c824f570ea1c6529f2b0b227b50/yarl-1.25.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:9d6ed3d17bccce4c05343e1ca8da13bc5c02c812a4e7282ddd05e8769322d3fc", size = 116085, upload-time = "2026-09-15T19:32:36.438Z" }, + { url = "https://files.pythonhosted.org/packages/f0/69/39fff459916aa0fab42215dc47b759586fd80f94aa56dfc4a7c15ba6e0dc/yarl-1.25.1-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:f38a70074041d3b7e138e452799f5174198bae5bd5ab2000917badf403908c5f", size = 107996, upload-time = "2026-09-15T19:32:38.959Z" }, + { url = "https://files.pythonhosted.org/packages/c0/39/80b9a55a3335590451d9ecf3eb593a8c635351f4c905ef056d7e8a8fd9e7/yarl-1.25.1-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:4ca89e4e21854ed27ec753297dde84b16c9f8e53b14a4866fb44457d643c19f8", size = 122549, upload-time = "2026-09-15T19:32:41.151Z" }, + { url = "https://files.pythonhosted.org/packages/42/7d/a179c6757818bb59372a4adafd09f7f26a3b4a0f04c3ae404b544c0b0c82/yarl-1.25.1-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:1ab7618921a93767387a4b83776f751588f5b5ae9bb5bc96620e2e2e00bca868", size = 115107, upload-time = "2026-09-15T19:32:43.072Z" }, + { url = "https://files.pythonhosted.org/packages/32/2b/a773ac867e4ab53a98ed98e5cefe3bae31e6f550252ca9d1de266f1a40c5/yarl-1.25.1-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:0ae12ff2b805fa02c4dab838005caef735e39986322698c48588d3beacb65c62", size = 120666, upload-time = "2026-09-15T19:32:45.061Z" }, + { url = "https://files.pythonhosted.org/packages/bc/41/52be6505e85b0f76b4f85b01b5de7e06a0512201abc2c95e14e099549174/yarl-1.25.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:90c30ed53546da833c700115c0064c22120d1b1560f474699fd31f22dd668233", size = 117505, upload-time = "2026-09-15T19:32:47.177Z" }, + { url = "https://files.pythonhosted.org/packages/f5/01/349c0386caedbbe488d519f252df54efac8a1459282d466c474bdd84a620/yarl-1.25.1-cp314-cp314-win_amd64.whl", hash = "sha256:acfa7e22aa6c6e7a5996a41d275bfa01efa7ea56ab890590280e9063e2cf5c1b", size = 103446, upload-time = "2026-09-15T19:32:49.615Z" }, + { url = "https://files.pythonhosted.org/packages/5c/f0/8ec63180f77912f0dc4e5a42760cb8c08d20da1d5ace3578a01b84d1f3d8/yarl-1.25.1-cp314-cp314-win_arm64.whl", hash = "sha256:8e7d98cdbb6d71e726f7d525952867096053d1f290dd4e3c50d7d313a136f414", size = 99159, upload-time = "2026-09-15T19:32:51.686Z" }, + { url = "https://files.pythonhosted.org/packages/47/7d/92d2220d6886b70ab1ed8579533ac2af2dfac716d5d929001daff7986df9/yarl-1.25.1-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:d21f0fa80a02d05299207eeaafef345d812ace96d5306e4ef265e1d419a615fa", size = 150071, upload-time = "2026-09-15T19:32:53.911Z" }, + { url = "https://files.pythonhosted.org/packages/64/fc/b245e448124bcda9340df38e3553fa222b50260fca027a84095e9bd8642d/yarl-1.25.1-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:17c9877a89fb6e2bca6f9087eb24cd7fb434653946ef5075e470d23d49b52287", size = 106780, upload-time = "2026-09-15T19:32:56.443Z" }, + { url = "https://files.pythonhosted.org/packages/51/e2/9a6ce2e334ebf218a30335ae76fb1696459430d42f733b8cb0d7d65b84d3/yarl-1.25.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:29273edf1530e397bd07cb784db1fbe0d2590b77569f2e24679a9c0a2d763b94", size = 107361, upload-time = "2026-09-15T19:32:58.827Z" }, + { url = "https://files.pythonhosted.org/packages/ed/70/66e8c76b569b450d16e190f15071c916c3df70b0e33927e415ac497cf0c2/yarl-1.25.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b7abffdf37af1cec6a2ad69b827aa84320db5894791bc8ed932dc93fb274b7e9", size = 114396, upload-time = "2026-09-15T19:33:02.24Z" }, + { url = "https://files.pythonhosted.org/packages/73/23/0d82838a05c57fdc05bc8b66e8c92dcc0df15e27463a5f163142d521c682/yarl-1.25.1-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:2239a02249d9326655419e0168a28ca9008938eaab31dc29fc875c217927a6c0", size = 104882, upload-time = "2026-09-15T19:33:04.494Z" }, + { url = "https://files.pythonhosted.org/packages/86/d4/ea08615c4edaa6049a13a2f1128944d068d1893abda7d708d4d7ea01599a/yarl-1.25.1-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:664ec6a520b74a1df2810666eb67695fcb77fa663e6ea0a25aaf2e529cb24dfa", size = 119485, upload-time = "2026-09-15T19:33:06.583Z" }, + { url = "https://files.pythonhosted.org/packages/1a/82/0898bdce9b1ae403b308b9c733d0d24af4a3464270c2c081f457b16c3e0d/yarl-1.25.1-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:4f1c91f5a5980a937ff8e238e98e6897e1ad74a4b1e2c0d68c73b5ffbb3f5c0b", size = 122490, upload-time = "2026-09-15T19:33:08.653Z" }, + { url = "https://files.pythonhosted.org/packages/d1/38/97d79b81c342b78246cfedb74809e68841f3198d21653e10d3232bd9c622/yarl-1.25.1-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7c88edaec8c349ad4c5ad4c486a3defcc4b80ceb2f074436ffa0a87caf5e76a6", size = 115336, upload-time = "2026-09-15T19:33:11.056Z" }, + { url = "https://files.pythonhosted.org/packages/8e/9d/2577896554cd310dc470adb6da0b7dd0b435cb63e2565204a7ac240e504c/yarl-1.25.1-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:35dcbea443fafb3eece757ad4e514560ddeb6c34cfae1582c620d7b293d7feee", size = 111825, upload-time = "2026-09-15T19:33:13.204Z" }, + { url = "https://files.pythonhosted.org/packages/29/6b/7ac49d8ba84a5c4bd73415a4c949d22c749cb3762579b3d50e48019a78aa/yarl-1.25.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:882569ff613758cac762a457a5d72d6e211b28d4bcfea89d1d71ea942b02eac0", size = 114655, upload-time = "2026-09-15T19:33:15.553Z" }, + { url = "https://files.pythonhosted.org/packages/e5/18/e5942a16723f5b72f9b1297fd5a85a54f6300cd15c0dcb5005b90cd89156/yarl-1.25.1-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:d0f1489233a254bb3643d2f05de7d59019254d81daeca6b9162fe9edef57e0c7", size = 106395, upload-time = "2026-09-15T19:33:17.599Z" }, + { url = "https://files.pythonhosted.org/packages/7b/2d/549fa46240781513ebc47ae7eb418df428a163a2a3d644cc9cbb3ecb7846/yarl-1.25.1-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:f41753a76f4f63927d03a0d8ba8f5ce0f2083bec29a8cfaccc55371b1564b96b", size = 119277, upload-time = "2026-09-15T19:33:19.973Z" }, + { url = "https://files.pythonhosted.org/packages/76/16/4763f78dcdc0b3b9fb3842b04afe72b9320857c6a69300c62a0eab03d119/yarl-1.25.1-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:8fb0eb4955adf0579001581f2f71a126e8781ba61bcd120f127b0401163c6c2d", size = 112504, upload-time = "2026-09-15T19:33:22.464Z" }, + { url = "https://files.pythonhosted.org/packages/ae/b4/974e3edfe0d188393ce1cb9de400111c63fe61f4eb3b772a500d84c970d1/yarl-1.25.1-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:a1e32763e641a1566507d90a8d3b19bfc3cc04a9d4e5ae3e32189874ed4b58a3", size = 116243, upload-time = "2026-09-15T19:33:24.788Z" }, + { url = "https://files.pythonhosted.org/packages/b0/aa/157b940428da80c104ca09666a740e51c94963df65d5b112e06b52e4d7a8/yarl-1.25.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:65b5b2066651b7432d389e9799d979c703bcc6ef44266bb8153ef54e91e4aab3", size = 115822, upload-time = "2026-09-15T19:33:26.886Z" }, + { url = "https://files.pythonhosted.org/packages/7e/af/19fbdce41412e1b96825544cc52cd7029d3724655d0988237972f078bd29/yarl-1.25.1-cp314-cp314t-win_amd64.whl", hash = "sha256:734f6e5400352ac4254456003d462866c684703570929cff7a7bde015d0cb371", size = 107386, upload-time = "2026-09-15T19:33:29.009Z" }, + { url = "https://files.pythonhosted.org/packages/2a/99/f6431c8968e89be608d74b28ae2d024521b2953f27dd44e0dece5e04f67a/yarl-1.25.1-cp314-cp314t-win_arm64.whl", hash = "sha256:287e99ff5aa4dc1c7630bfc683ded6f106d756c99dec432a2d7f197a784f51c6", size = 102094, upload-time = "2026-09-15T19:33:31.151Z" }, + { url = "https://files.pythonhosted.org/packages/54/22/318c7980066769c6bcd9221ed2248294f5698811da099013098c670565ed/yarl-1.25.1-py3-none-any.whl", hash = "sha256:681c758b0490f9e96b78e5fa8e8dc6e648e9185bb6eaebe73183c33ea0c445f3", size = 63617, upload-time = "2026-09-15T19:34:59.616Z" }, ] [[package]] From 827cc15bfc3bd7f2de6946668cc22ef70bcf6139 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 21 Oct 2026 01:14:53 +0000 Subject: [PATCH 57/66] bump: version 1.104.5 --- pyproject.toml | 4 ++-- uv.lock | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/pyproject.toml b/pyproject.toml index 2816de2316c..970d67d443e 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "litellm" -version = "1.104.4" +version = "1.104.5" description = "Library to easily interface with LLM API providers" readme = "README.md" requires-python = ">=3.10, <3.15" @@ -355,7 +355,7 @@ litellm-enterprise = { workspace = true } members = ["enterprise", "litellm-proxy-extras"] [tool.commitizen] -version = "1.104.4" +version = "1.104.5" version_files = [ "pyproject.toml:^version", ] diff --git a/uv.lock b/uv.lock index 232edd8cd3b..234047a1db1 100644 --- a/uv.lock +++ b/uv.lock @@ -4501,7 +4501,7 @@ wheels = [ [[package]] name = "litellm" -version = "1.104.4" +version = "1.104.5" source = { editable = "." } dependencies = [ { name = "aiohttp" }, From 23e0a798c059031c4b7638d8e131132a5c339f1c Mon Sep 17 00:00:00 2001 From: Mrinal Chanshetty Date: Tue, 20 Oct 2026 17:09:09 -0700 Subject: [PATCH 58/66] chore(deps): bump aiohttp to 3.14.5 and claude-agent-sdk to 0.2.165 to match main --- pyproject.toml | 2 +- uv.lock | 261 +++++++++++++++++++++++++------------------------ 2 files changed, 133 insertions(+), 130 deletions(-) diff --git a/pyproject.toml b/pyproject.toml index 2816de2316c..fc1ed7ffddc 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -286,7 +286,7 @@ ci = [ "langchain-openai==1.1.14", "langgraph>=1.2.4,<1.3.0", "langgraph-prebuilt>=1.1.0,<1.3.0", - "claude-agent-sdk==0.1.44", + "claude-agent-sdk==0.2.165", "google-cloud-speech==2.40.0", ] healthcheck = [ diff --git a/uv.lock b/uv.lock index af06b906e34..5ff15093bae 100644 --- a/uv.lock +++ b/uv.lock @@ -10,7 +10,7 @@ resolution-markers = [ ] [options] -exclude-newer = "2026-10-17T23:12:37.361448Z" +exclude-newer = "2026-10-18T00:08:44.741377Z" exclude-newer-span = "P3D" [manifest] @@ -85,7 +85,7 @@ wheels = [ [[package]] name = "aiohttp" -version = "3.14.4" +version = "3.14.5" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "aiohappyeyeballs" }, @@ -98,127 +98,127 @@ dependencies = [ { name = "typing-extensions", marker = "python_full_version < '3.13'" }, { name = "yarl" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/93/2f/6a91adaa2dc26877d6ed2f54c0370c8910f019db7d77c5c6a194611e93ea/aiohttp-3.14.4.tar.gz", hash = "sha256:831fc5bd39ec2517851e348f613ddb5447a47cf4b71cb09845af7ad7ed45d8f9", size = 8077839, upload-time = "2026-10-05T17:43:48.309Z" } +sdist = { url = "https://files.pythonhosted.org/packages/6c/4c/bdccd81e9ee225b69c60e7766c9a5b05364f118f4d383713b89a682d772d/aiohttp-3.14.5.tar.gz", hash = "sha256:5558a7f5a05af9ecf744af91e5baefc436f93c9333e656c27ec253f9a6bbe178", size = 8078052, upload-time = "2026-10-11T01:05:12.408Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/b3/08/290e4be6e3ed239751c446505c324406a4ae8a82a15009a12a3c550f18d9/aiohttp-3.14.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:dea3b3653c1d0d6babd8ce09cb9e5a7776864315d9cfb1c569f926389874a261", size = 834853, upload-time = "2026-10-05T17:37:45.079Z" }, - { url = "https://files.pythonhosted.org/packages/81/81/ed5e04508ba1fcf9a34e0449c78009956e8256f62ebef708e2948594cf94/aiohttp-3.14.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:3099a389e5b5900fc79c6f613015ff3f8fa06a519744e6001cc68a31ba418cac", size = 560957, upload-time = "2026-10-05T17:37:47.497Z" }, - { url = "https://files.pythonhosted.org/packages/90/28/1a91411c53704db0481cc64b0f0c9465aa9d738856abdcaa3a5bbbe18180/aiohttp-3.14.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:70247156fc76e92919f9aacb820556cb30289a54784299a31714d030bb604d84", size = 553475, upload-time = "2026-10-05T17:37:49.099Z" }, - { url = "https://files.pythonhosted.org/packages/cf/2e/1038f3fa8832f9f4bed0f9f751f70dbc52bc4a09c66788f97bbfb0ce3d88/aiohttp-3.14.4-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:fdf2d2a6ad402797422949f4a200a60d43e3a021695c8a7804aa1d5bbef22652", size = 1845211, upload-time = "2026-10-05T17:37:50.728Z" }, - { url = "https://files.pythonhosted.org/packages/ea/54/e2253f17604c5c1c69a05e3c12400b51cd6a5fb32d7175592114d8c7a470/aiohttp-3.14.4-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:ba835fad8d4b5eaea0d34f9461cf499737a720a5f8bc6768d2f6d98a1d3ba8b5", size = 1814629, upload-time = "2026-10-05T17:37:52.481Z" }, - { url = "https://files.pythonhosted.org/packages/f1/ef/7bd1e45db925376720555d7268c2d642b113105263d37a522e41e1ba3a6c/aiohttp-3.14.4-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:0d4415ca5c9c8b24bc2f5733f870d4eab4929e680203559ba60131dd1a27852a", size = 1898528, upload-time = "2026-10-05T17:37:54.078Z" }, - { url = "https://files.pythonhosted.org/packages/5d/40/26d09668e7e0cadc16027566765aa4ce26e8a41276bad6764848c8b04d11/aiohttp-3.14.4-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:f6757e02c2c2b0d7985f57be87cf4a7c5b35708f849e1feaea3f77656ddb9dff", size = 2024385, upload-time = "2026-10-05T17:37:55.626Z" }, - { url = "https://files.pythonhosted.org/packages/73/38/0f1c4aab1cc9518e1bf874e2481e59e541b3e32330b9542e52bb2712f86f/aiohttp-3.14.4-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2a950bd8418ef54eccf5f9f517f08e37c1adab4bc50a470a0422ee1cc1032e29", size = 1859130, upload-time = "2026-10-05T17:37:57.342Z" }, - { url = "https://files.pythonhosted.org/packages/5f/98/09d5998ba4b5fe9f0cb97d794fab9d1b3d8245c5ec6a5fb84e41a8cec142/aiohttp-3.14.4-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:34cf6f2fe4fc1d7183e8cc0d8c48bbdda828a740bc372d8278126149714d343c", size = 1714768, upload-time = "2026-10-05T17:37:58.831Z" }, - { url = "https://files.pythonhosted.org/packages/c2/63/39d01a74d525d6443084d47ad4aa8c719f44a030149d03566f3761527465/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:bc0fbe4f79c3b156d754dd062718ffe404c3b31ca878d9d2b88ecdbc72ef8369", size = 1813228, upload-time = "2026-10-05T17:38:00.611Z" }, - { url = "https://files.pythonhosted.org/packages/39/6b/183d7b969bdb7892e86af74147b4afedbb4e03b8cad5006e41aa2034c288/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:d3d50a5a07a2b31a4369b86dd4a3acf3c2577c45091dbd5e884b198dec56480b", size = 1831844, upload-time = "2026-10-05T17:38:02.272Z" }, - { url = "https://files.pythonhosted.org/packages/2c/be/4c6df02b62083efd3f008974cf9016a4afd2023f5a9d2c3fd55499fcbac6/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:de15c46a63f46da881d219e44a04778c40114c756e5575b5ea38143b20eb3713", size = 1868738, upload-time = "2026-10-05T17:38:03.831Z" }, - { url = "https://files.pythonhosted.org/packages/86/21/406be8b0cf1105a35a6a6da16a95796be39b354e29bfca0d1626d822835f/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:caa4c0fc9b25e8c679baac68337e9c00deb6baf6601fe6f07e8511469cc1ceba", size = 1700006, upload-time = "2026-10-05T17:38:05.631Z" }, - { url = "https://files.pythonhosted.org/packages/4e/e6/beac98020ea0885ea1ee3b2ef59ec952405590fe2ccef2fa4ef7614c3c2b/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:3647f8c090632c70abb1e80826e4ee24faea3f895f0283b60e91a0b17aea5e34", size = 1889997, upload-time = "2026-10-05T17:38:07.578Z" }, - { url = "https://files.pythonhosted.org/packages/c4/89/d608dd9571988a529c7fead5bc79ad36b56fd52bad7941f40774acbc87e9/aiohttp-3.14.4-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:3f3e8030169843fb652a60a3d32c206e03f260198aa398985a48b41cd7e42f0a", size = 1844619, upload-time = "2026-10-05T17:38:10.003Z" }, - { url = "https://files.pythonhosted.org/packages/7e/7d/7f51e6338d2c74b75173ee66fcb50d778d5407c32f34e76ef1c4b25d0d75/aiohttp-3.14.4-cp310-cp310-win32.whl", hash = "sha256:a1205cbdddfca1428129bb6d23e0b292b09e681df951fa828145d83a63ffc0ca", size = 489598, upload-time = "2026-10-05T17:38:11.795Z" }, - { url = "https://files.pythonhosted.org/packages/33/2a/3434e450a4395fc07f3070d6ac24553f0b170b173e949216b1723395028c/aiohttp-3.14.4-cp310-cp310-win_amd64.whl", hash = "sha256:e90980e0454a043f81b435309a089ac5deab883779557eb58d004f33990f61e4", size = 512204, upload-time = "2026-10-05T17:38:13.309Z" }, - { url = "https://files.pythonhosted.org/packages/53/c0/1d89303cf1bea5418268c1cb82b872661bad027e5fd785c2d30d0a31ee6f/aiohttp-3.14.4-cp310-cp310-win_arm64.whl", hash = "sha256:e63eecf9a4b670a24055d5c0486128af16f83b02d9817abd685d3238940f8752", size = 492725, upload-time = "2026-10-05T17:38:14.825Z" }, - { url = "https://files.pythonhosted.org/packages/81/e3/998dc75634ecd2a24f33bab480b57313059d55bcadff8825a46b7c80a8af/aiohttp-3.14.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:eb0093ca0817019d539f0d27bdf98e823944e05bb7efd9d2337a45b92e4d1b06", size = 832892, upload-time = "2026-10-05T17:38:16.373Z" }, - { url = "https://files.pythonhosted.org/packages/58/c9/9bacc26397854440d169f70ae00ea51721f504611d3a64cf043643792c32/aiohttp-3.14.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f482dc9c8309801b4259dd218609d3dae0a7bcdedeac56d90500eabaa0c23465", size = 559893, upload-time = "2026-10-05T17:38:18.74Z" }, - { url = "https://files.pythonhosted.org/packages/fa/f3/90c5856014328a8b1e9a753de794edea282182b776ff65f0602ad4ffa520/aiohttp-3.14.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:aa800bb7c1d00e166493931f2ddacb982db913292503dc2f4884db1f2bc5f105", size = 552850, upload-time = "2026-10-05T17:38:20.385Z" }, - { url = "https://files.pythonhosted.org/packages/9b/88/e71c29ce6daa78fcee0feb1992f0fdc408f09f42c3311b1f1c68c36f16ea/aiohttp-3.14.4-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d90e4dae71b26597f6d1fd12af7d092ae67551edf0e524b73e0687214b79ee33", size = 1928941, upload-time = "2026-10-05T17:38:22.218Z" }, - { url = "https://files.pythonhosted.org/packages/3a/4f/f0f3bebfa521a2ce5fd4302c937701cbc50cd6d908beaa597388639b0b98/aiohttp-3.14.4-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:5b681054b8c3b86aa6a0384b6ad7f5cb78dccbabab1f4a3a6793f98ad1378959", size = 1882092, upload-time = "2026-10-05T17:38:24.016Z" }, - { url = "https://files.pythonhosted.org/packages/b5/0d/5df041fd25dceb4f4cafbbee49bb2c1e2d54a91aedecaf03b77cbb404c44/aiohttp-3.14.4-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6dfe80b41bcf8d80d2125fb99a171adeb86db2fcb35c1a68e0226acba0ba7f03", size = 1986051, upload-time = "2026-10-05T17:38:26.022Z" }, - { url = "https://files.pythonhosted.org/packages/1a/07/e95eddafffef7c3a74446f67ac4e477a49cec2c78f2ab6c86d1acfd90d2d/aiohttp-3.14.4-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:71e4a59c6a8c5a6ae8b0b696c32635913e8f526cc01448762eaf5a3c59df8a4f", size = 2107840, upload-time = "2026-10-05T17:38:28.112Z" }, - { url = "https://files.pythonhosted.org/packages/da/6c/1f83990fea249dcb10f48086726953546efc9199c96b6be7114532ac361f/aiohttp-3.14.4-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f887c3b7fb3058fc1ccd917f52078540c18d938d12018cb9edd64b6811d20c57", size = 1930721, upload-time = "2026-10-05T17:38:30.046Z" }, - { url = "https://files.pythonhosted.org/packages/6f/d1/48184a186ea26df4f81dd466144dcab7f9cdd1e131bfee0f0e41278c6f0d/aiohttp-3.14.4-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0da4525e9ba145a11617d2cd7e44fe1acaf471f9c72a0cad28e72879c1020fbb", size = 1774508, upload-time = "2026-10-05T17:38:31.8Z" }, - { url = "https://files.pythonhosted.org/packages/0f/ef/a9ec758c6d3850453838c31b56d1e4499eb47c80883753a12dcb203f9afa/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:f7e8d3c5caa44fdbee3eba1aa1417aa58c74c95d4089fe3c451911117fcbb2f3", size = 1902311, upload-time = "2026-10-05T17:38:33.791Z" }, - { url = "https://files.pythonhosted.org/packages/d6/49/9a2be54900f2dea6e63bbf9628fced604686a2e301130ccde0b1aa2e7e53/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:09092cf906c18c824b6b16881da5a89cc9cfa9b15344e496bcf880e9045bee33", size = 1912107, upload-time = "2026-10-05T17:38:35.614Z" }, - { url = "https://files.pythonhosted.org/packages/a2/2b/151254abfc0fe5cbb8e6c41ad04d52122db0af176fb31dbf3bc44e081bda/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:dfd144837e92264878bba6d3a7ffa8206668b21e87748740afd45d193e48c87e", size = 1960207, upload-time = "2026-10-05T17:38:37.322Z" }, - { url = "https://files.pythonhosted.org/packages/23/99/92c8dce336ac5784755a3144623528516f2e3b6b4871d02cad5a0642ae66/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:9413cffe4e0d654b9b524f9c99dde8cbdb37e0ed9a2c4edd2e63adbac6b374e8", size = 1760168, upload-time = "2026-10-05T17:38:39.214Z" }, - { url = "https://files.pythonhosted.org/packages/66/3e/f05fd8d1a9595730db8d522882eea76429b9be2ed5337609f7c6e3d9d49c/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:f50d719f97ba488dfb8e306cf8c8cc172ff0683ec0af53917b288229aa555ba5", size = 1979946, upload-time = "2026-10-05T17:38:40.927Z" }, - { url = "https://files.pythonhosted.org/packages/b9/14/8941aa73ffceabc2a0eb26878b4f1b2958fb7b5358f97cc49b1c00ed9258/aiohttp-3.14.4-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:68ed4824d96b7afec1f3a8d7fba190fe282718041c5772e20298003e1e3e5d66", size = 1923375, upload-time = "2026-10-05T17:38:43.184Z" }, - { url = "https://files.pythonhosted.org/packages/18/b5/ef275b63c8bfe0a21e7e8d3ef0e67c4745ed403f1894fe5205057cedd3b9/aiohttp-3.14.4-cp311-cp311-win32.whl", hash = "sha256:d7a41d1427136828e6b11d3f3fd194d4357d5205a5b610be7ae07b1ba52ab974", size = 488414, upload-time = "2026-10-05T17:38:44.978Z" }, - { url = "https://files.pythonhosted.org/packages/e7/0b/21bdd70a1e072222d9dbd96bed4fbed26f7c46c5a20af11b78d32fd049d6/aiohttp-3.14.4-cp311-cp311-win_amd64.whl", hash = "sha256:2efbdb87e79d596325c4eefaef0f4495d701145e882351310ebc538e854dc7a3", size = 512755, upload-time = "2026-10-05T17:38:47.036Z" }, - { url = "https://files.pythonhosted.org/packages/b7/4c/bb324a7d20a9598187bb028ca8d6bcf66c63589c8632420919dd576964ed/aiohttp-3.14.4-cp311-cp311-win_arm64.whl", hash = "sha256:ac6e6f90d9360e460c873f945f11dc8698db0a71fec6612823f1aaaab2c11faa", size = 492960, upload-time = "2026-10-05T17:38:49.006Z" }, - { url = "https://files.pythonhosted.org/packages/22/02/db5935d45347fa8ede56b777930740fb0e72bbb4473ddb6ff8541f6f2afa/aiohttp-3.14.4-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:55b0b335982b0db7117dff7f6a8e3aad43c4105f9e392ca04f9fc8d958a95cce", size = 817689, upload-time = "2026-10-05T17:38:50.69Z" }, - { url = "https://files.pythonhosted.org/packages/e6/56/f00aa46127e6342f019d567853eeeb932e04fb9b9424b5fb981ad68f4178/aiohttp-3.14.4-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:2d0d8e435582b0d53009dac99e26a3d2be932ed7c9dbfcfc70f3fce1cf943bd5", size = 549599, upload-time = "2026-10-05T17:38:52.525Z" }, - { url = "https://files.pythonhosted.org/packages/3f/bc/825c09b09962253a2103e4a88c04374ee939c0c8ea31c270daa0308efb07/aiohttp-3.14.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:bf734016932d68e1324cfb638cac7a0866a83933a33badf15e836a7e24efb8c0", size = 548132, upload-time = "2026-10-05T17:38:54.629Z" }, - { url = "https://files.pythonhosted.org/packages/40/80/8a1bc8036540fe7cb38219cc5c0aa67d32e9068165725e8199ea8200b08b/aiohttp-3.14.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:322e3d741b3133bcbb981a41d4f9b8ac3545c18de49c662c2b1f4e1c770b98ad", size = 1898485, upload-time = "2026-10-05T17:38:56.439Z" }, - { url = "https://files.pythonhosted.org/packages/3c/fe/65b464d8520ace0d65b4ca69bc9abe175f842c8ce8d1522d363d9669903f/aiohttp-3.14.4-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:15a3bb5f90a4e515071f3617a45dfe26560beb834a6b6e108cdf4bc9e9719ec3", size = 1875334, upload-time = "2026-10-05T17:38:58.536Z" }, - { url = "https://files.pythonhosted.org/packages/be/51/9c583be502720e927560a8414f4dfb7c7de41945e1a30ccf7003b93c6f85/aiohttp-3.14.4-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:6c044e52df1a466af82cad3518c92ea80cc4ddcfea86966ff083bb34bab29bf4", size = 1937772, upload-time = "2026-10-05T17:39:00.376Z" }, - { url = "https://files.pythonhosted.org/packages/a2/3d/b56512df7ea9cbb5f59099a6b375088dd578356a5a3fb27198ab82e19832/aiohttp-3.14.4-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d613d7d51bf06fe9a5e3aab86ce06d835bb0ceb1a31ea9e8766df4a403ae62a6", size = 2066220, upload-time = "2026-10-05T17:39:02.54Z" }, - { url = "https://files.pythonhosted.org/packages/11/6c/a7a42701d9ea319140a3d44a24ec72a00b0b46d1b899b26d8a705e65bdd8/aiohttp-3.14.4-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c5e93ab6e6330dce40f5b43996f1fc5f2543296d263a5e4b59ff09e73870b7d8", size = 1922895, upload-time = "2026-10-05T17:39:04.638Z" }, - { url = "https://files.pythonhosted.org/packages/77/04/f8337bd824ca3fe3968d34dc5037ace1c4872551c4621f8266239311d301/aiohttp-3.14.4-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:20134dc8e68c67e7478124d516449428684c0545b2d3faa575691c8bcbd56678", size = 1712589, upload-time = "2026-10-05T17:39:06.671Z" }, - { url = "https://files.pythonhosted.org/packages/fe/a6/d20e2c940b592d7c4a21690889dbff64fe0ca3facd9190696368694e1488/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:f0daef5ef012369dddc391c61f604111424aa9a96313a69fb899018b09d1b01e", size = 1862251, upload-time = "2026-10-05T17:39:08.523Z" }, - { url = "https://files.pythonhosted.org/packages/f5/e4/d50edd5ae5d024b380a8e892e333840bb22967a9eb9c8492108a403f678a/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:19290a108de0718b73bc69b86e788975c6a59855c671ebe2a98a07a6f968328f", size = 1895155, upload-time = "2026-10-05T17:39:10.305Z" }, - { url = "https://files.pythonhosted.org/packages/c3/d3/f36f2931f807ccf8437ec15e8f8bfaa4748d4792639401cc767a866abaa0/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:1494877625baeffab669f4a25a09ec4eea721b49e35363081a2a8e4231fe141f", size = 1906623, upload-time = "2026-10-05T17:39:12.411Z" }, - { url = "https://files.pythonhosted.org/packages/5d/0a/94821b711493142bf5e11c27b0d7502776778f7792c77ecc6647357d20c1/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:a779ce4bf099ce4ad2cdfed62f1ca536d435f53237c54ff40172fddada24d1b5", size = 1698932, upload-time = "2026-10-05T17:39:14.446Z" }, - { url = "https://files.pythonhosted.org/packages/d9/76/3d5a0d28362f0053c1c457024749911932481e8fd105fddf8305b1f93c81/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:0b4cec9fca876e2d4f4c6cb32b177390132d04618867689f43fefabf3f5c3980", size = 1934528, upload-time = "2026-10-05T17:39:16.354Z" }, - { url = "https://files.pythonhosted.org/packages/a7/51/9784a21dc05d2e0f6acaf864f16db53dab0fbd7b0753cef168601eacb012/aiohttp-3.14.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:217707313e23aedde9bea67cf8365c7b138b549ae179121ef3f476cf67e3173a", size = 1901984, upload-time = "2026-10-05T17:39:18.299Z" }, - { url = "https://files.pythonhosted.org/packages/44/4f/f98c88703e6d620243aa08473a946ca4e3756b6288690e38f0d9f9c1d007/aiohttp-3.14.4-cp312-cp312-win32.whl", hash = "sha256:18a9fb9a3f6e6e63f4d27f9adeef313a2d3c69a84d31170a844623824e722534", size = 480278, upload-time = "2026-10-05T17:39:20.206Z" }, - { url = "https://files.pythonhosted.org/packages/b7/bc/8555013f84b53e4fdde423131b641af50e822c6d7d9118b24c52b31f6900/aiohttp-3.14.4-cp312-cp312-win_amd64.whl", hash = "sha256:69dcb02d33dfe415d5ee342cc63b7d320efcaf4b761701c7bd7bfb91c715481a", size = 506317, upload-time = "2026-10-05T17:39:22.706Z" }, - { url = "https://files.pythonhosted.org/packages/21/3f/ca5bad7bfdaa7ddca053a044a1c7c0d4f3ad9d1f12f96dcab10bfb9c50e7/aiohttp-3.14.4-cp312-cp312-win_arm64.whl", hash = "sha256:d36b0263e7c2fbf1750b9f35d4e7e48b0442d8c45e4a89e3e74168821fb014bb", size = 487683, upload-time = "2026-10-05T17:39:24.482Z" }, - { url = "https://files.pythonhosted.org/packages/23/ec/7fee140da700ec3f5aa5e0fd2319f67be5e86de197e2384d27e5e6209e0e/aiohttp-3.14.4-cp313-cp313-android_24_arm64_v8a.whl", hash = "sha256:264b5a7568306590c44ae4a0237ad1715e35d447ea44ebf324e4c8fd9f78f67a", size = 539114, upload-time = "2026-10-05T17:39:26.322Z" }, - { url = "https://files.pythonhosted.org/packages/4e/04/930c01ce9e186e787046433d7dc5b45b188885f8406c14b58435b4431974/aiohttp-3.14.4-cp313-cp313-android_24_x86_64.whl", hash = "sha256:17e5d7c7775d8dd8e894c7ef6ebfa26509de36868a9a6c7c4fcfaf6a1bf43d60", size = 553514, upload-time = "2026-10-05T17:39:28.104Z" }, - { url = "https://files.pythonhosted.org/packages/2c/d7/983e3cea81c07e95f35d34da4d1e182b5c05489c49b7560b198a83f0da79/aiohttp-3.14.4-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:e91dc8fe9cbd052d16f7f1267e285cf8bbac4d2194bd5741f05ef201c77ed09e", size = 521381, upload-time = "2026-10-05T17:39:30.419Z" }, - { url = "https://files.pythonhosted.org/packages/0e/2d/80baed11659093883f51245755105557d3253e45bd0b693d70df0059d68b/aiohttp-3.14.4-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:8df6157d31703972aec9e3b93963f039ff06318301e30b007c3e941ff8a7ac42", size = 528347, upload-time = "2026-10-05T17:39:32.344Z" }, - { url = "https://files.pythonhosted.org/packages/c8/18/bfda255c311096c08dab26dc65f3d219f090df37dc5f5f6345f8c3aefc1f/aiohttp-3.14.4-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:220912b351549dc736c59d104dc443fa615753102bb778a4e98f86e4d94bff6a", size = 539914, upload-time = "2026-10-05T17:39:34.265Z" }, - { url = "https://files.pythonhosted.org/packages/51/fc/3b6ca6117c0c42481d719411fff7b5d3970ebd906543d3dc1ba40fe2462f/aiohttp-3.14.4-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:2efa42b39bb3f524d5eca3760639b584afdd1143a6b047fda29910ffb75e4993", size = 813997, upload-time = "2026-10-05T17:39:36.061Z" }, - { url = "https://files.pythonhosted.org/packages/b5/f6/86e3e02a9712aadc1ae0a1076bb2d1adf3d9addfe5542a28190c8f9b6d9b/aiohttp-3.14.4-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:7e7356059c8262d2c1fd95242e2b7b70fbc6eee3135bf470049cbec3e968b5b0", size = 548058, upload-time = "2026-10-05T17:39:38.109Z" }, - { url = "https://files.pythonhosted.org/packages/85/7e/6b9c2e271419d40ca76589613b3c7ab185fd3050a407bd2565b6aa46f695/aiohttp-3.14.4-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:fac247d0cc956d732df1211ac2d8a9999ec8dc1a92a90401de9d52e4ead546f7", size = 545933, upload-time = "2026-10-05T17:39:40.193Z" }, - { url = "https://files.pythonhosted.org/packages/14/fc/33d6e24a5f8ac32423230088c415e2a1c6efee23d902b62f20506631e40b/aiohttp-3.14.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6e2eb0f8b03b4f2bd154ed8cf7c1a119a1ad04808c258bf58f90138c83b8c6d5", size = 1888265, upload-time = "2026-10-05T17:39:42.182Z" }, - { url = "https://files.pythonhosted.org/packages/8d/e8/2eca1d468d83a514621d1280f9992d08649191db2028c9236b4edfa7c723/aiohttp-3.14.4-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7fbe827d27e0e369fd7bb88ceeaa5b46ea006e73e015b9dd77e3723a53162293", size = 1872300, upload-time = "2026-10-05T17:39:44.195Z" }, - { url = "https://files.pythonhosted.org/packages/d6/f6/5872983de71b0214acdfb86822f5cca295b39be4832ec589fa224aee0f6c/aiohttp-3.14.4-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:a70387146d03af9f047c629b71aa27d9594b3b31ec4c9c91e1a73d0d8bf38e0e", size = 1926213, upload-time = "2026-10-05T17:39:46.199Z" }, - { url = "https://files.pythonhosted.org/packages/ee/65/ebfefa11a546c33c717af63c67868408ecf0b33b23a9d75669af95485407/aiohttp-3.14.4-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0d0934926fc65744e2fdd44ce68b2d79d5ee608a1e23f0596b35dd696519bb7c", size = 2056609, upload-time = "2026-10-05T17:39:48.221Z" }, - { url = "https://files.pythonhosted.org/packages/69/c0/70667e82ec041f4122a17afce711bbcf94a71bec5888b69a49aed8817be2/aiohttp-3.14.4-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ff4b366510c733974adb7a4102c094e4a6308e6f369315a4cf14d2d0a619cf82", size = 1914740, upload-time = "2026-10-05T17:39:50.304Z" }, - { url = "https://files.pythonhosted.org/packages/bf/86/559e9dfea676206b20737d7ccb5b3716bff5e58d2a8d53682e5301724cd1/aiohttp-3.14.4-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:85fac7c99e0ac3dcbd6ae1c33774e0603bfc732ddb967a6fce4a731103c1888e", size = 1703390, upload-time = "2026-10-05T17:39:52.385Z" }, - { url = "https://files.pythonhosted.org/packages/fc/91/c98897d4cf23e120b2f3980042835cb34c86bbe3c653f3eaacf4bf986349/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ef1e9c3b4a2300023a5dc865889ce532cfaf6798ba4ef78fbbefe738a9d23efa", size = 1852642, upload-time = "2026-10-05T17:39:54.391Z" }, - { url = "https://files.pythonhosted.org/packages/14/13/0258f352cb2c236f358a5b57d138e15fa2566e17accc0758d968dbf2ceb6/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:97e65916588be0f952b3307aaa8460c0771fa98dbea2dd27dabc9f5d84d53c3b", size = 1890616, upload-time = "2026-10-05T17:39:56.466Z" }, - { url = "https://files.pythonhosted.org/packages/64/3c/f43e294ce1a06d1234a97bd862c1aa31acfa1a0eea3786c22fd0dc1ea731/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:840775cb39a9424f9edf142133a1192263ac5bd79117ad2a16602cef6a0c1e9d", size = 1896638, upload-time = "2026-10-05T17:39:58.585Z" }, - { url = "https://files.pythonhosted.org/packages/9f/f7/ce1e3a85b73d05037d729d3d32da7d6959b9e433435e9abd46c2fb38410f/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:54f9256430ca040d58affbd551513de13a5cff7d065204fc52b9a1b0af09a049", size = 1693003, upload-time = "2026-10-05T17:40:00.698Z" }, - { url = "https://files.pythonhosted.org/packages/1d/72/45eb900d6a9ee046728f5589f3d07f5d78f049b5fb84f48881fa4174d5df/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:6112d5931bf12c776188cab81b82bbb17d86e2e1381f2ade6edc43e6b240f0cb", size = 1927730, upload-time = "2026-10-05T17:40:02.943Z" }, - { url = "https://files.pythonhosted.org/packages/b2/43/a83ff79dc8375953a1f00b808a21c82590f4e68304fecccdcc42a25fb7d8/aiohttp-3.14.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:facc6df39047c4732cbd885bb62e40df20885fcd709fc399e11f81b45ce0fff9", size = 1891177, upload-time = "2026-10-05T17:40:04.989Z" }, - { url = "https://files.pythonhosted.org/packages/5c/ba/fbdc41608d4e2fb6084d960a41b392fa82beb5b126c2466de549b5c67fc8/aiohttp-3.14.4-cp313-cp313-win32.whl", hash = "sha256:7968634fa3a967a2bc0b9aeba1d5a1955501dcd7d0de44b96f7ebfb662797735", size = 479943, upload-time = "2026-10-05T17:40:07.402Z" }, - { url = "https://files.pythonhosted.org/packages/35/51/d75629750e705832fd5cd52516a82943ed58b6e09c30e14830f5d87452fa/aiohttp-3.14.4-cp313-cp313-win_amd64.whl", hash = "sha256:c0a894b0265d139cd4c2c8bd4643822cc289a4a5331e21e810881bd000ffb2dc", size = 506209, upload-time = "2026-10-05T17:40:09.49Z" }, - { url = "https://files.pythonhosted.org/packages/02/64/66452d2ffcc13e5e5ee4ba4a968656fa4a98c29ed5ff0205d4fde02b2943/aiohttp-3.14.4-cp313-cp313-win_arm64.whl", hash = "sha256:da16c3037178e72589d91de59536d271dffc92c2be2b47c38a45538cba54fd29", size = 487163, upload-time = "2026-10-05T17:40:11.526Z" }, - { url = "https://files.pythonhosted.org/packages/d2/fd/b653b1f969e2e949fe4726af7a8043e8ef117f202bed7757ac8564e077a1/aiohttp-3.14.4-cp314-cp314-android_24_arm64_v8a.whl", hash = "sha256:749bfc43bb1df71bbe6ed215044d5412d786698fc5771d2037436ca49622f3c9", size = 540738, upload-time = "2026-10-05T17:40:14.109Z" }, - { url = "https://files.pythonhosted.org/packages/90/b5/eea49a0bb697deffac5165d707ec53a24748d6720b3af77a544107b49573/aiohttp-3.14.4-cp314-cp314-android_24_x86_64.whl", hash = "sha256:c113e4b489d711f606ca278cd8dc89179746244ea841aa0638b1b134600afad0", size = 554494, upload-time = "2026-10-05T17:40:16.231Z" }, - { url = "https://files.pythonhosted.org/packages/11/ea/cf8f4efbbfa8572d9965cd43b3c6c84c581aa006772e5ce3ab4020027e9b/aiohttp-3.14.4-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:50969522bc7022026a2c7968e67da5c789f6b716b988edac55dc630390efd5df", size = 522653, upload-time = "2026-10-05T17:40:18.879Z" }, - { url = "https://files.pythonhosted.org/packages/a3/24/9f6721f0b52323789cb1041ffc3afa729462d9925607e733a065b6fc5e17/aiohttp-3.14.4-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:cbf92cd7a1c800cee244558dd5630abb45c1c1093ef7b0d546a99f526ff7a9eb", size = 529697, upload-time = "2026-10-05T17:40:21.296Z" }, - { url = "https://files.pythonhosted.org/packages/9c/a4/399debc3c2ca0ab88a08e3082b4c4f62d0f66978af60243c63f2345ef337/aiohttp-3.14.4-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:fc76be08ff407fba717a769aff04ca1b4bf9ecfdcb5caadef84a563fdbbd146d", size = 540526, upload-time = "2026-10-05T17:40:23.548Z" }, - { url = "https://files.pythonhosted.org/packages/a2/97/90379813b18b795bccdeb3a5a85e9b93ac2c69f9c2a5d0faba59da3ad6d1/aiohttp-3.14.4-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:9b416f995b68a921069e6ec61fa07f2ac3ff033d92e97a69f673af89f5bb954d", size = 818866, upload-time = "2026-10-05T17:40:25.842Z" }, - { url = "https://files.pythonhosted.org/packages/78/70/824fd0dac819652f1df895b3f621a75bf0a3050c30e38d8d2316e34ab821/aiohttp-3.14.4-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:2c9585101cfca10e74a07cc0ef2bdc6d90616e6750926b20456f429d0608f740", size = 549666, upload-time = "2026-10-05T17:40:28.523Z" }, - { url = "https://files.pythonhosted.org/packages/8c/45/eafb2dd200dd2b770ed25a2dc5731c4ba5d58ab3fa8e2e82494bb946808e/aiohttp-3.14.4-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:3c4dcf611b095e7983421f49d01ffbed7ed574891533d606ea115fc23e7c4e90", size = 548961, upload-time = "2026-10-05T17:40:30.613Z" }, - { url = "https://files.pythonhosted.org/packages/a7/bc/6c733a1c71300293471ac7ef1dffd12b5b4dc9a43c53461224b2b8a7f667/aiohttp-3.14.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f8f61a9b5fa56c58e3441f9dc64137f786232d40fb89127190d0e0f84e1e5865", size = 1883165, upload-time = "2026-10-05T17:40:33.062Z" }, - { url = "https://files.pythonhosted.org/packages/37/34/885ddbd351679a31141b25e0d1a5e4f67738806e564c858b399709b61239/aiohttp-3.14.4-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:d43e538dfc85b705fd832620d050970ef5613b3869a7169b44a554b9dab9eee9", size = 1844119, upload-time = "2026-10-05T17:40:35.266Z" }, - { url = "https://files.pythonhosted.org/packages/cc/ef/0a64dac53c11d569851efb3e7eddb43551df72b2c172ebb34cccc93bcd3f/aiohttp-3.14.4-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:4135c4bb4b7682a7633fadc7170ea969d843f83aa7224e70111a20675105c985", size = 1930222, upload-time = "2026-10-05T17:40:37.527Z" }, - { url = "https://files.pythonhosted.org/packages/69/5f/774792ed8f973e0d234fcb06b0f0bc9f29e9a0a0dd847f6418c2904be7d9/aiohttp-3.14.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:9055324f156a94fdf6dc9a825ae60f9a2947b88f591ea81ee80826633de62ae7", size = 2038842, upload-time = "2026-10-05T17:40:39.815Z" }, - { url = "https://files.pythonhosted.org/packages/cb/05/e00f35581c97656d9e864edaa03292382c620dd1d9c836a4f73a2279acc4/aiohttp-3.14.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fb22c8e4b60385a9b414c70c6e8b2d0f4b23ff7fc4bb572ceb58297b228169f1", size = 1887845, upload-time = "2026-10-05T17:40:42.359Z" }, - { url = "https://files.pythonhosted.org/packages/ca/2e/07e3eff5b4c1b082a2eaf0ffb508b409b21ea1ddc9fdc57f3eabb51469a1/aiohttp-3.14.4-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:3b6945559a260112742ed58cde2165488d2fc51aeea34afbaa99d9371b43e1b5", size = 1702533, upload-time = "2026-10-05T17:40:44.569Z" }, - { url = "https://files.pythonhosted.org/packages/75/44/816844b7f876e6f8fee4ecb088269fcd92241da712e4814a4d624eda13a9/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:8f4078a90b174f15efb2c8725e8720c40dbd3b2cf6350dbc085c964a938d9de7", size = 1849058, upload-time = "2026-10-05T17:40:47.818Z" }, - { url = "https://files.pythonhosted.org/packages/ae/bd/163242e12464a1f3e58a77e28beca949652ddce84abdd5500a91c70a1e0d/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:f433c5654e32f72de3ef074d715eb5c7604eb6d28a5c2f3c9e5056f20fe6b306", size = 1854600, upload-time = "2026-10-05T17:40:50.401Z" }, - { url = "https://files.pythonhosted.org/packages/f2/59/5c1ae708a89524eddfd9c727b87cae26b5c50c3c76683b910ac06151ead0/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:871035fe79c636b6bc126ed78df37d72b830dfc751612cb4b1040360edf2719f", size = 1896565, upload-time = "2026-10-05T17:40:52.625Z" }, - { url = "https://files.pythonhosted.org/packages/37/45/95300a7de69241fe47d3f838f3fb582c712782e172d447ff650a013ea673/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:2617132524f66338f6c1d218cd16081576aefc40df4f2bcba338a99fbf67fec1", size = 1693092, upload-time = "2026-10-05T17:40:54.862Z" }, - { url = "https://files.pythonhosted.org/packages/ff/33/01a8e61d48d0094121092c74125df14c0f8f10ee3149bfe68b6f869409a9/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:d8bc326133272deee8ef337581550450e4bb735c0520be893b950a1f5baaf41a", size = 1917073, upload-time = "2026-10-05T17:40:57.656Z" }, - { url = "https://files.pythonhosted.org/packages/9e/d6/1a4f24624cda6686d5b927e26d5d1ae3ebb692faf88e93017fab4b391fd0/aiohttp-3.14.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:3ec57223e261b7fa9979c12dbce009ca53439be76cac3af27f860d3e4b1d6f7a", size = 1872656, upload-time = "2026-10-05T17:41:00.123Z" }, - { url = "https://files.pythonhosted.org/packages/be/be/ed286fcfa2d22061ae021b568c790123505cd482df35e23023339ecaed96/aiohttp-3.14.4-cp314-cp314-win32.whl", hash = "sha256:7242043e71fc449a19a47d92f4e9fd1e0ae8d3f88488982381f422bf6d651218", size = 485461, upload-time = "2026-10-05T17:41:02.686Z" }, - { url = "https://files.pythonhosted.org/packages/c0/74/e040e6f65f4da305777f1adb3023d47401693489e4a337c983b52d2a0a6b/aiohttp-3.14.4-cp314-cp314-win_amd64.whl", hash = "sha256:019587c7b3a44917dd61bcb312fd5c034f341dc9851b83e7b41b65e08b68ca0f", size = 512147, upload-time = "2026-10-05T17:41:04.98Z" }, - { url = "https://files.pythonhosted.org/packages/2e/5e/bddb33ae15fdd5a68a10a986587aa9916c418a712fdd110d3b3ae9b51407/aiohttp-3.14.4-cp314-cp314-win_arm64.whl", hash = "sha256:60dc71d38db0988f37e78f6ad4a010a2f6355cfac3fff5f130cf5ef2231f3f0d", size = 494685, upload-time = "2026-10-05T17:41:07.366Z" }, - { url = "https://files.pythonhosted.org/packages/22/2e/7b884014b40573f919fc3a528e5028bc37b249e31a93928ba61bdd25c960/aiohttp-3.14.4-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:674f53ab9d2794e2dd767619a3384bf1006f8d075e43c19d449a645f8ff641c2", size = 855696, upload-time = "2026-10-05T17:41:09.514Z" }, - { url = "https://files.pythonhosted.org/packages/5f/e6/b6e2b4f580ab6ae39241bb9182aca60e6e1915cdad0148faaa04db3f366b/aiohttp-3.14.4-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:6d243221f73e5ac546c2ed9255100423e4bc092b08b944f23498e8cf3096c26c", size = 567931, upload-time = "2026-10-05T17:41:11.685Z" }, - { url = "https://files.pythonhosted.org/packages/63/99/ae8e3a1a18adcbf636839d18b3cccc51007836ccdae5209381c5cf82d1ae/aiohttp-3.14.4-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:0daa016eb74e7888ed5f9ceec6eea3158999c1c4a115ef5cbe88baa8d924f94c", size = 567421, upload-time = "2026-10-05T17:41:13.836Z" }, - { url = "https://files.pythonhosted.org/packages/63/38/c5d4bb58be72b967a4090d2deeb38571f8c992852936c51dbbbeae49db1c/aiohttp-3.14.4-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:70c031a622aa20add05ebd234b90adaf6bf51c1c88cc305ec760721af83308c3", size = 2054173, upload-time = "2026-10-05T17:41:16.098Z" }, - { url = "https://files.pythonhosted.org/packages/eb/87/3c8a9c7670f56d478a75c5bb84b336fb61a67b908e36c30a4a96ed8c8e86/aiohttp-3.14.4-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7df363fa7c38945a896e12c69af4a1a56cbd4152791d9e41fd0bac396b72de38", size = 1918296, upload-time = "2026-10-05T17:41:18.478Z" }, - { url = "https://files.pythonhosted.org/packages/49/97/bd00e499c0a1505b44f5e23b9739034ea9be792ad42537f2894211ba1c07/aiohttp-3.14.4-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:02a508ba5ad91c4d730523584c0adc65882274bba5e37c33bc2f475e37577256", size = 2027513, upload-time = "2026-10-05T17:41:20.874Z" }, - { url = "https://files.pythonhosted.org/packages/23/1d/a3666a7c224f86a881f18d673a8ffdc92fa4c35274fb4361822f8f0dc566/aiohttp-3.14.4-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:0cb3edece6fe6a944eaf97d803b88f606da6bc1600b1894c2969e78ffdc1fc29", size = 2152686, upload-time = "2026-10-05T17:41:23.181Z" }, - { url = "https://files.pythonhosted.org/packages/46/7e/f4204b8c4959c46f6367c182afbbacef08a1b53874281912c52fbd80151c/aiohttp-3.14.4-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:21ce1223b461bcc5fb389a7204001578f1c0b85c2da60a84d915ebb021294245", size = 2006431, upload-time = "2026-10-05T17:41:25.776Z" }, - { url = "https://files.pythonhosted.org/packages/33/43/091e69d42967cbea833ceb355c5457f8f70748fe08b88c9d91491b3fafb8/aiohttp-3.14.4-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:35d5432f0dc1c8b71307e9112461b52f336da225e344283eec4779222c0a1dff", size = 1789101, upload-time = "2026-10-05T17:41:28.095Z" }, - { url = "https://files.pythonhosted.org/packages/47/7b/b57cbe533c01098c5d30471f057e7c3c19f281122f756acc9c716b636e2c/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:d6ec364493057c118d08292f7cd60865965c209167d8657b45643a26aef77495", size = 1974472, upload-time = "2026-10-05T17:41:30.499Z" }, - { url = "https://files.pythonhosted.org/packages/9f/44/79acce03611450e4ed8594f96f1cea40d70bc84fb4e918f94d7d9454a4af/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:70492983b7aed9e61bda82fe1ce80bcba9199610886443133783a288638923c0", size = 1956340, upload-time = "2026-10-05T17:41:33.009Z" }, - { url = "https://files.pythonhosted.org/packages/da/bb/36e6cbd6720e3377a02f8709aec6fe80de729ef41e78ba01f13d50363c73/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:a77776673331577147e9d25cd7833a72e8891b47556336cff06ba1569e488b99", size = 1965771, upload-time = "2026-10-05T17:41:35.506Z" }, - { url = "https://files.pythonhosted.org/packages/69/0f/879735ac70ce5e6852916eed51c706a517b205150a8d384f9fa60933a3fc/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:73799000dd6fd5247094fd8e6d3e1eb871e41aab5cc35dff9d9f654cd230bc24", size = 1780297, upload-time = "2026-10-05T17:41:38.284Z" }, - { url = "https://files.pythonhosted.org/packages/01/5d/7c030ca5b6baf3b02eccd11afc3d58f0b35e407031d5cc78cae9c24921c0/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:27b370fb532e707e8c96d04fa0c96301fb7dba2d50aaca57f6c456cdfffec5bd", size = 2001374, upload-time = "2026-10-05T17:41:40.888Z" }, - { url = "https://files.pythonhosted.org/packages/80/1e/ddacbb8141d727034c51dd192d17749521d5b30b03f84aa034325396089e/aiohttp-3.14.4-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:884e0d1c707b6217fee3080b9b4029eee7551af788ee761010df19be158414b7", size = 1968531, upload-time = "2026-10-05T17:41:43.62Z" }, - { url = "https://files.pythonhosted.org/packages/3a/08/2214f823701eebc3e57db141faeae76df7bfd415f254cc7c1692258f228d/aiohttp-3.14.4-cp314-cp314t-win32.whl", hash = "sha256:f2e3d34edb151d3e27f93a8338e2da33e2c7261cd4c879ce5f5fe280cc190ea5", size = 504126, upload-time = "2026-10-05T17:41:46.321Z" }, - { url = "https://files.pythonhosted.org/packages/91/a1/90e9b6fd23310b4e82d0c0a37b5ecc2944053350473c57533c1da9647235/aiohttp-3.14.4-cp314-cp314t-win_amd64.whl", hash = "sha256:88cf889e51092537fe44adfbff96c2a22d6479d6f92b97b3d413fbfd0a4decf4", size = 531494, upload-time = "2026-10-05T17:41:48.849Z" }, - { url = "https://files.pythonhosted.org/packages/97/ab/5b501472c92b9b1dc53742591d6210dccb262962f4721299300d3a9f664b/aiohttp-3.14.4-cp314-cp314t-win_arm64.whl", hash = "sha256:ca450c6d42fda7c0bfaf0e200f32f77c5f2c960a33be1e14d197c84588b7f5f6", size = 510544, upload-time = "2026-10-05T17:41:51.358Z" }, - { url = "https://files.pythonhosted.org/packages/2b/27/5e1f8446545be98e9416af59c396b1ed1f9f3294afb0a40ee3a709889273/aiohttp-3.14.4-py3-none-any.whl", hash = "sha256:5c6758ba62aea282c537179cfc8474a90f2b5f7b089cc5ff66d8920d86a9bfdd", size = 279487, upload-time = "2026-10-05T17:43:44.905Z" }, + { url = "https://files.pythonhosted.org/packages/ca/82/f7f0652e3a845e095d8505a2807a0fe5782abb71f99b2f516c93ff0be492/aiohttp-3.14.5-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:ef692a24087a699c0a4a26af45e746e0c1eae2116f6d8a5ff91d8aae2b867b45", size = 834351, upload-time = "2026-10-11T00:59:07.668Z" }, + { url = "https://files.pythonhosted.org/packages/95/c5/10cb0a5195bc3ec05a74ee494f8431a15e559800f2e869f3526ad4a16f04/aiohttp-3.14.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1220353657ad49493551f089ce02f1a348fd57ffd585bfec77f2f3c4fe3a7346", size = 560663, upload-time = "2026-10-11T00:59:09.853Z" }, + { url = "https://files.pythonhosted.org/packages/32/dc/b7fefdd7dd64d080da2d69d609344191cc94b0e2eba70200c371014c9b36/aiohttp-3.14.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:330900acd0dc4cb8b27f9c127fbaad770964845338493e7906ae3822e82dbf8d", size = 553263, upload-time = "2026-10-11T00:59:11.5Z" }, + { url = "https://files.pythonhosted.org/packages/61/5f/3271cad1b34347e8bf27abee20d501ebdc56cec97e8ae59cd3fabb23d917/aiohttp-3.14.5-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0684952aeae1f5dbfe02d46039338513b94009baecd15d8e4098a357c4c4a2a6", size = 1843813, upload-time = "2026-10-11T00:59:13.143Z" }, + { url = "https://files.pythonhosted.org/packages/67/af/2011b30fe61889af112ad380e6fd44a93cca4b51296f612cac666c177882/aiohttp-3.14.5-cp310-cp310-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:d94e44be379e569758fee8a9a58431cfc3c2598c708b92b1cfe96c66b4c94aef", size = 1811243, upload-time = "2026-10-11T00:59:15.091Z" }, + { url = "https://files.pythonhosted.org/packages/e3/ba/72f3ac523ed48d38cdfb169f1b2a2e93ce06d9fcf4f46d0f5692e9539bcc/aiohttp-3.14.5-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:5af42135fdfebdadbc2bcd9c0842a48ccf0d62794c36a260b21dc4b94d1e0119", size = 1898815, upload-time = "2026-10-11T00:59:17.224Z" }, + { url = "https://files.pythonhosted.org/packages/e6/69/bbf24f3b555ea1befa7db1e2510c728c8b0e80e61ce360beb7d94bc562b7/aiohttp-3.14.5-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:4f07fe3ac408d8b3f768be471dc3f56d43843c47d97c66120534467a15ead197", size = 2022390, upload-time = "2026-10-11T00:59:19.244Z" }, + { url = "https://files.pythonhosted.org/packages/5d/38/01f5fc732d5373d6c099db0343279cd4e6607287d336bab6ff6ae9085a0d/aiohttp-3.14.5-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f375db73a39f5cf83696d500e21a67f418dc9a988955756f254be8f03b7b3651", size = 1856329, upload-time = "2026-10-11T00:59:21.19Z" }, + { url = "https://files.pythonhosted.org/packages/15/85/1f86fbd8fe34ad447c63e679404a1d5be435fe256a9d281b791fc1ed0d35/aiohttp-3.14.5-cp310-cp310-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:8df7d481654ac96fe1ba9a02a9f67770fdd367823e0d5ef01b922725c4bd2cfa", size = 1712763, upload-time = "2026-10-11T00:59:22.982Z" }, + { url = "https://files.pythonhosted.org/packages/39/1e/ced51cf47e427e7aa6142c3bf6f33022472703bc9061289329532d3c40c0/aiohttp-3.14.5-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:e95c8def4b81c5d68d5cf1f54c07acd7c0d2577af244e5b6da802120825737c6", size = 1812125, upload-time = "2026-10-11T00:59:25.032Z" }, + { url = "https://files.pythonhosted.org/packages/6a/f1/9610b4e263b554ca4191501ba72b952efe06556b647da74887abc5d41049/aiohttp-3.14.5-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:f2ebb54b3f932210503072f09974b4fb574d823e497a944adfdcd140a6a00255", size = 1829550, upload-time = "2026-10-11T00:59:27.078Z" }, + { url = "https://files.pythonhosted.org/packages/ac/8a/1d1fb27cf9fa99b13133de33044c4d10d7705be0d4173d6d56abad1b67f9/aiohttp-3.14.5-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:038c2c7e8caa26b6c8423779b5eaf1893904048a512c19b32fe841ffa5592b50", size = 1868179, upload-time = "2026-10-11T00:59:29.315Z" }, + { url = "https://files.pythonhosted.org/packages/24/9f/3cfafa86ff025623dcca0d30335db7b8a6f3fa348148441208147e827e04/aiohttp-3.14.5-cp310-cp310-musllinux_1_2_riscv64.whl", hash = "sha256:b7806e804889231b0e06469fd4a5c06313d1c0a3377322b6d9237fa5e0fe4167", size = 1697721, upload-time = "2026-10-11T00:59:31.161Z" }, + { url = "https://files.pythonhosted.org/packages/62/1d/86439a23bf32296e715d8c75535f0cd701821d36719324baef65bcd6af9e/aiohttp-3.14.5-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:9bab2045550c4fe0f7baf89574db1b455c195750702ba96fef1f16972b146617", size = 1887000, upload-time = "2026-10-11T00:59:33.329Z" }, + { url = "https://files.pythonhosted.org/packages/1d/0f/6044f2d02b3874966d84cd119f9b8eda46aa2991230078aea4dd17750cc9/aiohttp-3.14.5-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:96a2e584f0b9ed8f1fa33211397dcf67bb7069866402cb405d191c2f0defb9a3", size = 1842020, upload-time = "2026-10-11T00:59:35.384Z" }, + { url = "https://files.pythonhosted.org/packages/18/64/b49d2a34428ff937631b07dde74d5879a7a2c8559aab39331d40769e8cb6/aiohttp-3.14.5-cp310-cp310-win32.whl", hash = "sha256:602c1e9b718a3275c580149f947e7fac65044c0a20e599553fb12e9700da9eca", size = 489282, upload-time = "2026-10-11T00:59:37.061Z" }, + { url = "https://files.pythonhosted.org/packages/a6/7c/1114e723f1c4a65597820b605a0ddcd7f3b28fdfde3ac8d520d517ca582c/aiohttp-3.14.5-cp310-cp310-win_amd64.whl", hash = "sha256:bea559ad70218d230663e4210875735076a9bfea5994cef34a55a25faeaf2544", size = 512021, upload-time = "2026-10-11T00:59:38.7Z" }, + { url = "https://files.pythonhosted.org/packages/48/97/e08c646f4bad63d77876b24591d013d7f33f02fda7c931eafe3224f38467/aiohttp-3.14.5-cp310-cp310-win_arm64.whl", hash = "sha256:dca3fa8d8a0a26679862eccb0b1a9151b2b9f1cd2c212e7a6335778faaff5833", size = 493016, upload-time = "2026-10-11T00:59:40.525Z" }, + { url = "https://files.pythonhosted.org/packages/d8/f3/8997f18890a92c79f77fcfbb4f78ca17c2d4ab109e9eb6d31b4e9de194a0/aiohttp-3.14.5-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:d51db97c96384fbfcaf8f4c65922183a68b94f891c3c10c862ef5f6df2adbb1f", size = 832358, upload-time = "2026-10-11T00:59:42.195Z" }, + { url = "https://files.pythonhosted.org/packages/8e/42/084651e9efb5cadb99265f786df60f2a7b353cead7bfd2c87003cb4867ad/aiohttp-3.14.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ae53924aa853a7a2ca20ed4142c7c6b56338e4d4cd999e2980075b9efc2e257a", size = 559636, upload-time = "2026-10-11T00:59:43.677Z" }, + { url = "https://files.pythonhosted.org/packages/3d/fe/92838944e601f0fe195fd3f3ada37e29fbee3d19bfd323fe15937ec79d36/aiohttp-3.14.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a2c473a355f9239efcb72c92d5abfd8fcdb0cc78c8e9af607e72ca12dbb36593", size = 552588, upload-time = "2026-10-11T00:59:45.592Z" }, + { url = "https://files.pythonhosted.org/packages/8f/b8/dd9b95c5c20ceae1b47738e656bd79e9883e3117a9cc8b143901eb604e9a/aiohttp-3.14.5-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:32e8fa6644e541fcd7e02430588c7fc93b602c1778ea0bc345505db76b61cfb4", size = 1928224, upload-time = "2026-10-11T00:59:47.294Z" }, + { url = "https://files.pythonhosted.org/packages/c6/47/70010cd2ba8746968d53d433ff328c33f06a66c99da5f3de759c64a6b2eb/aiohttp-3.14.5-cp311-cp311-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:579f97d5120f2971876d2ddca2968135f6944d00c44c3a6590ad7d86ca9b403f", size = 1877674, upload-time = "2026-10-11T00:59:49.472Z" }, + { url = "https://files.pythonhosted.org/packages/c5/a1/b026f071dbd87f0bdba86b92d47e46f3899e3ad7143b6e0fe7e7887090b4/aiohttp-3.14.5-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:24409db442e2fb6e766bc7f3943851a8381dec3098140e43bb2e843b79e31b12", size = 1985850, upload-time = "2026-10-11T00:59:51.296Z" }, + { url = "https://files.pythonhosted.org/packages/36/d1/f7b6f6f8c3cb5a71b53baeddc2e70c224c28b12a23a55c42994c504019b7/aiohttp-3.14.5-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:5e8f97c0488ffda3082766ac0f2c8150a9a58c4d05788330e479cfd449b37939", size = 2105471, upload-time = "2026-10-11T00:59:53.191Z" }, + { url = "https://files.pythonhosted.org/packages/42/74/2a2b22953de15c6c8a80debf26db3047e4e8a5a5db6dd7c2c6c01eec0605/aiohttp-3.14.5-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:50a195903119008fe9cc68710535eb37f556ffffd6a7759afe70a2c145587045", size = 1929915, upload-time = "2026-10-11T00:59:55.609Z" }, + { url = "https://files.pythonhosted.org/packages/33/ad/f80e8d33933d0eacd0217efa3b7fb32c9f48ed480ed0db53cf9948bf474f/aiohttp-3.14.5-cp311-cp311-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0133c3c3b54a0bf1e71fa5c1ad95c93f07fd54e24ef1fe182f5122e1573d2bf1", size = 1773832, upload-time = "2026-10-11T00:59:57.611Z" }, + { url = "https://files.pythonhosted.org/packages/04/a4/0273d239f3e3bb69438f209c64c82e1f98dc60d5db264795e41f7dd05dcb/aiohttp-3.14.5-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c172db893e516e1358e65a95ee20b7ce7173963eefe318b6ab2a2220688b999e", size = 1901001, upload-time = "2026-10-11T01:00:00.605Z" }, + { url = "https://files.pythonhosted.org/packages/16/ed/7dd439d26c654645bc34ca3c9a822fc11c1c51801fed1cefdfe1cc41c1f6/aiohttp-3.14.5-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:f2a7966bda23dd85051f1661ce0ace38d6890e05ec6c357ecae9d2479cba377e", size = 1907218, upload-time = "2026-10-11T01:00:02.699Z" }, + { url = "https://files.pythonhosted.org/packages/32/dd/86249c3b8248562a17fd3e22ee0c164378d65766f01aceef62cf52783710/aiohttp-3.14.5-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:4887d130a7bbfed3a85493bb5a25e5b5b558d40c1d986dd16970d2bb26d63793", size = 1958650, upload-time = "2026-10-11T01:00:04.851Z" }, + { url = "https://files.pythonhosted.org/packages/bc/0b/ca4d53d68f683ce195807fd0aeb063bf6d1c6b39343fff234c9524e8d5a9/aiohttp-3.14.5-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:225c579c23b68b343cccea27a7e06e3bd8ec23a09c30b427eb3f1e4ca6239b20", size = 1760057, upload-time = "2026-10-11T01:00:06.978Z" }, + { url = "https://files.pythonhosted.org/packages/6b/42/005437ffd7fa56c2ce3347add40404b654a32754ce91f2e2a14b9e5ab2bc/aiohttp-3.14.5-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:ab52d8f1fc1b64821c1fbad64a647ed6203627004059a6d1ed4f0858a1499703", size = 1978081, upload-time = "2026-10-11T01:00:08.868Z" }, + { url = "https://files.pythonhosted.org/packages/03/71/3a5b66fe1b7b23d3c6524350817ed55de5feb7fbb4cccba7cbe044d118dd/aiohttp-3.14.5-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:cb131d775a1573c1aee66656bd78b023577bbdb6cb8349a07773bd4f73e68a6e", size = 1922954, upload-time = "2026-10-11T01:00:11.035Z" }, + { url = "https://files.pythonhosted.org/packages/69/84/d08a554f281d42fd7c6b2b6dd7738f3e3a7a9f657ddd87e11ca2091cdfe3/aiohttp-3.14.5-cp311-cp311-win32.whl", hash = "sha256:e87046c8ff77a8decdb6a41d8ab25824b47531b2da933aeab0c1e21c7acff329", size = 488101, upload-time = "2026-10-11T01:00:12.933Z" }, + { url = "https://files.pythonhosted.org/packages/0f/15/52b5e65f02b33686ae49f1518548ae4f5a7adaf31d9d3c54fa12a143137b/aiohttp-3.14.5-cp311-cp311-win_amd64.whl", hash = "sha256:6f275c11d1aa6d4c458e05a68be084efe3c55a113d99e3f46a318098e52948fc", size = 512575, upload-time = "2026-10-11T01:00:14.743Z" }, + { url = "https://files.pythonhosted.org/packages/b0/b9/bb75012635f3defb0f7cbb7c4ae391e36bb9cb3fbdca3b9944e2ebebf743/aiohttp-3.14.5-cp311-cp311-win_arm64.whl", hash = "sha256:b032a0023eb41d768ce77d83210ab2a3c389bc0b09313273c7e1eca48c10a755", size = 493179, upload-time = "2026-10-11T01:00:16.961Z" }, + { url = "https://files.pythonhosted.org/packages/d5/94/6ba86efddcb616c811b40e6a0dfdd862738f647e4e3860a961075d5e9ed8/aiohttp-3.14.5-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:df37b620684e19b5e25724412518ccafc3b1a49cdac706fdbd2f983fad943450", size = 817499, upload-time = "2026-10-11T01:00:18.901Z" }, + { url = "https://files.pythonhosted.org/packages/5e/e1/7bca6d84dabd228aa8eb4b7f9feac2586aaa9be5505d7d65bf287a615c43/aiohttp-3.14.5-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:ef60869969180ec2464f1349aff07138ae35ca2200f0946cb3552e49e8f301a8", size = 549467, upload-time = "2026-10-11T01:00:20.854Z" }, + { url = "https://files.pythonhosted.org/packages/64/91/11b89f45ca486252dd67dd5f3231fec04bf5518da39a95cb3997619f17fb/aiohttp-3.14.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d079c0a0135c36e7beb6f1c88087c8f108dc5891cdd0b5eafa778421bda70ed2", size = 548067, upload-time = "2026-10-11T01:00:22.659Z" }, + { url = "https://files.pythonhosted.org/packages/22/ff/c6615806c14aab34f82b9424ccde8ce6e417315fd57ce1c5b4d4747888e1/aiohttp-3.14.5-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:abfda5cb094a829f7bc25216a32f7db2e85cc65bd59910f8e7b40b3d9b224764", size = 1896245, upload-time = "2026-10-11T01:00:24.638Z" }, + { url = "https://files.pythonhosted.org/packages/39/b2/25a8c971ae6a92c8394d77e42422d7f38989e05cf41a5ceb92d73d67ab7e/aiohttp-3.14.5-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:9cc882cf8619109583c906b4d4a85d6a111a98afa34b7a450d1e08118d016820", size = 1872180, upload-time = "2026-10-11T01:00:26.838Z" }, + { url = "https://files.pythonhosted.org/packages/2f/d5/99f93ea36cc5205e47c1e5a803e087f2ad21b5430b5db2e942cb6e988a37/aiohttp-3.14.5-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:7457580535e019e1247ea35d6a02bf081ad30c26d0cbc210c93f6c3ab67a0835", size = 1937261, upload-time = "2026-10-11T01:00:28.74Z" }, + { url = "https://files.pythonhosted.org/packages/40/a6/9ac9c9e6695040bd73d2584a1b59a9388f6433c76d5294a7bf591e21ffe5/aiohttp-3.14.5-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:c5ed596aedb9c42afd3fe0aae3117725378ac73d2cc5ddc735056fbdb96c5d02", size = 2064994, upload-time = "2026-10-11T01:00:30.623Z" }, + { url = "https://files.pythonhosted.org/packages/da/e4/aa172eb534b7f02f1f8ff1c3213347eaf3cf218db91a727c6863c22f1035/aiohttp-3.14.5-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:20f085697d7e911f1f73c43ed03fafbed1e7121797e2eb5428efa80398060584", size = 1919630, upload-time = "2026-10-11T01:00:32.548Z" }, + { url = "https://files.pythonhosted.org/packages/06/7d/4eedafc5bababa8932636c141e346806966eade12c0b7e5946d43bf8218b/aiohttp-3.14.5-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:74b0a9c8270f9b0a11410e124ff8d4f18bfc1f1837440ec84da5ae7b50927b5d", size = 1710016, upload-time = "2026-10-11T01:00:34.471Z" }, + { url = "https://files.pythonhosted.org/packages/b2/94/eee018537ba19da0ceb2ac79cab83faed4ac49568e08376e2799043f2538/aiohttp-3.14.5-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:19e2ba471507c34f8252402ab50f5ab512398b9ea8c8f1cb26beb3f75793ba30", size = 1858112, upload-time = "2026-10-11T01:00:36.581Z" }, + { url = "https://files.pythonhosted.org/packages/68/76/354653a306547238f3427283905972d796ba7c292ba9977abec9f2b6f260/aiohttp-3.14.5-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:d418ce2af40c6bb685b3f663e9e8de27cb0a22431d8e88a167348d7f01878073", size = 1896371, upload-time = "2026-10-11T01:00:38.478Z" }, + { url = "https://files.pythonhosted.org/packages/f2/ec/63e8c7136b570e356345ad3174e3820fdc973ea10712cb6c649bf875755a/aiohttp-3.14.5-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:70cb4008ac2ed1e0ca9e824deb4b53d3aa0d939109698ebf1e723a84337bd794", size = 1905836, upload-time = "2026-10-11T01:00:40.527Z" }, + { url = "https://files.pythonhosted.org/packages/57/d8/11365bda144b127928cd42533d0eff78a55613c9e28f81941bd6630ea887/aiohttp-3.14.5-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:a23fe35d776bc03cb495938b9594450d047e3bc08c5255315a82323e9cb7d2dd", size = 1696534, upload-time = "2026-10-11T01:00:42.686Z" }, + { url = "https://files.pythonhosted.org/packages/2f/3d/82df0461b18e00b2998f205c03e0d3010222478c43640aceb8e03dcd7e8f/aiohttp-3.14.5-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:3e0eb43bed3c6801a6cee315195377789e90b2a72c2277a475b578535312488d", size = 1933970, upload-time = "2026-10-11T01:00:44.71Z" }, + { url = "https://files.pythonhosted.org/packages/03/ad/6ddfe0aacd931c17b53533336d97e9d11a98b96d6ae815a9da0b19f82ccf/aiohttp-3.14.5-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:3be7dd397d64ca3e1869626fa9318aaebb54b7bf93bc72d7a205448d83e4f748", size = 1899501, upload-time = "2026-10-11T01:00:46.629Z" }, + { url = "https://files.pythonhosted.org/packages/9e/8e/189bdd9ae4793059bb09f6dc880f211a6c6c7859cebcbf33912dbfab7dd7/aiohttp-3.14.5-cp312-cp312-win32.whl", hash = "sha256:eb324e2009fb54db30a071dad7caf6998ee2879c4704007efb244514dad1fec1", size = 480370, upload-time = "2026-10-11T01:00:48.468Z" }, + { url = "https://files.pythonhosted.org/packages/ae/ce/1f08114679d49655b30a6e0a29858375c94b82c1de1a0bd0a20c2fee8b02/aiohttp-3.14.5-cp312-cp312-win_amd64.whl", hash = "sha256:2cc38a4f2b516bef1714e690df87a0e043faf1a7693c82d860091684453d5111", size = 506141, upload-time = "2026-10-11T01:00:50.272Z" }, + { url = "https://files.pythonhosted.org/packages/79/d4/c7b4f60b16a1b7e43249fa9031ae05e7e8c341ba4b7d1866f914dafeaa0e/aiohttp-3.14.5-cp312-cp312-win_arm64.whl", hash = "sha256:a63afd1f757de949028387e65a7127b61ad0f775432dbb0e62816ae619fe69ac", size = 488108, upload-time = "2026-10-11T01:00:52.321Z" }, + { url = "https://files.pythonhosted.org/packages/d3/e1/2841e020ebb7aefae5513586193e011e06313d9a6bdbd296622afbbce204/aiohttp-3.14.5-cp313-cp313-android_24_arm64_v8a.whl", hash = "sha256:9ad7e6aa38c20da1be697874349c4c273c8a03b7887169665081706398d0439a", size = 538932, upload-time = "2026-10-11T01:00:54.3Z" }, + { url = "https://files.pythonhosted.org/packages/f7/a6/7fb8ea8fe96bcc7b7c7a36d10f021d99d01a8dc8a4b3f0ddacecfad9a80e/aiohttp-3.14.5-cp313-cp313-android_24_x86_64.whl", hash = "sha256:f59c7673465908cbe506117176156c127f29f917677afceada34957179221d91", size = 553329, upload-time = "2026-10-11T01:00:56.442Z" }, + { url = "https://files.pythonhosted.org/packages/de/64/d056e3c27647dc25af1a592cf356245382ea7c808171b9dac7677afedfc8/aiohttp-3.14.5-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:1b5416552740edf07234cc9437d0706f2acb67b93c198670b1a68e1b2b587dec", size = 521367, upload-time = "2026-10-11T01:00:58.345Z" }, + { url = "https://files.pythonhosted.org/packages/3e/e4/95226147e11d4db916fd1d495dcf85af8e3816e38333e42718241196e848/aiohttp-3.14.5-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:43351bdb5e4c3cb7d1772368e988534e869a74db7778079a83782c11c69535c7", size = 528322, upload-time = "2026-10-11T01:01:00.211Z" }, + { url = "https://files.pythonhosted.org/packages/17/cd/1d3c9192cafdb51cad62b2d3ded96cff9cc8af51893210aadd448a325389/aiohttp-3.14.5-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:c8c4478bef6d57fcfda15dae461ea3c9f06aa7b257c58df3f2300174ccbb185a", size = 539874, upload-time = "2026-10-11T01:01:02.06Z" }, + { url = "https://files.pythonhosted.org/packages/f6/0c/dfa33aecc7d4d1dc75e05248f5eac5a0edf4d09e7b44d93ab62529b0c1db/aiohttp-3.14.5-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:c2c30484dd1417ef98b51021ffa2cc0d7f3c78918adaaaab7e70817335ab3e02", size = 813836, upload-time = "2026-10-11T01:01:04.01Z" }, + { url = "https://files.pythonhosted.org/packages/33/17/4a63738052d20567d55529d6daa1b9480d906fd52930fbcf6d3fbed618f0/aiohttp-3.14.5-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:dab9ac5a67c8d1f070c00fa8fccb7cbd1b8dcc1a8d6b42f37540df9b3d4cc603", size = 548070, upload-time = "2026-10-11T01:01:06.035Z" }, + { url = "https://files.pythonhosted.org/packages/15/e5/b57e58695a757fd4c02497c033fced96a69c631b13866c43d336530c9670/aiohttp-3.14.5-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:e1cc2bfaee8c214f06080a7c7d5772419b8a1108e8e5349236189811823fb02a", size = 545786, upload-time = "2026-10-11T01:01:07.817Z" }, + { url = "https://files.pythonhosted.org/packages/9a/68/8c2c67a3aedf46e00f3c42f04fbc6983de80d4ed5786151e33681ba45883/aiohttp-3.14.5-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:74efb69332b85675b1eabd760a8cfc2e2cf42c60607c66f88014c1bdfb40942d", size = 1886492, upload-time = "2026-10-11T01:01:09.834Z" }, + { url = "https://files.pythonhosted.org/packages/ab/4b/74aab5e8d28c62e8f795b4fe8f38cf5586fd264a9a27bd2141ef6490333d/aiohttp-3.14.5-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:42b5e616946dbaf505e2bff18c9af2cd4ef9e7ef300ee58a6e951a5b7cf147ae", size = 1870057, upload-time = "2026-10-11T01:01:12.045Z" }, + { url = "https://files.pythonhosted.org/packages/a8/f7/eafc3b1988302b1815d9fd4a21071be5c360d616c0a430d02fd92dc97688/aiohttp-3.14.5-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f9033b43f511f27547c557dcaba0177649e10a3725336ccd2cce0fdc1dc4850d", size = 1925119, upload-time = "2026-10-11T01:01:14.09Z" }, + { url = "https://files.pythonhosted.org/packages/a1/04/78d8f294f74dd570f3898ff20402349fce524176045df98ba727d6846a68/aiohttp-3.14.5-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:15a310d3c71398e3d7bfc93a1a73fbe664315cd9e9016b8efc1cff85eeab7155", size = 2053137, upload-time = "2026-10-11T01:01:16.344Z" }, + { url = "https://files.pythonhosted.org/packages/32/51/395d225ef36f5a50d8e548dcd3141bfdbcd31fb6eed859022c573d2c4d66/aiohttp-3.14.5-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1ffa3a523a36d8628f98c06492ae16a31a23d14c0b4ec721757b477319f656d6", size = 1911038, upload-time = "2026-10-11T01:01:18.653Z" }, + { url = "https://files.pythonhosted.org/packages/ff/a4/2aec1aa06d82e8a244843b5dae31d78061e5e76744270a86dd0ee051c889/aiohttp-3.14.5-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:5fb6a6e919bfb703227bc1ce6579281b84b1a2ba57deb9794dfdbec7dcd1e40c", size = 1702205, upload-time = "2026-10-11T01:01:20.904Z" }, + { url = "https://files.pythonhosted.org/packages/16/27/6051bfde7b6f418f70edd60d655fa426abb3355fa0981764739d87ecf160/aiohttp-3.14.5-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:43e1b7994a8b038125f722bff07492ef501110722c2727c408995d9fb864c421", size = 1848588, upload-time = "2026-10-11T01:01:22.918Z" }, + { url = "https://files.pythonhosted.org/packages/9e/44/55efc06fc26c4e6e1c095f231b4c222bf2d86d64a8eebbc24b2bb5958ea8/aiohttp-3.14.5-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:5f3e96071686755d9cd3600c3880183eb94b012178e92746d68101800f0ed8a3", size = 1887540, upload-time = "2026-10-11T01:01:25.278Z" }, + { url = "https://files.pythonhosted.org/packages/48/dc/1502bfdc2a65760d386ac6a00090b0addaa8a3c9c60b3f8127fad3a9afb2/aiohttp-3.14.5-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:cd88b01f3d37b7a2a34f91d98f14720206f1ea3d540843fab2d649dd5fb91fec", size = 1895030, upload-time = "2026-10-11T01:01:27.316Z" }, + { url = "https://files.pythonhosted.org/packages/93/7e/44174bb6288264418c9eec07a5e35180969c0d5a796c7af544db3cb8a33a/aiohttp-3.14.5-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:f2ed8b64dc0c651c0f5a9c926777719770021251b8f336d97c4b80b660836ce1", size = 1693244, upload-time = "2026-10-11T01:01:29.39Z" }, + { url = "https://files.pythonhosted.org/packages/47/dd/b507d64e50db23888582fff08eda13998b12f9dea70c072edaac19218380/aiohttp-3.14.5-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:a9918e58faf62ba2c7147927d06057aec78f42475aff5048047ec47e7265a600", size = 1926308, upload-time = "2026-10-11T01:01:31.634Z" }, + { url = "https://files.pythonhosted.org/packages/98/4b/5b51b4f63e3f2793151f4aea49c48fe1e00baeb7cec9c7a206de499f8de0/aiohttp-3.14.5-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:42f320d4a5b00b9af0bddcfec5407dc6f2d9816f006b2f79ebbaa31f16895df3", size = 1888406, upload-time = "2026-10-11T01:01:33.715Z" }, + { url = "https://files.pythonhosted.org/packages/ff/13/d5e818a5eaba9f822016727299f41c0e1075799f82a6433ec508a93ab867/aiohttp-3.14.5-cp313-cp313-win32.whl", hash = "sha256:3ae800a20947e2c2e53088047d021e6bf7d51560cc49f6a0737a1f79d2e3a13c", size = 479970, upload-time = "2026-10-11T01:01:35.677Z" }, + { url = "https://files.pythonhosted.org/packages/8d/d0/8eca2c65aa467320990d78fb2005f38ed3588944280c39ff9deb6423fef1/aiohttp-3.14.5-cp313-cp313-win_amd64.whl", hash = "sha256:d05e94cdfe0d15d0206f970722d2554780ce562787b21b218b275447f8751319", size = 505985, upload-time = "2026-10-11T01:01:37.574Z" }, + { url = "https://files.pythonhosted.org/packages/7a/f8/4cdd65305d2fca14b886bea9ed2abb1fe726287872524e56e3d26692b47d/aiohttp-3.14.5-cp313-cp313-win_arm64.whl", hash = "sha256:f001b571ead90ca1770f1e616db255351a1703317f20374c361ef22f12c06d09", size = 487629, upload-time = "2026-10-11T01:01:39.477Z" }, + { url = "https://files.pythonhosted.org/packages/43/be/3184a1d34a8be665569eadb7e9e764b4629e4f3413e241cb2e4d6fecf3b3/aiohttp-3.14.5-cp314-cp314-android_24_arm64_v8a.whl", hash = "sha256:939042d5cda21d41a6f512e7cc8b8e33a2aebff863352251da495fbd91b673b5", size = 540673, upload-time = "2026-10-11T01:01:41.354Z" }, + { url = "https://files.pythonhosted.org/packages/60/2a/d35f3ba4cf157b072e3b674bf9983047ca5ea5173c995d32d877e1191d36/aiohttp-3.14.5-cp314-cp314-android_24_x86_64.whl", hash = "sha256:6da32b5ff3fd78d244e37300463434c7145162bfd2b6e9e915ab164da37f7343", size = 554087, upload-time = "2026-10-11T01:01:43.719Z" }, + { url = "https://files.pythonhosted.org/packages/fc/d2/61a33880ca4eaca95a9c60ca3f6beed15555af1028652dfaac601627787b/aiohttp-3.14.5-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:1b438b73c38111818d0c9d6a5c2bfed8584c8e503a49ef085d70e874ec846738", size = 522613, upload-time = "2026-10-11T01:01:46.154Z" }, + { url = "https://files.pythonhosted.org/packages/31/1d/de579b299d2225dc2c6fd99d579d91f16c02a913fb5af9a3cf2fe9bd88ba/aiohttp-3.14.5-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:755933b107ea7a6a9ac916f635a70595a5b1a32fac10a8ff0b9f2ab88555550c", size = 529682, upload-time = "2026-10-11T01:01:48.477Z" }, + { url = "https://files.pythonhosted.org/packages/f4/4a/ddb923564e15e053b6e060b0036e1694dcadcb13aa476c5a87dcad20e336/aiohttp-3.14.5-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:b3cc509327c7b27f6f4727a8830f4004f6df7766e179f2f4b8e54e65c0bec5d3", size = 540120, upload-time = "2026-10-11T01:01:50.474Z" }, + { url = "https://files.pythonhosted.org/packages/3d/36/a640fbecaa53727a5900b892bdbe17b5f3e8cc88903e22864fe41b654def/aiohttp-3.14.5-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:7bd8ac754ebd6733a3e2a0dd1674c4d8ab086196803fd8dcd776f07b4e2607d9", size = 818795, upload-time = "2026-10-11T01:01:52.665Z" }, + { url = "https://files.pythonhosted.org/packages/ef/b6/d52ca608859e271b5fa7944074802dc45f60e52c318a4ddc34edbf73586e/aiohttp-3.14.5-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:e724a7b6091f0b1ac064f9d1b15ff9ec52e6033a86cdae649e5f086e32a3c0db", size = 549667, upload-time = "2026-10-11T01:01:54.65Z" }, + { url = "https://files.pythonhosted.org/packages/ce/b5/05b8ac39a76ff4bca89f42a4c2471560c71f894ff6e4bc16158c951874e3/aiohttp-3.14.5-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:c32e26310cc10e547f53cd13d39a369034f69dcb7d749d5cb0e5f67bc196b6ba", size = 548922, upload-time = "2026-10-11T01:01:56.547Z" }, + { url = "https://files.pythonhosted.org/packages/19/b0/5aa186d56ce2334dabe29b70bd99dc8ae926ee44184c0de64a53d415a4f3/aiohttp-3.14.5-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1eb8167961ec4dfcc8cb9dd50bd0ee72519f7ef496be95203e49e27b01618382", size = 1882422, upload-time = "2026-10-11T01:01:59.258Z" }, + { url = "https://files.pythonhosted.org/packages/db/f7/7d5c91bb9620db300c8ddb05337a9014301acb626223faff3abcb8ea47d7/aiohttp-3.14.5-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:c1d60eafd9c7e8e74abd03a5b00df44e7febfe6d9b89b559c0a6551eef0699d4", size = 1843621, upload-time = "2026-10-11T01:02:01.417Z" }, + { url = "https://files.pythonhosted.org/packages/30/0a/b208953b96d8f24b75f6da704f508e6c5cf3022f52b60c61933df082e89c/aiohttp-3.14.5-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:137351bf20bbed9a65e839f4a4452ac377389bdb2f2857d2acffef38f5e9f2d1", size = 1927915, upload-time = "2026-10-11T01:02:03.697Z" }, + { url = "https://files.pythonhosted.org/packages/f6/79/90ebcccb55e2d1e11a1fed581d83bb966e38fb35fb4b2577fdc980f8707a/aiohttp-3.14.5-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:fba47bc2c3d7303c3d027c6cf4d07626c37b1314ac81f5820c31032e0ca1f677", size = 2036339, upload-time = "2026-10-11T01:02:06.046Z" }, + { url = "https://files.pythonhosted.org/packages/a6/66/55a8904b3a129fafdf94f9cc0a2e4ca09a3c914650be52355db7ad0bbdb6/aiohttp-3.14.5-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:94684b879ac1d71e4238850c99b62dc1b28d9086b156a2555f082010b85a865c", size = 1888041, upload-time = "2026-10-11T01:02:08.384Z" }, + { url = "https://files.pythonhosted.org/packages/0b/b8/96b25da7329a52e42c812b1e8b076386039ec4fc312afa043d173d8147fc/aiohttp-3.14.5-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:56572c42e3ecd636de8d2c3dd54cf5fc939cb5c32eb56297f176a0d366fac622", size = 1703849, upload-time = "2026-10-11T01:02:10.903Z" }, + { url = "https://files.pythonhosted.org/packages/1b/43/fbf976e3ae4c038d6f5c84945ab2150298c2d71201674d4e53d158063e75/aiohttp-3.14.5-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:a95529a92a446db351675f4aab518feaf5e99842f63f5dd17160c2b74f382db3", size = 1849703, upload-time = "2026-10-11T01:02:13.15Z" }, + { url = "https://files.pythonhosted.org/packages/8b/7d/218e912f4c1d89bde7ac551409be57ad2f6121638e56942d395a7cb1fa58/aiohttp-3.14.5-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:3edbece0379b8b4aaa67619b8aa2399bb66fce372cd5911098a434ea77220aa0", size = 1852695, upload-time = "2026-10-11T01:02:15.295Z" }, + { url = "https://files.pythonhosted.org/packages/5a/42/252a1b9287e3b6e393a1c3bd1776f36af30f5f25f071bbf2b0cb7eba9116/aiohttp-3.14.5-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:56d9828f204331a5ca8850fcfe2bcce95a149f1f223f60cc7216e5524978e480", size = 1893493, upload-time = "2026-10-11T01:02:17.93Z" }, + { url = "https://files.pythonhosted.org/packages/78/97/71cae83d5100556fad1521684f7cd1e3e578432644f850245ed3bd969310/aiohttp-3.14.5-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:20064a177a070d789ee64a50b01a9161d3468e989baacfc6c714aa685c4b332f", size = 1693468, upload-time = "2026-10-11T01:02:20.666Z" }, + { url = "https://files.pythonhosted.org/packages/1f/69/73d88e97a8b5f0ca7a946d0011c0de99fb188b1687c7948ecd0553dc5bf0/aiohttp-3.14.5-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:81c2b3dfd56c62bee6108e4852d5970b4cf9086390b6983f52b666e878c1f115", size = 1915398, upload-time = "2026-10-11T01:02:23.011Z" }, + { url = "https://files.pythonhosted.org/packages/05/f0/881644bcb15d4b258daea9b720a0af9dc4330496cc8d6ade9090cdd0cffc/aiohttp-3.14.5-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:09ec102b4b8c9a920275733bbc11fdbb615efe6f9231a06007c0218d336fb77a", size = 1871470, upload-time = "2026-10-11T01:02:25.278Z" }, + { url = "https://files.pythonhosted.org/packages/7f/de/19d9ebbcce5aedaa3242d8a99ff8816a60bdb7629fb0084bf4a45bfd1f62/aiohttp-3.14.5-cp314-cp314-win32.whl", hash = "sha256:9c428eb2bd8817588d16a0ab898aa4eb5d141f896aa2b394cc79a4cf61d9a8e2", size = 485517, upload-time = "2026-10-11T01:02:27.579Z" }, + { url = "https://files.pythonhosted.org/packages/a9/74/8cdaf0e58c2588371670d5a9a8215bbb971d36940b6e5d051967dd05c07d/aiohttp-3.14.5-cp314-cp314-win_amd64.whl", hash = "sha256:6f967dde489ca6a8c02d093ab245d2cbf50ccb5c36adf0188b17b0ca39d24b67", size = 511755, upload-time = "2026-10-11T01:02:29.685Z" }, + { url = "https://files.pythonhosted.org/packages/1a/6b/e0100e25502430a531c7cf1482a378d0b65bf728ab60c01ee270e56bc469/aiohttp-3.14.5-cp314-cp314-win_arm64.whl", hash = "sha256:1d2d981b53dd09a319e3570ef8cc3bbc3ef86f5a7abef0f6b2bff3867db3a9e7", size = 495151, upload-time = "2026-10-11T01:02:32.163Z" }, + { url = "https://files.pythonhosted.org/packages/9d/c2/ca2ead7b655688c53c03aeeb6e96e6851c9ff08d6be7b13802f53a6ae8fd/aiohttp-3.14.5-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:9ce66feae6ac65327379460380549bf1b8df8e17c4e25df2a2bcf168272e3bed", size = 855396, upload-time = "2026-10-11T01:02:34.443Z" }, + { url = "https://files.pythonhosted.org/packages/a7/70/22206fea409255a240c926ce11de48de354ae2bb90ca44f709c05497585d/aiohttp-3.14.5-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:27c2322e03f66101acb09869ce1cf1efc04994ee95e1735b69827bf8c8b9d781", size = 567734, upload-time = "2026-10-11T01:02:36.644Z" }, + { url = "https://files.pythonhosted.org/packages/ce/e5/79a36c118308b56f8667d67e05d2fb6dc638ab45985704cdb199631bedaa/aiohttp-3.14.5-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:ff75a7537413a86e7cafe98e0e1d6e3dc4b15c6349896e7d5c6b881bfdb6d550", size = 567379, upload-time = "2026-10-11T01:02:38.757Z" }, + { url = "https://files.pythonhosted.org/packages/63/a3/2ebec7dece3b1f02c30d2e484647f6f7b13952b1bb40a4cb285b849e8432/aiohttp-3.14.5-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9c061aa954daaf57d2a4b8374f9fca621ef0e1b603584431c220c22458c59b6d", size = 2050686, upload-time = "2026-10-11T01:02:41.169Z" }, + { url = "https://files.pythonhosted.org/packages/3a/d2/7e4d093db2f4450482652e7ef19a9e19919028f5135aa52bc4078c3beb80/aiohttp-3.14.5-cp314-cp314t-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:1612fa5857b37bf32e5c1eaeefb96e3b01e9c70679eec81f0934e8a600080863", size = 1915077, upload-time = "2026-10-11T01:02:43.563Z" }, + { url = "https://files.pythonhosted.org/packages/a6/88/bd40d09958442a0a1df67da81de496361d6e2afc04f9db2950d835da750b/aiohttp-3.14.5-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:adbeee7d6fd4cf5fe0aece2fb3edc4243615d3180430ba8149d01a90670cac99", size = 2027204, upload-time = "2026-10-11T01:02:46.185Z" }, + { url = "https://files.pythonhosted.org/packages/63/eb/3a601c1f8d3103c1a60ea981f20924855da9f575d2007fc38f8898b792fb/aiohttp-3.14.5-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:b2966998927d7bed9db12c0a4647b0c7b179755878fc9c357fe1ffd3e3b0c1a5", size = 2149520, upload-time = "2026-10-11T01:02:48.812Z" }, + { url = "https://files.pythonhosted.org/packages/22/d0/4e41bfe1b1ce1cb6f6d2e59fa7a88ef5cf92c402b2d07e9018778ba9edbc/aiohttp-3.14.5-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8e317e0fb6b16212c881d2205a7d87414c29acd69320b3aa6dce9d9c7b86fe4f", size = 2002039, upload-time = "2026-10-11T01:02:51.293Z" }, + { url = "https://files.pythonhosted.org/packages/6f/5e/72067019545c502b881b031153c437752ecef48d7d213bc0218ccebb4bfb/aiohttp-3.14.5-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:50343c1757b4b6f6708eeaf24534b32f19dfb99fb1b762c00420867a62fc81e0", size = 1786164, upload-time = "2026-10-11T01:02:53.533Z" }, + { url = "https://files.pythonhosted.org/packages/d9/fe/7741efd6119bfb7a00827fe6f7b84b4409de58d888ae21adc5a9a6824992/aiohttp-3.14.5-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:083673c7a94c3ea035caaa5ca04288bdb44887abfe1f5ba23294e6a4b03efd2d", size = 1970689, upload-time = "2026-10-11T01:02:55.888Z" }, + { url = "https://files.pythonhosted.org/packages/43/e7/342a13bf67f34d269bf2f7e870ecd72b99c832cc6f0a271a9210c0ebfb84/aiohttp-3.14.5-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:2528cb4c6b92008c76ac9ac6298624069bb2db91ff4929905512d1d84485f658", size = 1951967, upload-time = "2026-10-11T01:02:58.467Z" }, + { url = "https://files.pythonhosted.org/packages/e7/d4/fdb3b27340617e5e64df18a70fa89097778652ea5c7c7e2f79def76999c3/aiohttp-3.14.5-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:b1b8ece1e71132d2afba4dbc0c3d62c766e25165990b25db1196c04969eb3d84", size = 1968511, upload-time = "2026-10-11T01:03:00.883Z" }, + { url = "https://files.pythonhosted.org/packages/83/b2/e8f88298de78d1a951f36f9f966d38ec6ed1d4721303ba02064a545e8aa6/aiohttp-3.14.5-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:fce9523df31cea6284f3e2c479876750d7687cf671d7b25d32b19effc0e86441", size = 1778497, upload-time = "2026-10-11T01:03:03.206Z" }, + { url = "https://files.pythonhosted.org/packages/22/68/9ccdb93d664345c546be7f34480b921774d8c0d98f47e70d7e03b115d475/aiohttp-3.14.5-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:09e0eb18c7e0c8777e2f9149de63799195b9b3ca1b5c81ba6f32f2c6b8628210", size = 1999676, upload-time = "2026-10-11T01:03:05.829Z" }, + { url = "https://files.pythonhosted.org/packages/57/4a/a33cfa6dcb00e94194ae4fe710432ca4ed111e016356b4ba4d2f4c3a124c/aiohttp-3.14.5-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:6774814fd5c338e72ee0da5cbb9432816df450e69c019f72b5d29bdec2a1792d", size = 1963437, upload-time = "2026-10-11T01:03:08.196Z" }, + { url = "https://files.pythonhosted.org/packages/f4/20/eacbecfea3b5c3dcbfc9b023e3a5460f43e5dda16d06a2877ebe7184c3f3/aiohttp-3.14.5-cp314-cp314t-win32.whl", hash = "sha256:33f706574e32c6e694f352a856e05caf18f7f2c871b3e87b41c55ea452b409ab", size = 503973, upload-time = "2026-10-11T01:03:10.481Z" }, + { url = "https://files.pythonhosted.org/packages/ff/78/18eec294f6c8c5dc845dcf6d730a0147d8d0f17e86138a7bdb85e43a30fa/aiohttp-3.14.5-cp314-cp314t-win_amd64.whl", hash = "sha256:5ba14a839fbe87cf7c12a6b5661c05f324a296eb8363141edb3944ba63d4c9d3", size = 531190, upload-time = "2026-10-11T01:03:12.716Z" }, + { url = "https://files.pythonhosted.org/packages/9d/39/e53f8169acc85271ebd12b5b32ad7f1541b35639ccbe0f49034c64785d10/aiohttp-3.14.5-cp314-cp314t-win_arm64.whl", hash = "sha256:1061b364556e8172e8d46b0b183adeeb73e8c42d30ebc745591e1bd89acad52e", size = 510360, upload-time = "2026-10-11T01:03:15.08Z" }, + { url = "https://files.pythonhosted.org/packages/68/30/173960c42b05a6c59f7558e4b12a4b0d9ba376cf6aa9bde7f9e08a30ca8d/aiohttp-3.14.5-py3-none-any.whl", hash = "sha256:efc21a454892828368b11c2c780de0ff8bc991f73f6b99c6b66e56205470929b", size = 279517, upload-time = "2026-10-11T01:05:08.523Z" }, ] [[package]] @@ -1146,19 +1146,22 @@ wheels = [ [[package]] name = "claude-agent-sdk" -version = "0.1.44" +version = "0.2.165" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "anyio" }, + { name = "jsonschema" }, { name = "mcp" }, + { name = "sniffio" }, { name = "typing-extensions", marker = "python_full_version < '3.11'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/30/40/5661e10daf69ee5c864f82a1888cc33c9378b2d7f7d11db3c2360aef3a30/claude_agent_sdk-0.1.44.tar.gz", hash = "sha256:8629436e7af367a1cbc81aa2a58a93aa68b8b2e4e14b0c5be5ac3627bd462c1b", size = 62439, upload-time = "2026-02-26T01:17:28.118Z" } +sdist = { url = "https://files.pythonhosted.org/packages/7f/45/10f00a408b480926b5e340e3507562ede1e30d4ce5b73eea9ccc3468a9e6/claude_agent_sdk-0.2.165.tar.gz", hash = "sha256:1bfa8e7a6bb36e82de9a12324c9bcfa6eebd4f96ee5890f0c656d50445240ff8", size = 365169, upload-time = "2026-10-08T18:18:49.528Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/e9/1a/dcde83a6477bfdf8c5510fd84006cca763296e6bc5576e90cd89b97ec034/claude_agent_sdk-0.1.44-py3-none-macosx_11_0_arm64.whl", hash = "sha256:1dd976ad3efb673aefd5037dc75ee7926fb5033c4b9ab7382897ab647fed74e6", size = 55828889, upload-time = "2026-02-26T01:17:15.474Z" }, - { url = "https://files.pythonhosted.org/packages/4b/33/3b161256956968e18c81e2b2650fed7d2a1144d51042ed6317848643e5d7/claude_agent_sdk-0.1.44-py3-none-manylinux_2_17_aarch64.whl", hash = "sha256:d35b38ca40fa28f50fa88705599a298ab30c121c56b53655025eeceb463ac399", size = 70795212, upload-time = "2026-02-26T01:17:18.873Z" }, - { url = "https://files.pythonhosted.org/packages/17/cb/67af9796dad77a94dfe851138f5ffc9e2e0a14407ba55fea07462c1cc8e5/claude_agent_sdk-0.1.44-py3-none-manylinux_2_17_x86_64.whl", hash = "sha256:853c15501f71a913a6cc6b40dc0b24b9505166cad164206b8eab229889e670b8", size = 71424685, upload-time = "2026-02-26T01:17:22.345Z" }, - { url = "https://files.pythonhosted.org/packages/46/cd/2d3806c791250a76de2c1be863fc01d420729ad61496253e3d3033464c72/claude_agent_sdk-0.1.44-py3-none-win_amd64.whl", hash = "sha256:597e2fcad372086f93e4f6a380d3088ec4dd9b9efce309c5281b52a256fd5d25", size = 73493771, upload-time = "2026-02-26T01:17:25.837Z" }, + { url = "https://files.pythonhosted.org/packages/e4/a7/a7226ae5e7fa3f225d99a0acf12ee354c4af9c953661f66bbcd424e48853/claude_agent_sdk-0.2.165-py3-none-macosx_11_0_arm64.whl", hash = "sha256:7f7017bb59eaf77b9a7c7ce3b9ed2c8a397b8201c8630f011bb1b955290f06e4", size = 97973182, upload-time = "2026-10-08T18:18:56.039Z" }, + { url = "https://files.pythonhosted.org/packages/5c/9d/1eaa82f8dbafa63a3fb26aabc088be307c4977438269cc6cb10056a32e99/claude_agent_sdk-0.2.165-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:f4b5c6f536062e3af72357b1235f05ad4513230a32a3c639341a91a607d2df1e", size = 102479136, upload-time = "2026-10-08T18:19:01.908Z" }, + { url = "https://files.pythonhosted.org/packages/40/4a/93fe172811bcd7704c4c4776d5eed1bb1881ba440d86e0f8e5cbbec0dca9/claude_agent_sdk-0.2.165-py3-none-manylinux_2_17_aarch64.whl", hash = "sha256:46a47e1e1075a8f2b7976f6bd5aa06c5610cb322c47cdc5b728fb25d02691164", size = 107447420, upload-time = "2026-10-08T18:19:09.571Z" }, + { url = "https://files.pythonhosted.org/packages/57/81/a0d3ff04ae7045218566b36d1c78729c3fc7550877e154697f263ac5122e/claude_agent_sdk-0.2.165-py3-none-manylinux_2_17_x86_64.whl", hash = "sha256:9dbee4bfc69f0bb27ee455afdc19d78f958540a99217d2e28831fb9b7d496f08", size = 107800988, upload-time = "2026-10-08T18:19:16.24Z" }, + { url = "https://files.pythonhosted.org/packages/7f/d8/1685e8fc14bae5b9cbcfd6f4f6ca8b7ae8fd497a8bbf9c108978dd98620b/claude_agent_sdk-0.2.165-py3-none-win_amd64.whl", hash = "sha256:cf41dc1b1019bc7321b695d621fc94e6d8982c095cfb7d433d5c293e356a2404", size = 110401968, upload-time = "2026-10-08T18:19:24.136Z" }, ] [[package]] @@ -4871,7 +4874,7 @@ ci = [ { name = "assemblyai", specifier = "==0.52.4" }, { name = "beautifulsoup4", specifier = "==4.14.3" }, { name = "blockbuster", specifier = "==1.5.26" }, - { name = "claude-agent-sdk", specifier = "==0.1.44" }, + { name = "claude-agent-sdk", specifier = "==0.2.165" }, { name = "detect-secrets", specifier = "==1.5.0" }, { name = "google-cloud-speech", specifier = "==2.40.0" }, { name = "google-generativeai", specifier = "==0.8.6" }, From 631e26f361a911ea9f82940d1cc413449cce9caf Mon Sep 17 00:00:00 2001 From: Mrinal Chanshetty Date: Tue, 20 Oct 2026 17:34:07 -0700 Subject: [PATCH 59/66] chore(cost-map): mirror model_prices_and_context_window.json and backup from main at 6083cf97769aeedb2719c5b5c901ded3106cc79e --- ...odel_prices_and_context_window_backup.json | 21995 +++++++--------- model_prices_and_context_window.json | 21995 +++++++--------- 2 files changed, 20370 insertions(+), 23620 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 617aabeeecf..98fee42de3c 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -99,22 +99,22 @@ "input_cost_per_token": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-large.md" }, "ai21.jamba-1-5-mini-v1:0": { "deprecation_date": "2026-11-26", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-07, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-mini.md" }, "ai21.jamba-instruct-v1:0": { "input_cost_per_token": 5e-07, @@ -293,6 +293,7 @@ "supports_nova_canvas_image_edit": true }, "us.writer.palmyra-x4-v1:0": { + "deprecation_date": "2027-03-09", "input_cost_per_token": 2.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -300,23 +301,25 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "supports_function_calling": true, "supports_pdf_input": true }, "us.writer.palmyra-x5-v1:0": { + "deprecation_date": "2027-03-21", "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "supports_function_calling": true, "supports_pdf_input": true }, "writer.palmyra-x4-v1:0": { + "deprecation_date": "2027-03-09", "input_cost_per_token": 2.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -324,42 +327,52 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "supports_function_calling": true, "supports_pdf_input": true }, "writer.palmyra-x5-v1:0": { + "deprecation_date": "2027-03-21", "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "supports_function_calling": true, "supports_pdf_input": true }, "writer.palmyra-vision-7b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_vision": true }, "amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, + "output_cost_per_token_batches": 1.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -369,13 +382,19 @@ }, "amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_priority": 1.3125e-07, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -386,16 +405,21 @@ "supports_vision": true }, "amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_image_token": 1.25e-06, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.1875e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 1.75e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -406,14 +430,14 @@ "supports_vision": true }, "apac.amazon.nova-2-lite-v1:0": { - "cache_read_input_token_cost": 8.25e-08, - "input_cost_per_token": 3.3e-07, + "cache_read_input_token_cost": 9.9e-08, + "input_cost_per_token": 3.96e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 2.75e-06, + "output_cost_per_token": 3.311e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -424,16 +448,17 @@ "supports_vision": true }, "apac.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.4375e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_image_token": 1.375e-06, + "input_cost_per_audio_token": 1.375e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1.1e-05, + "source": "https://aws.amazon.com/nova/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -444,14 +469,14 @@ "supports_vision": true }, "eu.amazon.nova-2-lite-v1:0": { - "cache_read_input_token_cost": 8.25e-08, - "input_cost_per_token": 3.3e-07, + "cache_read_input_token_cost": 1.0725e-07, + "input_cost_per_token": 4.29e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 2.75e-06, + "output_cost_per_token": 3.597e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -462,16 +487,17 @@ "supports_vision": true }, "eu.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.4375e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_image_token": 1.375e-06, + "input_cost_per_audio_token": 1.375e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1.1e-05, + "source": "https://aws.amazon.com/nova/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -483,13 +509,22 @@ }, "us.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_flex": 4.125e-08, + "cache_read_input_token_cost_priority": 1.44375e-07, "input_cost_per_token": 3.3e-07, + "input_cost_per_token_batches": 1.65e-07, + "input_cost_per_token_flex": 1.65e-07, + "input_cost_per_token_priority": 5.775e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-06, + "output_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_flex": 1.375e-06, + "output_cost_per_token_priority": 4.8125e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -500,16 +535,21 @@ "supports_vision": true }, "us.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.4375e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_image_token": 1.375e-06, + "input_cost_per_audio_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.40625e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 1.925e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -539,26 +579,60 @@ "amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 8.75e-09, "input_cost_per_token": 3.5e-08, + "input_cost_per_token_batches": 1.75e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, + "output_cost_per_token_batches": 7e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, + "amazon.nova-premier-v1:0": { + "cache_read_input_token_cost": 6.25e-07, + "cache_read_input_token_cost_priority": 1.09375e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_priority": 4.375e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.25e-05, + "output_cost_per_token_batches": 6.25e-06, + "output_cost_per_token_priority": 2.1875e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 8e-07, + "input_cost_per_token_batches": 4e-07, + "input_cost_per_token_flex": 4e-07, + "input_cost_per_token_priority": 1.4e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -639,16 +713,20 @@ "mode": "image_generation" }, "amazon.titan-image-generator-v2": { + "deprecation_date": "2026-06-30", "input_cost_per_image": 0.0, "output_cost_per_image": 0.008, "litellm_provider": "bedrock", - "mode": "image_generation" + "mode": "image_generation", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-image-generator-g1-v2.html" }, "amazon.titan-image-generator-v2:0": { + "deprecation_date": "2026-06-30", "input_cost_per_image": 0.0, "output_cost_per_image": 0.008, "litellm_provider": "bedrock", - "mode": "image_generation" + "mode": "image_generation", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-image-generator-g1-v2.html" }, "twelvelabs.marengo-embed-2-7-v1:0": { "deprecation_date": "2026-11-30", @@ -738,51 +816,58 @@ "supports_image_input": true }, "twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "us.twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "eu.twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "global.twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", "supports_video_input": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md" }, "amazon.titan-text-express-v1": { - "input_cost_per_token": 1.3e-06, + "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", - "output_cost_per_token": 1.7e-06 + "output_cost_per_token": 6e-07 }, "amazon.titan-text-lite-v1": { - "input_cost_per_token": 3e-07, + "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 4e-07 + "output_cost_per_token": 2e-07 }, "amazon.titan-text-premier-v1:0": { "input_cost_per_token": 5e-07, @@ -837,7 +922,11 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-07, - "output_cost_per_token_batches": 2.5e-06 + "output_cost_per_token_batches": 2.5e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-haiku-4-5@20251001": { "cache_creation_input_token_cost": 1.25e-06, @@ -869,7 +958,7 @@ "anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", @@ -879,10 +968,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 3e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07 }, @@ -891,7 +976,7 @@ "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", @@ -903,11 +988,7 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 3e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07 + "supports_vision": true }, "anthropic.claude-3-7-sonnet-20240620-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -999,7 +1080,11 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "token_count_model": { + "model": "anthropic.claude-opus-4-1-20250805-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -1058,7 +1143,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1094,7 +1183,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1130,7 +1223,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1166,7 +1263,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1202,7 +1303,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "au.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1238,7 +1343,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1276,7 +1385,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "anthropic.claude-mythos-preview": { "cache_creation_input_token_cost": 3.4375e-05, @@ -1334,7 +1448,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1372,7 +1491,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1410,7 +1534,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "au.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1448,7 +1577,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, @@ -1480,13 +1614,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-fable-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, @@ -1557,13 +1696,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-fable-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, @@ -1634,13 +1778,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-fable-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.375e-05, @@ -1711,7 +1860,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -1793,7 +1942,12 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -1833,7 +1987,12 @@ "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -1871,7 +2030,12 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -1911,7 +2075,12 @@ "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "global.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -1949,7 +2118,12 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -1989,7 +2163,12 @@ "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -2027,7 +2206,12 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "eu.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -2105,7 +2289,12 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "au.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -2145,7 +2334,12 @@ "prompt_cache_min_tokens": 512, "thinking_always_on": true, "supports_forced_tool_use": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "jp.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -2257,12 +2451,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2296,12 +2496,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2335,12 +2541,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2374,12 +2586,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "au.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2413,12 +2631,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "jp.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2452,12 +2676,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "jp.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -2494,7 +2724,12 @@ "supports_minimal_reasoning_effort": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2528,12 +2763,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2567,12 +2808,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2606,12 +2853,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2645,12 +2898,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "au.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2684,12 +2943,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "jp.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2723,6 +2988,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -2749,7 +3015,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2763,7 +3029,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2784,7 +3054,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2798,7 +3068,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2819,7 +3093,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2833,7 +3107,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2854,7 +3132,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2868,7 +3146,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "au.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2889,7 +3171,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2903,7 +3185,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "jp.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2924,7 +3210,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2938,7 +3224,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -2950,7 +3240,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -2971,18 +3261,23 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -3009,7 +3304,11 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, "output_cost_per_token_batches": 7.5e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-v1": { "input_cost_per_token": 8e-06, @@ -3180,13 +3479,16 @@ }, "apac.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.1e-07, + "cache_read_input_token_cost_flex": 1.05e-07, "input_cost_per_token": 8.4e-07, + "input_cost_per_token_flex": 4.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.36e-06, + "output_cost_per_token_flex": 1.68e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -3219,7 +3521,11 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "apac.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -3231,7 +3537,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -3252,7 +3558,11 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "assemblyai/best": { "input_cost_per_second": 3.333e-05, @@ -3276,6 +3586,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -3302,17 +3613,21 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "azure/ada": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 1e-07, + "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/codex-mini": { "cache_read_input_token_cost": 3.75e-07, @@ -3358,7 +3673,7 @@ "supports_function_calling": true }, "azure_ai/claude-haiku-4-5": { - "deprecation_date": "2026-10-19", + "deprecation_date": "2026-11-15", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, @@ -3378,10 +3693,11 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-opus-4-5": { - "deprecation_date": "2026-10-19", + "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, @@ -3402,7 +3718,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-opus-4-6": { "deprecation_date": "2027-02-02", @@ -3588,6 +3905,7 @@ "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2027-09-18", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, @@ -3604,7 +3922,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" }, "azure_ai/claude-opus-4-8": { "deprecation_date": "2027-09-01", @@ -3640,7 +3959,7 @@ "prompt_cache_min_tokens": 1024 }, "azure_ai/claude-sonnet-4-5": { - "deprecation_date": "2026-10-19", + "deprecation_date": "2026-11-30", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, @@ -3660,7 +3979,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-sonnet-5": { "deprecation_date": "2027-06-30", @@ -3705,11 +4025,11 @@ "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -3720,7 +4040,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models" }, "azure/computer-use-preview": { "input_cost_per_token": 3e-06, @@ -3751,9 +4072,10 @@ "supports_vision": true }, "azure/container": { - "code_interpreter_cost_per_session": 0.03, + "code_interpreter_cost_per_session": 0.033, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure_ai/gpt-oss-120b": { "input_cost_per_token": 1.5e-07, @@ -3916,6 +4238,55 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure_ai/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure_ai/gpt-5.5": { "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5e-07, @@ -3927,7 +4298,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -3965,7 +4336,7 @@ }, "azure_ai/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-12-02", + "deprecation_date": "2027-05-18", "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 272000, @@ -4062,7 +4433,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4109,7 +4480,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4156,7 +4527,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4204,7 +4575,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4252,7 +4623,7 @@ "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -4298,7 +4669,7 @@ "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -4545,6 +4916,26 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/eu/gpt-4o": { + "deprecation_date": "2027-04-14", + "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/eu/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, @@ -4565,6 +4956,25 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/eu/gpt-4o-mini": { + "cache_read_input_token_cost": 8.3e-08, + "deprecation_date": "2027-04-14", + "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/eu/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", @@ -4606,6 +5016,7 @@ "azure/eu/gpt-4o-realtime-preview-2024-10-01": { "cache_creation_input_audio_token_cost": 2.2e-05, "cache_read_input_token_cost": 2.75e-06, + "deprecation_date": "2025-03-26", "input_cost_per_audio_token": 0.00011, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", @@ -4615,6 +5026,7 @@ "mode": "realtime", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 2.2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, @@ -4628,12 +5040,13 @@ "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_modalities": [ "text", "audio" @@ -4873,6 +5286,25 @@ "supports_vision": true, "cache_read_input_token_cost_batches": 2.75e-09 }, + "azure/eu/o1": { + "cache_read_input_token_cost": 8.25e-06, + "deprecation_date": "2026-11-19", + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/eu/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", @@ -4909,6 +5341,24 @@ "supports_prompt_caching": true, "supports_vision": false }, + "azure/eu/o3-mini": { + "cache_read_input_token_cost": 6.05e-07, + "deprecation_date": "2026-11-19", + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "azure/eu/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, "deprecation_date": "2026-11-19", @@ -5140,12 +5590,13 @@ "supports_tool_choice": true }, "azure/gpt-3.5-turbo-instruct-0914": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_tokens": 4097, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-35-turbo": { "input_cost_per_token": 5e-07, @@ -5184,20 +5635,22 @@ "supports_tool_choice": true }, "azure/gpt-35-turbo-instruct": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_tokens": 4097, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-35-turbo-instruct-0914": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_tokens": 4097, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-4": { "deprecation_date": "2025-06-06", @@ -5274,38 +5727,41 @@ "supports_tool_choice": true }, "azure/gpt-4-turbo": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-turbo-2024-04-09": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4-turbo-vision-preview": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_tool_choice": true, "supports_vision": true }, @@ -5692,14 +6148,14 @@ }, "azure/gpt-audio-1.5": { "deprecation_date": "2027-08-24", - "input_cost_per_audio_token": 4e-05, + "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions" @@ -5721,19 +6177,20 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-audio-1.5-2026-02-23": { "deprecation_date": "2027-08-24", - "input_cost_per_audio_token": 4e-05, + "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/chat/completions" ], @@ -5853,13 +6310,13 @@ "azure/gpt-4o-mini": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 1.65e-07, + "input_cost_per_token": 1.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6.6e-07, + "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5888,15 +6345,16 @@ "supports_vision": true }, "azure/gpt-4o-mini-audio-preview-2024-12-17": { - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 2.5e-06, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 1.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 1e-05, + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 6e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/chat/completions" ], @@ -6079,7 +6537,7 @@ "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, - "deprecation_date": "2027-07-31", + "deprecation_date": "2027-06-25", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, @@ -6090,7 +6548,7 @@ "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "supported_endpoints": [ "/v1/realtime" ], @@ -6114,7 +6572,7 @@ "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, - "deprecation_date": "2027-07-31", + "deprecation_date": "2027-06-25", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, @@ -6125,7 +6583,7 @@ "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "supported_endpoints": [ "/v1/realtime" ], @@ -6215,7 +6673,7 @@ }, "azure/gpt-4o-mini-transcribe": { "deprecation_date": "2027-06-15", - "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 16000, @@ -6228,7 +6686,7 @@ }, "azure/gpt-4o-mini-tts": { "deprecation_date": "2027-06-15", - "input_cost_per_token": 2.5e-06, + "input_cost_per_token": 6e-07, "litellm_provider": "azure", "mode": "audio_speech", "output_cost_per_audio_token": 1.2e-05, @@ -6248,6 +6706,7 @@ "azure/gpt-4o-realtime-preview-2024-10-01": { "cache_creation_input_audio_token_cost": 2e-05, "cache_read_input_token_cost": 2.5e-06, + "deprecation_date": "2025-03-26", "input_cost_per_audio_token": 0.0001, "input_cost_per_token": 5e-06, "litellm_provider": "azure", @@ -6257,6 +6716,7 @@ "mode": "realtime", "output_cost_per_audio_token": 0.0002, "output_cost_per_token": 2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, @@ -6269,12 +6729,13 @@ "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_modalities": [ "text", "audio" @@ -6291,27 +6752,29 @@ "supports_tool_choice": true }, "azure/gpt-4o-transcribe": { - "deprecation_date": "2026-12-31", - "input_cost_per_audio_token": 2.5e-06, + "deprecation_date": "2026-10-15", + "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "azure/gpt-4o-transcribe-diarize": { "deprecation_date": "2027-04-15", - "input_cost_per_audio_token": 2.5e-06, + "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/audio/transcriptions" ] @@ -6320,6 +6783,9 @@ "deprecation_date": "2027-05-06", "input_cost_per_second": 0.0002833333333333333, "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "audio_transcription", "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", "supported_endpoints": [ @@ -7374,7 +7840,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7430,7 +7896,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7480,7 +7946,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7530,7 +7996,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7586,7 +8052,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7636,7 +8102,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7687,7 +8153,7 @@ "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -7736,7 +8202,7 @@ "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -8413,11 +8879,17 @@ "azure/gpt-6-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_priority": 4e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_priority": 4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -8425,11 +8897,9 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -8462,11 +8932,17 @@ "azure/gpt-6-sol-2026-09-22": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_priority": 4e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_priority": 4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -8474,11 +8950,9 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -8508,9 +8982,254 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6.1-sol-2026-09-29": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/us/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/eu/gpt-6.1-sol": { + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2.4e-06, + "input_cost_per_token_above_272k_tokens": 4.8e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/apac/gpt-6.1-sol": { + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2.4e-06, + "input_cost_per_token_above_272k_tokens": 4.8e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-12-02", + "deprecation_date": "2027-05-18", "input_cost_per_token": 5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -8906,10 +9625,16 @@ "deprecation_date": "2028-03-11", "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05, + "cache_creation_input_token_cost_priority": 5.5e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07, + "cache_read_input_token_cost_priority": 4.4e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8.8e-06, + "input_cost_per_token_priority": 4.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -8917,11 +9642,9 @@ "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token_above_272k_tokens_priority": 3.3e-05, + "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -8953,7 +9676,7 @@ }, "azure/us/gpt-chat-latest": { "cache_read_input_token_cost": 5.5e-07, - "deprecation_date": "2026-12-02", + "deprecation_date": "2027-05-18", "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -9228,7 +9951,7 @@ "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9287,7 +10010,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9342,7 +10065,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9394,7 +10117,7 @@ "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9454,7 +10177,7 @@ "input_cost_per_token_above_272k_tokens_priority": 2e-05, "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9513,7 +10236,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9566,7 +10289,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9620,7 +10343,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9673,7 +10396,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -10001,6 +10724,7 @@ "cache_read_input_token_cost_batches": 1e-08 }, "azure/gpt-image-1": { + "cache_read_input_image_token_cost": 2.5e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-10-23", "input_cost_per_image_token": 1e-05, @@ -10008,28 +10732,32 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 4e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/hd/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 7.629e-08, + "input_cost_per_pixel": 8.39233e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/hd/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, + "input_cost_per_pixel": 7.19343e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/hd/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, + "input_cost_per_pixel": 7.19343e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/high/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", @@ -10122,6 +10850,7 @@ ] }, "azure/gpt-image-1-mini": { + "cache_read_input_image_token_cost": 2.5e-07, "cache_read_input_token_cost": 2e-07, "deprecation_date": "2027-04-07", "input_cost_per_image_token": 2.5e-06, @@ -10129,12 +10858,14 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 8e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-1.5": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2026-12-16", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10142,12 +10873,15 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, + "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-1.5-2025-12-16": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-12-16", "input_cost_per_token": 5e-06, @@ -10155,12 +10889,15 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, + "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-2": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-10-21", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10168,6 +10905,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10176,6 +10914,7 @@ "supports_pdf_input": true }, "azure/gpt-image-2.5-flare": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10183,6 +10922,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10191,6 +10931,7 @@ "supports_pdf_input": true }, "azure/gpt-image-2.5-sunburst": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10198,6 +10939,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10206,6 +10948,7 @@ "supports_pdf_input": true }, "azure/gpt-image-2-2026-04-21": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", "input_cost_per_token": 5e-06, @@ -10213,6 +10956,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10481,7 +11225,6 @@ }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -10550,7 +11293,6 @@ "output_cost_per_token_batches": 4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -10582,7 +11324,6 @@ "output_cost_per_token_batches": 4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -10659,52 +11400,55 @@ "output_cost_per_token": 0.0 }, "azure/standard/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 3.81469e-08, + "input_cost_per_pixel": 4.19617e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/standard/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, + "input_cost_per_pixel": 4.79562e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/standard/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, + "input_cost_per_pixel": 4.79562e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-3-large": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 1.3e-07, + "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", - "max_input_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 8192, + "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-3-small": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 2e-08, + "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", - "max_input_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 8192, + "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-ada-002": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 1e-07, + "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", - "max_input_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 8192, + "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/speech/azure-tts": { "input_cost_per_character": 1.5e-05, @@ -10737,9 +11481,10 @@ }, "azure/tts-1-hd": { "deprecation_date": "2026-12-15", - "input_cost_per_character": 3e-05, + "input_cost_per_character": 3.3e-05, "litellm_provider": "azure", - "mode": "audio_speech" + "mode": "audio_speech", + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/us/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", @@ -10871,6 +11616,26 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/gpt-4o": { + "deprecation_date": "2027-04-14", + "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, @@ -10891,6 +11656,25 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/gpt-4o-mini": { + "cache_read_input_token_cost": 8.3e-08, + "deprecation_date": "2027-04-14", + "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", @@ -10932,6 +11716,7 @@ "azure/us/gpt-4o-realtime-preview-2024-10-01": { "cache_creation_input_audio_token_cost": 2.2e-05, "cache_read_input_token_cost": 2.75e-06, + "deprecation_date": "2025-03-26", "input_cost_per_audio_token": 0.00011, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", @@ -10941,6 +11726,7 @@ "mode": "realtime", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 2.2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, @@ -10954,12 +11740,13 @@ "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_modalities": [ "text", "audio" @@ -11199,6 +11986,25 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/o1": { + "cache_read_input_token_cost": 8.25e-06, + "deprecation_date": "2026-11-19", + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", @@ -11235,6 +12041,39 @@ "supports_prompt_caching": true, "supports_vision": false }, + "azure/us/o3": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/o3-2025-04-16": { "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, @@ -11268,6 +12107,24 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/o3-mini": { + "cache_read_input_token_cost": 6.05e-07, + "deprecation_date": "2026-11-19", + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "azure/us/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, "deprecation_date": "2026-11-19", @@ -11286,6 +12143,27 @@ "supports_tool_choice": true, "supports_vision": false }, + "azure/us/o4-mini": { + "cache_read_input_token_cost": 3.03e-07, + "deprecation_date": "2026-11-19", + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/o4-mini-2025-04-16": { "cache_read_input_token_cost": 3.03e-07, "deprecation_date": "2026-11-19", @@ -11358,6 +12236,8 @@ }, "azure_ai/FLUX-1.1-pro": { "litellm_provider": "azure_ai", + "max_input_tokens": 5000, + "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", @@ -11367,18 +12247,22 @@ }, "azure_ai/FLUX.1-Kontext-pro": { "litellm_provider": "azure_ai", + "max_input_tokens": 5000, + "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, - "source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", "supported_endpoints": [ "/v1/images/generations" ] }, "azure_ai/flux.2-pro": { "litellm_provider": "azure_ai", + "max_input_tokens": 32000, + "max_tokens": 32000, "mode": "image_generation", "output_cost_per_image": 0.04, - "source": "https://ai.azure.com/explore/models/flux.2-pro/version/1/registry/azureml-blackforestlabs", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_endpoints": [ "/v1/images/generations" ] @@ -11699,34 +12583,37 @@ "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", "mode": "image_generation", - "output_cost_per_image": 0.05, + "output_cost_per_image": 0.048, "output_cost_per_image_token": 4.7e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], - "deprecation_date": "2026-10-01" + "deprecation_date": "2026-10-01", + "max_input_tokens": 32000 }, "azure_ai/MAI-Image-2.5-Flash": { "input_cost_per_image_token": 1.75e-06, "input_cost_per_token": 1.75e-06, "litellm_provider": "azure_ai", "mode": "image_generation", - "output_cost_per_image": 0.0338, - "output_cost_per_image_token": 3.3e-05, + "output_cost_per_image": 0.02, + "output_cost_per_image_token": 1.95e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], - "deprecation_date": "2026-10-01" + "deprecation_date": "2026-10-01", + "max_input_tokens": 32000 }, "azure_ai/MAI-Image-2.5-Pro": { "deprecation_date": "2026-10-01", "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", + "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image": 0.1085, "output_cost_per_image_token": 0.000106, @@ -11764,11 +12651,11 @@ "input_cost_per_token": 7.1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.1e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_tool_choice": true }, @@ -11776,8 +12663,8 @@ "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11799,6 +12686,7 @@ "supports_vision": true }, "azure_ai/Meta-Llama-3-70B-Instruct": { + "deprecation_date": "2025-06-30", "input_cost_per_token": 1.1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 8192, @@ -11806,9 +12694,11 @@ "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.7e-07, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true }, "azure_ai/Meta-Llama-3.1-70B-Instruct": { + "deprecation_date": "2025-06-30", "input_cost_per_token": 2.68e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11816,10 +12706,11 @@ "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.54e-06, - "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true }, "azure_ai/Phi-3-medium-128k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.7e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11827,11 +12718,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-medium-4k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.7e-07, "litellm_provider": "azure_ai", "max_input_tokens": 4096, @@ -11839,11 +12731,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-mini-128k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11851,11 +12744,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-mini-4k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 4096, @@ -11863,11 +12757,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-small-128k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11875,11 +12770,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-small-8k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 8192, @@ -11887,11 +12783,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3.5-MoE-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11899,11 +12796,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.4e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3.5-mini-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11911,11 +12809,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3.5-vision-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11923,7 +12822,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": true }, @@ -12058,6 +12957,7 @@ "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/" }, "azure_ai/MAI-DS-R1": { + "deprecation_date": "2026-02-27", "input_cost_per_token": 1.35e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12065,11 +12965,12 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/cohere-rerank-v3-english": { + "deprecation_date": "2025-06-30", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -12077,9 +12978,11 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "rerank", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" }, "azure_ai/cohere-rerank-v3-multilingual": { + "deprecation_date": "2025-06-30", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -12087,7 +12990,8 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "rerank", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" }, "azure_ai/cohere-rerank-v4.0-pro": { "input_cost_per_query": 0.0025, @@ -12114,12 +13018,12 @@ "azure_ai/deepseek-v3.2": { "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -12129,12 +13033,12 @@ "azure_ai/deepseek-v3.2-speciale": { "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -12142,6 +13046,7 @@ "supports_tool_choice": true }, "azure_ai/deepseek-v3": { + "deprecation_date": "2025-08-31", "input_cost_per_token": 1.14e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12149,7 +13054,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true }, "azure_ai/deepseek-v4-pro": { @@ -12190,11 +13095,11 @@ "input_cost_per_token": 4.4e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 384000, + "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -12216,17 +13121,18 @@ "text", "image" ], - "supports_embedding_image_input": true + "supports_embedding_image_input": true, + "input_cost_per_image_token": 4.7e-07 }, "azure_ai/grok-4": { "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 262000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -12239,12 +13145,12 @@ "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, - "max_output_tokens": 200000, - "max_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -12265,7 +13171,7 @@ "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -12315,9 +13221,9 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, @@ -12329,9 +13235,9 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, @@ -12343,18 +13249,19 @@ "azure_ai/grok-code-fast-1": { "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/jais-30b-chat": { + "deprecation_date": "2026-01-30", "input_cost_per_token": 0.0032, "litellm_provider": "azure_ai", "max_input_tokens": 8192, @@ -12362,9 +13269,10 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00971, - "source": "https://ai.azure.com/catalog/models/jais-30b-chat" + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" }, "azure_ai/jamba-instruct": { + "deprecation_date": "2025-03-01", "input_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 70000, @@ -12372,6 +13280,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true }, "azure_ai/kimi-k2.5": { @@ -12416,6 +13325,7 @@ "supports_prompt_caching": true }, "azure_ai/ministral-3b": { + "deprecation_date": "2026-12-09", "input_cost_per_token": 4e-08, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12428,6 +13338,7 @@ "supports_tool_choice": true }, "azure_ai/mistral-large": { + "deprecation_date": "2025-04-15", "input_cost_per_token": 4e-06, "litellm_provider": "azure_ai", "max_input_tokens": 32000, @@ -12435,10 +13346,12 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/mistral-large-2407": { + "deprecation_date": "2025-05-13", "input_cost_per_token": 2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12446,7 +13359,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true, "supports_tool_choice": true }, @@ -12476,6 +13389,7 @@ "supports_vision": true }, "azure_ai/mistral-medium-2505": { + "deprecation_date": "2026-12-09", "input_cost_per_token": 4e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, @@ -12488,6 +13402,7 @@ "supports_tool_choice": true }, "azure_ai/mistral-nemo": { + "deprecation_date": "2026-01-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, @@ -12495,10 +13410,11 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true }, "azure_ai/mistral-small": { + "deprecation_date": "2025-07-31", "input_cost_per_token": 1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 32000, @@ -12506,10 +13422,12 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/mistral-small-2503": { + "deprecation_date": "2026-12-09", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12535,43 +13453,43 @@ "source": "https://developers.openai.com/api/docs/pricing" }, "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { + "cost_per_second": 0.001902, "input_cost_per_second": 0.001902, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_second": 0.001902, "supports_tool_choice": true }, "bedrock/*/1-month-commitment/cohere.command-text-v14": { + "cost_per_second": 0.011, "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_second": 0.011, "supports_tool_choice": true }, "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { + "cost_per_second": 0.0011416, "input_cost_per_second": 0.0011416, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_second": 0.0011416, "supports_tool_choice": true }, "bedrock/*/6-month-commitment/cohere.command-text-v14": { + "cost_per_second": 0.0066027, "input_cost_per_second": 0.0066027, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_second": 0.0066027, "supports_tool_choice": true }, "bedrock/guardrails": { @@ -12590,61 +13508,61 @@ "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.01475, "input_cost_per_second": 0.01475, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.01475, "supports_tool_choice": true }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.0455, "input_cost_per_second": 0.0455, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.0455 + "mode": "chat" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.0455, "input_cost_per_second": 0.0455, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.0455, "supports_tool_choice": true }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.008194, "input_cost_per_second": 0.008194, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.008194, "supports_tool_choice": true }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.02527, "input_cost_per_second": 0.02527, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.02527 + "mode": "chat" }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.02527, "input_cost_per_second": 0.02527, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.02527, "supports_tool_choice": true }, "bedrock/ap-northeast-1/anthropic.claude-instant-v1": { @@ -12679,12 +13597,14 @@ }, "bedrock/ap-northeast-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -12692,32 +13612,36 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/ap-northeast-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/ap-northeast-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -12725,71 +13649,86 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.3e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.03e-06, + "output_cost_per_token_flex": 1.52e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/ap-northeast-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_flex": 1.8e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/ap-northeast-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/moonshotai.kimi-k2-thinking": { - "input_cost_per_token": 7.3e-07, + "deprecation_date": "2027-03-30", + "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", - "output_cost_per_token": 3.03e-06, + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", - "output_cost_per_token": 3.03e-06, - "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", + "output_cost_per_token": 3e-06, + "output_cost_per_token_flex": 1.5e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -12800,31 +13739,37 @@ "supports_response_schema": true }, "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.18e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4.2e-06 + "output_cost_per_token": 4.2e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.2e-07 + "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/ap-south-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -12832,32 +13777,36 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/ap-south-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/ap-south-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -12865,59 +13814,69 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/ap-south-1/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.1e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.94e-06, + "output_cost_per_token_flex": 1.47e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/ap-south-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_flex": 1.8e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/ap-south-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/ap-southeast-2/minimax.minimax-m2.5": { - "input_cost_per_token": 3.09e-07, + "input_cost_per_token": 3.1e-07, + "input_cost_per_token_flex": 1.55e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -12925,16 +13884,19 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.236e-06 + "output_cost_per_token": 1.24e-06, + "output_cost_per_token_flex": 6.2e-07 }, "bedrock/ap-southeast-3/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -12942,32 +13904,36 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/ap-southeast-3/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/ap-southeast-3/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -12975,66 +13941,77 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/ap-southeast-3/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_flex": 1.8e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/ap-southeast-3/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4.03e-06 + "output_cost_per_token": 4.03e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6.9e-07 + "output_cost_per_token": 6.9e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-north-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13042,32 +14019,36 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/eu-north-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/eu-north-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13075,80 +14056,83 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/eu-north-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_flex": 1.8e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.01635, "input_cost_per_second": 0.01635, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.01635, "supports_tool_choice": true }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.0415, "input_cost_per_second": 0.0415, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.0415 + "mode": "chat" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.0415, "input_cost_per_second": 0.0415, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.0415, "supports_tool_choice": true }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.009083, "input_cost_per_second": 0.009083, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.009083, "supports_tool_choice": true }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.02305, "input_cost_per_second": 0.02305, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.02305 + "mode": "chat" }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.02305, "input_cost_per_second": 0.02305, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.02305, "supports_tool_choice": true }, "bedrock/eu-central-1/anthropic.claude-instant-v1": { @@ -13181,29 +14165,33 @@ "supports_tool_choice": true }, "bedrock/eu-central-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/eu-central-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13211,66 +14199,77 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/eu-central-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.86e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.78e-06 + "output_cost_per_token": 3.78e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6.5e-07 + "output_cost_per_token": 6.5e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-west-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/eu-west-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13278,66 +14277,77 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/eu-west-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.45e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4.55e-06 + "output_cost_per_token": 4.55e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.8e-07 + "output_cost_per_token": 7.8e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-west-2/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.7e-07, + "input_cost_per_token_flex": 2.35e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.86e-06, + "output_cost_per_token_flex": 9.3e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/eu-west-2/minimax.minimax-m2.5": { "input_cost_per_token": 4.7e-07, + "input_cost_per_token_flex": 2.35e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13345,16 +14355,19 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.86e-06 + "output_cost_per_token": 1.86e-06, + "output_cost_per_token_flex": 9.3e-07 }, "bedrock/eu-west-2/nvidia.nemotron-super-3-120b": { "input_cost_per_token": 2.3e-07, + "input_cost_per_token_flex": 1.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.01e-06, + "output_cost_per_token_flex": 5.05e-07, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_audio_input": false, "supports_function_calling": true, @@ -13366,75 +14379,85 @@ }, "bedrock/eu-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 7.8e-07, + "input_cost_per_token_flex": 3.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.86e-06, + "output_cost_per_token_flex": 9.3e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 5.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.56e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 5.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9.1e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "bedrock/eu-south-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/eu-south-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13442,23 +14465,26 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/eu-south-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -13479,31 +14505,37 @@ "cache_creation_input_token_cost": 3.75e-06 }, "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.45e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 5.88e-06 + "output_cost_per_token": 5.88e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.01e-06 + "output_cost_per_token": 1.01e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/sa-east-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13511,32 +14543,36 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/sa-east-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/sa-east-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13544,107 +14580,116 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/sa-east-1/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.3e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.03e-06, + "output_cost_per_token_flex": 1.52e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/sa-east-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_flex": 1.8e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/sa-east-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.011, "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.011, "supports_tool_choice": true }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.0175 + "mode": "chat" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.0175, "supports_tool_choice": true }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.00611, "input_cost_per_second": 0.00611, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.00611, "supports_tool_choice": true }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.00972 + "mode": "chat" }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.00972, "supports_tool_choice": true }, "bedrock/us-east-1/anthropic.claude-instant-v1": { @@ -13678,62 +14723,72 @@ "supports_tool_choice": true }, "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.5e-06 + "output_cost_per_token": 3.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-07 + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-east-1/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_flex": 3.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_flex": 9.25e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13741,29 +14796,34 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/us-east-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, + "input_cost_per_token_flex": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/us-east-1/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_flex": 1.5e-07, "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", @@ -13773,59 +14833,69 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" }, "bedrock/us-east-1/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/us-east-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_flex": 1.5e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/us-east-1/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_flex": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/us-east-2/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_flex": 3.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_flex": 9.25e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13833,32 +14903,36 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/us-east-2/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, + "input_cost_per_token_flex": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/us-east-2/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_flex": 1.5e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13866,50 +14940,59 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.2e-06 + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07 }, "bedrock/us-east-2/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/us-east-2/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_flex": 1.5e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/us-east-2/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_flex": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.4e-07, @@ -13995,7 +15078,11 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -14114,7 +15201,7 @@ "output_vector_size": 1536 }, "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": { - "input_cost_per_token": 2e-07, + "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, @@ -14123,13 +15210,13 @@ "output_vector_size": 1024 }, "bedrock/us-gov-west-1/amazon.titan-text-express-v1": { - "input_cost_per_token": 1.3e-06, + "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", - "output_cost_per_token": 1.7e-06 + "output_cost_per_token": 1.6e-06 }, "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": { "input_cost_per_token": 3e-07, @@ -14172,7 +15259,11 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -14220,79 +15311,83 @@ "supports_pdf_input": true }, "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.5e-06 + "output_cost_per_token": 3.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-07 + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.011, "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.011, "supports_tool_choice": true }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.0175 + "mode": "chat" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.0175, "supports_tool_choice": true }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.00611, "input_cost_per_second": 0.00611, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.00611, "supports_tool_choice": true }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.00972 + "mode": "chat" }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.00972, "supports_tool_choice": true }, "bedrock/us-west-2/anthropic.claude-instant-v1": { @@ -14326,44 +15421,50 @@ "supports_tool_choice": true }, "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-west-2/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_flex": 3.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_flex": 9.25e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -14371,29 +15472,34 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/us-west-2/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, + "input_cost_per_token_flex": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/us-west-2/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_flex": 1.5e-07, "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", @@ -14403,50 +15509,58 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" }, "bedrock/us-west-2/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/us-west-2/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_flex": 1.5e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/us-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_flex": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": { "cache_creation_input_token_cost": 1e-06, @@ -14642,6 +15756,7 @@ "source": "https://developers.openai.com/api/docs/pricing" }, "claude-haiku-4-5-20251001": { + "supports_web_search": true, "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_creation_input_token_cost_batches": 6.25e-07, @@ -14699,18 +15814,14 @@ "claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_creation_input_token_cost_batches": 1.875e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, "cache_read_input_token_cost_batches": 1.5e-07, + "deprecation_date": "2026-11-30", "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -14737,18 +15848,14 @@ "claude-sonnet-4-5-20250929": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_creation_input_token_cost_batches": 1.875e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, "cache_read_input_token_cost_batches": 1.5e-07, + "deprecation_date": "2026-11-30", "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -14774,6 +15881,7 @@ "source": "https://docs.anthropic.com/en/docs/about-claude/pricing" }, "claude-sonnet-5": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, @@ -14817,7 +15925,54 @@ "prompt_cache_min_tokens": 1024, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, + "claude-sonnet-5-5": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_web_search": true + }, "claude-sonnet-4-6": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, @@ -14840,7 +15995,7 @@ }, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -14891,6 +16046,7 @@ "output_cost_per_token_batches": 7.5e-06 }, "claude-opus-4-5-20251101": { + "supports_web_search": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, @@ -14960,6 +16116,7 @@ "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-6": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -15045,6 +16202,7 @@ "prompt_cache_min_tokens": 4096 }, "claude-opus-4-7": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -15132,6 +16290,7 @@ "prompt_cache_min_tokens": 2048 }, "claude-fable-5": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, @@ -15176,6 +16335,7 @@ "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-fable-5-1": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, @@ -15221,6 +16381,7 @@ "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-5-5": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, @@ -15258,9 +16419,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "provider_specific_entry": { - "fast": 2.0 - }, + "provider_specific_entry": {"us":1.1,"fast":2}, "supports_output_config": true, "supports_speed": true, "supports_fast_mode": true, @@ -15268,6 +16427,7 @@ "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-5": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -15315,6 +16475,7 @@ "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-8": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -15361,6 +16522,82 @@ "prompt_cache_min_tokens": 1024, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, + "cloudflare/clef-omni": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 64000, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/", + "supports_audio_input": true, + "supports_video_input": true, + "supports_vision": true + }, + "cloudflare/@cf/cloudflare/clef-omni": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 64000, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/", + "supports_audio_input": true, + "supports_video_input": true, + "supports_vision": true + }, + "cloudflare/clef": { + "input_cost_per_token": 2.4e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true + }, + "cloudflare/clef-flash": { + "input_cost_per_token": 9e-08, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true + }, + "cloudflare/@cf/cloudflare/clef": { + "input_cost_per_token": 2.4e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true + }, + "cloudflare/@cf/cloudflare/clef-flash": { + "input_cost_per_token": 9e-08, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true + }, + "cloudflare/clairic": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "extraction", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clairic/", + "supports_vision": true + }, + "cloudflare/@cf/cloudflare/clairic": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "extraction", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clairic/", + "supports_vision": true + }, "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", @@ -15796,7 +17033,31 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, - "supports_embedding_image_input": true + "supports_embedding_image_input": true, + "input_cost_per_image_token": 4.7e-07, + "source": "https://cohere.com/pricing" + }, + "cohere/embed-v5.0-pro": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "cohere", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048, + "supports_embedding_image_input": true, + "source": "https://cohere.com/pricing" + }, + "cohere/embed-v5.0-fast": { + "input_cost_per_token": 8e-08, + "litellm_provider": "cohere", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048, + "supports_embedding_image_input": true, + "source": "https://cohere.com/pricing" }, "cohere/parse-v5.0": { "litellm_provider": "cohere", @@ -15811,11 +17072,12 @@ "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "bedrock", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "rerank", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-cohere-rerank-3-5.md" }, "command-a-03-2025": { "input_cost_per_token": 2.5e-06, @@ -15896,6 +17158,144 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "coralbricks/glm-5.3-fast": { + "cache_creation_input_token_cost": 1.68e-06, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1.12e-06, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "coralbricks/glm-5.3-fp4": { + "cache_creation_input_token_cost": 1.68e-06, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1.12e-06, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "coralbricks/glm-5.3": { + "cache_creation_input_token_cost": 1.68e-06, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1.12e-06, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "coralbricks/deepseek-v4.1-flash-fast": { + "cache_creation_input_token_cost": 9e-08, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1e-08, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "coralbricks/deepseek-v4.1-flash-fast-fp4": { + "cache_creation_input_token_cost": 9e-08, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1e-08, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "coralbricks/deepseek-v4.1-flash": { + "cache_creation_input_token_cost": 9e-08, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1e-08, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "computer-use-preview": { "deprecation_date": "2026-07-23", "input_cost_per_token": 3e-06, @@ -15926,8 +17326,39 @@ "supports_vision": true, "source": "https://platform.openai.com/docs/models/computer-use-preview" }, + "computer-use-preview-2025-03-11": { + "deprecation_date": "2026-07-23", + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://developers.openai.com/api/docs/models/computer-use-preview" + }, "deepseek-chat": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, @@ -15949,6 +17380,7 @@ }, "deepseek-reasoner": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, @@ -16810,7 +18242,9 @@ ] }, "dashscope/qwen3.7-max": { + "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "dashscope", "max_input_tokens": 991808, @@ -16961,6 +18395,281 @@ "/v1/images/generations" ] }, + "dashscope/wan3.0-video": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", + "output_cost_per_second": 0.165025, + "output_cost_per_second_480p": 0.041256, + "output_cost_per_second_720p": 0.082513, + "output_cost_per_second_1080p": 0.165025, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan3.0-video-prime": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", + "output_cost_per_second": 0.254399, + "output_cost_per_second_480p": 0.0636, + "output_cost_per_second_720p": 0.127199, + "output_cost_per_second_1080p": 0.254399, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.1-t2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.1-i2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.1-r2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.0-t2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.0-i2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.0-r2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan2.7-t2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan2.7-i2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan2.7-r2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, "qwencloud/deepseek-v4-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, @@ -17802,7 +19511,9 @@ ] }, "qwencloud/qwen3.7-max": { + "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "qwencloud", "max_input_tokens": 991808, @@ -17913,6 +19624,281 @@ "/v1/images/generations" ] }, + "qwencloud/wan3.0-video": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", + "output_cost_per_second": 0.2, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.2, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan3.0-video-prime": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", + "output_cost_per_second": 0.28, + "output_cost_per_second_480p": 0.068, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.28, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.1-t2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", + "output_cost_per_second": 0.18, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.18, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 text-to-video. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.1-i2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", + "output_cost_per_second": 0.18, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.18, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 image-to-video from a first frame. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.1-r2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", + "output_cost_per_second": 0.18, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.18, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.0-t2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", + "output_cost_per_second": 0.24, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.24, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.0-i2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", + "output_cost_per_second": 0.24, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.24, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.0-r2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", + "output_cost_per_second": 0.24, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.24, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan2.7-t2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", + "output_cost_per_second": 0.15, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.15, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan2.7-i2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", + "output_cost_per_second": 0.15, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.15, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan2.7-r2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", + "output_cost_per_second": 0.15, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.15, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "Wan 2.7 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, "qwen_ai_platform/deepseek-v4-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, @@ -18754,7 +20740,9 @@ ] }, "qwen_ai_platform/qwen3.7-max": { + "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, @@ -18905,6 +20893,281 @@ "/v1/images/generations" ] }, + "qwen_ai_platform/wan3.0-video": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", + "output_cost_per_second": 0.165025, + "output_cost_per_second_480p": 0.041256, + "output_cost_per_second_720p": 0.082513, + "output_cost_per_second_1080p": 0.165025, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan3.0-video-prime": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", + "output_cost_per_second": 0.254399, + "output_cost_per_second_480p": 0.0636, + "output_cost_per_second_720p": 0.127199, + "output_cost_per_second_1080p": 0.254399, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.1-t2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.1-i2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.1-r2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.0-t2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.0-i2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.0-r2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan2.7-t2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan2.7-i2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan2.7-r2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, "databricks/databricks-bge-large-en": { "cache_creation_input_token_cost": 1.0003e-07, "cache_read_input_token_cost": 1.0003e-07, @@ -19094,7 +21357,7 @@ "output_cost_per_token": 2.5000010000000002e-05, "output_dbu_cost_per_token": 0.000357143, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, "supports_legacy_thinking": true, "supports_prompt_caching": true, @@ -19186,6 +21449,41 @@ "supports_tool_choice": true, "supports_vision": true }, + "databricks/databricks-claude-opus-5-5": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_creation_input_token_cost_above_1hr": 8.00002e-06, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_token": 4.00001e-06, + "input_dbu_cost_per_token": 5.7143e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.999998e-05, + "output_dbu_cost_per_token": 0.000285714, + "prompt_cache_min_tokens": 512, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_anthropic_thinking_payload": true, + "supports_assistant_prefill": false, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_output_config": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, "databricks/databricks-claude-sonnet-4": { "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, @@ -19274,7 +21572,7 @@ "output_cost_per_token": 1.5000020000000002e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, "supports_legacy_thinking": true, "supports_prompt_caching": true, @@ -19317,6 +21615,7 @@ "input_cost_per_token": 1.4e-07, "input_dbu_cost_per_token": 2e-06, "litellm_provider": "databricks", + "token_count_framing": 97, "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, @@ -19337,8 +21636,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false, - "token_count_framing": 97 + "supports_vision": false }, "databricks/system.ai.deepseek-v4-flash-0731": { "litellm_provider": "databricks", @@ -19623,6 +21921,7 @@ ], "supports_function_calling": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, @@ -19647,6 +21946,7 @@ ], "supports_function_calling": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, @@ -19678,6 +21978,7 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, @@ -19741,6 +22042,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, @@ -20313,6 +22615,7 @@ "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", + "token_count_framing": 100, "max_input_tokens": 1000000, "max_output_tokens": 1048576, "max_tokens": 1048576, @@ -20334,8 +22637,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true, - "token_count_framing": 100 + "supports_vision": true }, "databricks/system.ai.kimi-k3": { "litellm_provider": "databricks", @@ -20463,6 +22765,30 @@ "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, + "databricks/databricks-openjev-qwen35-4b": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 0.0, + "litellm_provider": "databricks", + "metadata": { + "notes": "Pay-per-token Foundation Model API decision endpoint (OpenJev, Qwen 3.5 4B) queried through the System One API. Databricks published no DBU rate for it as of 2026-10-07, so a deployment's model_info prices set the billed cost." + }, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models" + }, + "databricks/ai_decide": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 0.0, + "litellm_provider": "databricks", + "metadata": { + "notes": "The ai_decide AI Function (Beta), called through POST /api/2.0/ai-functions/ai-decide. Its response carries no token usage, so LiteLLM records no spend for it." + }, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.databricks.com/api/ai-functions/v1/ai-decide" + }, "dataforseo/search": { "input_cost_per_query": 0.003, "litellm_provider": "dataforseo", @@ -21844,6 +24170,7 @@ "deepseek/deepseek-chat": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", @@ -21898,6 +24225,7 @@ }, "deepseek/deepseek-reasoner": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", @@ -21953,14 +24281,15 @@ "supports_tool_choice": true }, "deepseek.v3-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 5.8e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 163840, - "max_output_tokens": 81920, - "max_tokens": 81920, + "max_input_tokens": 128000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -21968,17 +24297,23 @@ }, "deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, + "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 164000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, + "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -22198,6 +24533,265 @@ "litellm_provider": "perplexity", "mode": "search" }, + "sail/moonshotai/Kimi-K3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.25e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token_balanced": 2e-06, + "output_cost_per_token_balanced": 1e-05, + "cache_read_input_token_cost_balanced": 2e-07, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_flex": 6.25e-06, + "cache_read_input_token_cost_flex": 1.5e-07, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/zai-org/GLM-5.3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 9.8e-07, + "output_cost_per_token": 3.08e-06, + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token_balanced": 5e-07, + "output_cost_per_token_balanced": 2.5e-06, + "cache_read_input_token_cost_balanced": 1.2e-07, + "input_cost_per_token_flex": 4e-07, + "output_cost_per_token_flex": 1.8e-06, + "cache_read_input_token_cost_flex": 8e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/zai-org/GLM-5.3-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.1e-07, + "output_cost_per_token": 3.5e-07, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_balanced": 8e-08, + "output_cost_per_token_balanced": 2.8e-07, + "cache_read_input_token_cost_balanced": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1.8e-07, + "cache_read_input_token_cost_flex": 1e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/deepseek-ai/DeepSeek-V4-Pro-0813": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 9.2e-07, + "output_cost_per_token": 2.77e-06, + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token_balanced": 7.4e-07, + "output_cost_per_token_balanced": 2.22e-06, + "cache_read_input_token_cost_balanced": 3e-08, + "input_cost_per_token_flex": 4.6e-07, + "output_cost_per_token_flex": 1.39e-06, + "cache_read_input_token_cost_flex": 2e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_balanced": 7e-08, + "output_cost_per_token_balanced": 1.4e-07, + "cache_read_input_token_cost_balanced": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 9e-08, + "cache_read_input_token_cost_flex": 1e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/deepseek-ai/DeepSeek-V4.1-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token_balanced": 7e-08, + "output_cost_per_token_balanced": 2.2e-07, + "cache_read_input_token_cost_balanced": 5e-09, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1.5e-07, + "cache_read_input_token_cost_flex": 4e-09, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/moonshotai/Kimi-K2.6": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_balanced": 4.5e-07, + "output_cost_per_token_balanced": 3e-06, + "cache_read_input_token_cost_balanced": 2e-07, + "input_cost_per_token_flex": 3.5e-07, + "output_cost_per_token_flex": 2e-06, + "cache_read_input_token_cost_flex": 1e-07, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/google/gemma-4-31B-it": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_balanced": 1.2e-07, + "output_cost_per_token_balanced": 6e-07, + "cache_read_input_token_cost_balanced": 8e-08, + "input_cost_per_token_flex": 6e-08, + "output_cost_per_token_flex": 3e-07, + "cache_read_input_token_cost_flex": 2e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/nvidia/Gemma-4-31B-IT-NVFP4": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token_balanced": 1.1e-07, + "output_cost_per_token_balanced": 3.2e-07, + "cache_read_input_token_cost_balanced": 6e-08, + "input_cost_per_token_flex": 7e-08, + "output_cost_per_token_flex": 2e-07, + "cache_read_input_token_cost_flex": 4e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/google/gemma-4-12B-it": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token_balanced": 1e-07, + "output_cost_per_token_balanced": 2e-06, + "cache_read_input_token_cost_balanced": 7e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1e-06, + "cache_read_input_token_cost_flex": 2e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/openai/gpt-oss-120b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/Qwen/Qwen3.6-35B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 4e-07, + "cache_read_input_token_cost_flex": 2e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://docs.sailresearch.com/models" + }, "searxng/search": { "litellm_provider": "searxng", "mode": "search", @@ -22231,7 +24825,7 @@ } }, "agentcore/search": { - "input_cost_per_query": 0.0, + "input_cost_per_query": 0.007, "litellm_provider": "agentcore", "mode": "search", "metadata": { @@ -22246,6 +24840,11 @@ "notes": "Grounding with Bing Search (G1 SKU): $14 per 1,000 transactions. Tokens for the Foundry model deployment that runs the grounded search are billed separately on that deployment." } }, + "deepseek/search": { + "input_cost_per_query": 0.00075, + "litellm_provider": "deepseek", + "mode": "search" + }, "tinyfish/search": { "input_cost_per_query": 0.0, "litellm_provider": "tinyfish", @@ -22390,13 +24989,16 @@ }, "eu.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.625e-07, + "cache_read_input_token_cost_flex": 1.3125e-07, "input_cost_per_token": 1.05e-06, + "input_cost_per_token_flex": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 4.2e-06, + "output_cost_per_token_flex": 2.1e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_pdf_input": true, @@ -22450,7 +25052,11 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -22547,7 +25153,11 @@ "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, - "deprecation_date": "2027-01-08" + "deprecation_date": "2027-01-08", + "token_count_model": { + "model": "anthropic.claude-opus-4-1-20250805-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -22585,7 +25195,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -22606,7 +25216,11 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, @@ -22618,6 +25232,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -22644,9 +25259,14 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "eu.meta.llama3-2-1b-instruct-v1:0": { + "deprecation_date": "2026-07-07", "input_cost_per_token": 1.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -22654,10 +25274,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.3e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "eu.meta.llama3-2-3b-instruct-v1:0": { + "deprecation_date": "2026-07-07", "input_cost_per_token": 1.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -22665,6 +25287,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.9e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, @@ -22672,10 +25295,11 @@ "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md", "supports_function_calling": true, "supports_tool_choice": false }, @@ -24984,9 +27608,10 @@ "output_cost_per_token": 5e-07 }, "fireworks-ai-up-to-4b": { - "input_cost_per_token": 2e-07, + "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "output_cost_per_token": 2e-07 + "output_cost_per_token": 1e-07, + "source": "https://docs.fireworks.ai/serverless/pricing" }, "fireworks_ai/WhereIsAI/UAE-Large-V1": { "input_cost_per_token": 1.6e-08, @@ -25013,7 +27638,7 @@ "fireworks_ai/accounts/fireworks/models/deepseek-r1": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 163840, "max_output_tokens": 20480, "max_tokens": 20480, "mode": "chat", @@ -25025,7 +27650,7 @@ "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 160000, + "max_input_tokens": 163840, "max_output_tokens": 160000, "max_tokens": 160000, "mode": "chat", @@ -25037,7 +27662,7 @@ "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { "input_cost_per_token": 5.5e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 163840, "max_output_tokens": 20480, "max_tokens": 20480, "mode": "chat", @@ -25049,7 +27674,7 @@ "fireworks_ai/accounts/fireworks/models/deepseek-v3": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", @@ -25182,7 +27807,7 @@ "fireworks_ai/accounts/fireworks/models/glm-4p5": { "input_cost_per_token": 5.5e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 96000, "max_tokens": 96000, "mode": "chat", @@ -25196,7 +27821,7 @@ "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { "input_cost_per_token": 2.2e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 96000, "max_tokens": 96000, "mode": "chat", @@ -25211,7 +27836,7 @@ "input_cost_per_token": 5.5e-07, "output_cost_per_token": 2.19e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 202800, "max_tokens": 202800, "mode": "chat", @@ -25225,7 +27850,7 @@ "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 202800, "max_tokens": 202800, "mode": "chat", @@ -25240,7 +27865,7 @@ "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", @@ -25275,6 +27900,7 @@ "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-08, "cache_read_input_token_cost_priority": 1.8e-08, + "deprecation_date": "2026-11-07", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "fireworks_ai", @@ -25284,7 +27910,7 @@ "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -25404,7 +28030,7 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -25417,7 +28043,7 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -25430,7 +28056,7 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -25444,7 +28070,7 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -25457,7 +28083,7 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -25470,7 +28096,7 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -25508,7 +28134,7 @@ "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 204800, + "max_input_tokens": 196608, "max_output_tokens": 204800, "max_tokens": 204800, "mode": "chat", @@ -25609,7 +28235,7 @@ "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 202800, "max_tokens": 202800, "mode": "chat", @@ -25624,7 +28250,7 @@ "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", @@ -25675,6 +28301,7 @@ "fireworks_ai/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-08, "cache_read_input_token_cost_priority": 1.8e-08, + "deprecation_date": "2026-11-07", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "fireworks_ai", @@ -25684,7 +28311,7 @@ "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -25799,7 +28426,7 @@ "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 204800, + "max_input_tokens": 196608, "max_output_tokens": 204800, "max_tokens": 204800, "mode": "chat", @@ -26152,6 +28779,7 @@ "ft:gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.875e-06, "cache_read_input_token_cost_batches": 9e-07, + "deprecation_date": "2027-01-14", "input_cost_per_token": 3.75e-06, "input_cost_per_token_batches": 2.225e-06, "litellm_provider": "openai", @@ -26173,6 +28801,7 @@ }, "ft:gpt-4o-2024-11-20": { "cache_creation_input_token_cost": 1.875e-06, + "deprecation_date": "2027-01-14", "input_cost_per_token": 3.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -26191,6 +28820,7 @@ "ft:gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, + "deprecation_date": "2027-01-14", "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "litellm_provider": "openai", @@ -26212,6 +28842,7 @@ "ft:gpt-4.1-2025-04-14": { "cache_read_input_token_cost": 7.5e-07, "cache_read_input_token_cost_batches": 5e-07, + "deprecation_date": "2027-01-14", "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "openai", @@ -26232,6 +28863,7 @@ "ft:gpt-4.1-mini-2025-04-14": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, + "deprecation_date": "2027-01-14", "input_cost_per_token": 8e-07, "input_cost_per_token_batches": 4e-07, "litellm_provider": "openai", @@ -26338,6 +28970,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 1.5e-07, @@ -26370,7 +29003,8 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26428,7 +29062,8 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26450,6 +29085,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3-pro-image-preview": { @@ -26479,7 +29115,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26501,17 +29138,20 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, + "cache_read_input_token_cost_priority": 9e-08, "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -26522,10 +29162,12 @@ "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.4e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26547,6 +29189,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image-preview": { @@ -26567,7 +29210,8 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26589,16 +29233,20 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2027-06-28", "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, @@ -26609,10 +29257,12 @@ "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.7e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26679,6 +29329,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -26740,6 +29391,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -26787,6 +29439,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -26799,6 +29452,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -26812,7 +29466,7 @@ "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, - "mode": "image_generation", + "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, @@ -26885,6 +29539,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-08, "input_cost_per_token_batches": 5e-08, @@ -26939,6 +29594,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -26985,6 +29641,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -27032,7 +29689,8 @@ "search_context_size_high": 0.035 }, "gemini_native_audio": true, - "input_cost_per_image_token": 3e-06 + "input_cost_per_image_token": 3e-06, + "input_cost_per_video_token": 3e-06 }, "gemini-live-2.5-flash-preview-native-audio-09-2025": { "input_cost_per_audio_token": 3e-06, @@ -27171,6 +29829,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, "input_cost_per_token_batches": 6.25e-07, @@ -27182,22 +29841,33 @@ "output_cost_per_token_priority": 1.8e-05 }, "gemini-3.1-pro-preview": { - "prompt_cache_min_tokens": 4096, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", + "output_cost_per_image": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, - "output_cost_per_image": 0.00012, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27215,33 +29885,18 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "cache_read_input_token_cost_flex": 2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "web_search_billing_unit": "per_query" }, "gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, @@ -27293,6 +29948,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -27349,20 +30005,32 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_flex": 5e-08, - "input_cost_per_token": 5e-07, + "cache_read_input_token_cost_priority": 9e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.4e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27380,6 +30048,7 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -27389,23 +30058,7 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 9e-07, - "input_cost_per_audio_token_priority": 1.8e-06, - "output_cost_per_token_priority": 5.4e-06, - "cache_read_input_token_cost_priority": 9e-08, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 5e-07, - "input_cost_per_token_batches": 2.5e-07, - "input_cost_per_token_flex": 2.5e-07, - "output_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_flex": 1.5e-06 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.5-flash": { "prompt_cache_min_tokens": 4096, @@ -27460,6 +30113,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -27508,6 +30162,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -27518,11 +30173,13 @@ "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, + "deprecation_date": "2026-11-19", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -27567,6 +30224,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -27577,22 +30235,26 @@ "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, + "deprecation_date": "2027-01-28", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3.8-flash": { - "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, @@ -27602,7 +30264,11 @@ "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27620,29 +30286,21 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 1.35e-06, - "output_cost_per_token_priority": 6.75e-06, - "cache_read_input_token_cost_priority": 1.35e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, @@ -27685,6 +30343,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_url_context": false, @@ -27694,6 +30353,7 @@ "supports_native_streaming": true }, "vertex_ai/gemini-3.8-live": { + "gemini_audio_only_live": true, "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, @@ -27706,7 +30366,8 @@ "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "output_cost_per_video_token": 1e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/vertex_ai/live", "/v1/realtime" @@ -27726,26 +30387,36 @@ "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, - "supports_web_search": true, - "gemini_audio_only_live": true + "supports_web_search": true }, "vertex_ai/gemini-3.1-pro-preview": { - "prompt_cache_min_tokens": 4096, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", + "output_cost_per_image": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, - "output_cost_per_image": 0.00012, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27763,33 +30434,18 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "cache_read_input_token_cost_flex": 2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, @@ -27847,6 +30503,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -27931,7 +30588,7 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_reasoning_token": 5e-06, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "search_context_cost_per_query": { @@ -28152,8 +30809,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28174,6 +30831,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "supports_reasoning": false }, @@ -28195,8 +30853,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28218,6 +30876,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite-preview": { @@ -28279,6 +30938,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -28309,7 +30969,7 @@ "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", @@ -28346,7 +31006,7 @@ "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", @@ -28428,8 +31088,10 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.4e-07, @@ -28441,7 +31103,7 @@ }, "gemini/gemini-2.5-flash-image": { "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-10-02", + "deprecation_date": "2027-03-15", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, @@ -28461,8 +31123,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28507,6 +31169,7 @@ "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token_batches": 6e-05, "output_cost_per_token": 1.2e-05, "rpm": 1000, "tpm": 4000000, @@ -28516,8 +31179,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28528,7 +31191,7 @@ "image" ], "supports_function_calling": false, - "supports_prompt_caching": true, + "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, @@ -28538,8 +31201,9 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", - "supports_reasoning": false + "supports_reasoning": true }, "gemini/nano-banana-pro-preview": { "input_cost_per_image": 0.0011, @@ -28563,8 +31227,7 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28598,15 +31261,17 @@ "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 6e-05, + "output_cost_per_image_token_batches": 3e-05, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, - "rpm": 1000, - "tpm": 4000000, + "rpm": 1000.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28617,17 +31282,14 @@ "image" ], "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, + "tpm": 4000000.0, "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite-image": { @@ -28647,8 +31309,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28659,8 +31321,9 @@ "image" ], "supports_function_calling": false, + "supports_pdf_input": true, "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, @@ -28668,21 +31331,20 @@ "tpm": 4000000 }, "gemini/deep-research-pro-preview-12-2025": { + "deprecation_date": "2026-10-23", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.134, - "output_cost_per_image_token": 0.00012, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", "output_cost_per_token": 1.2e-05, - "rpm": 1000, - "tpm": 4000000, "output_cost_per_token_batches": 6e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "rpm": 1000.0, + "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, + "source": "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -28690,23 +31352,21 @@ ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": false, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } + "tpm": 4000000.0 }, "gemini/gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, @@ -28757,8 +31417,10 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 1.5e-07, + "input_cost_per_audio_token_priority": 5.4e-07, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_flex": 5e-08, "input_cost_per_token_priority": 1.8e-07, @@ -28886,6 +31548,7 @@ "web_search_billing_unit": "per_query" }, "gemini/gemini-2.5-flash-preview-tts": { + "deprecation_date": "2026-11-17", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", @@ -28960,13 +31623,16 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 5e-06, - "output_cost_per_token_flex": 5e-06 + "output_cost_per_token_flex": 5e-06, + "supports_url_context": true }, "gemini/gemini-2.5-computer-use-preview-10-2025": { + "deprecation_date": "2026-07-28", "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "gemini", @@ -29055,9 +31721,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "input_cost_per_audio_token_batches": 2.5e-07, + "input_cost_per_audio_token_priority": 9e-07 }, "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, @@ -29102,6 +31770,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29115,6 +31784,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29171,6 +31841,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 5e-07, @@ -29234,6 +31905,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -29283,6 +31955,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29299,6 +31972,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29344,6 +32018,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29360,6 +32035,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29405,6 +32081,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29421,6 +32098,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29456,7 +32134,7 @@ "supports_video_input": true, "supports_vision": true, "tpm": 800000, - "deprecation_date": "2026-09-30" + "deprecation_date": "2026-10-22" }, "gemini/gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, @@ -29516,6 +32194,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, @@ -29579,6 +32258,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, @@ -29587,9 +32267,15 @@ "gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 9e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, @@ -29597,6 +32283,11 @@ "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.4e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -29614,6 +32305,7 @@ ], "supports_audio_output": false, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -29624,23 +32316,7 @@ "supports_url_context": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 9e-07, - "input_cost_per_audio_token_priority": 1.8e-06, - "output_cost_per_token_priority": 5.4e-06, - "cache_read_input_token_cost_priority": 9e-08, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 5e-07, - "input_cost_per_token_batches": 2.5e-07, - "input_cost_per_token_flex": 2.5e-07, - "output_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_flex": 1.5e-06 + "web_search_billing_unit": "per_query" }, "gemini-omni-flash-preview": { "input_cost_per_audio_token": 1.5e-06, @@ -29726,6 +32402,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -29774,6 +32451,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29784,11 +32462,13 @@ "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, + "deprecation_date": "2026-11-19", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29833,6 +32513,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29843,22 +32524,26 @@ "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, + "deprecation_date": "2027-01-28", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "gemini-3.8-flash": { - "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, @@ -29868,6 +32553,10 @@ "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -29883,32 +32572,24 @@ "supported_output_modalities": [ "text" ], - "supports_audio_output": false, "supports_audio_input": true, + "supports_audio_output": false, "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 1.35e-06, - "output_cost_per_token_priority": 6.75e-06, - "cache_read_input_token_cost_priority": 1.35e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "web_search_billing_unit": "per_query" }, "gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, @@ -29951,6 +32632,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_url_context": false, @@ -29961,6 +32643,7 @@ }, "gemini/gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-07, + "deprecation_date": "2026-11-17", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, @@ -30221,6 +32904,7 @@ "output_cost_per_image": 0.08 }, "gemini/veo-3.1-fast-generate-preview": { + "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, @@ -30237,6 +32921,7 @@ ] }, "gemini/veo-3.1-generate-preview": { + "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, @@ -30252,6 +32937,7 @@ ] }, "gemini/veo-3.1-lite-generate-preview": { + "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, @@ -30297,83 +32983,270 @@ "video" ] }, - "github_copilot/claude-haiku-4.5": { + "github_copilot/claude-fable-5": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ - "/v1/chat/completions" + "/v1/chat/completions", + "/v1/messages" ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true - }, - "github_copilot/claude-opus-4.5": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_output_config": true - }, - "github_copilot/claude-opus-4.6-fast": { "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "github_copilot/claude-fable-5.1": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-05, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "github_copilot/claude-haiku-4.5": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token": 5e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_vision": true }, - "github_copilot/claude-opus-41": { - "litellm_provider": "github_copilot", - "max_input_tokens": 80000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_vision": true - }, - "github_copilot/claude-sonnet-4": { + "github_copilot/claude-haiku-5.5": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_100k_tokens": 5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ - "/v1/chat/completions" + "/v1/chat/completions", + "/v1/messages" ], + "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": false + }, + "github_copilot/claude-opus-4.8": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 5e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_vision": true }, - "github_copilot/claude-sonnet-4.5": { + "github_copilot/claude-opus-4.8-fast": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/claude-opus-5": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 5e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/claude-opus-5.5": { + "cache_creation_input_token_cost": 5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "github_copilot/claude-sonnet-5": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/claude-sonnet-5.5": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "github_copilot/gemini-3.7-flash": { + "cache_read_input_token_cost": 7.5e-08, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 7.5e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_vision": true + }, + "github_copilot/gemini-3.8-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_sampling_params": false, "supports_vision": true }, "github_copilot/gpt-3.5-turbo": { @@ -30418,22 +33291,26 @@ "supports_parallel_function_calling": true }, "github_copilot/gpt-4.1": { + "deprecation_date": "2026-06-01", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-4.1-2025-04-14": { + "deprecation_date": "2026-06-01", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -30500,82 +33377,304 @@ "supports_function_calling": true, "supports_parallel_function_calling": true }, - "github_copilot/gpt-5": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true - }, "github_copilot/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 2.5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true - }, - "github_copilot/gpt-5.1": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true - }, - "github_copilot/gpt-5.1-codex-max": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "supported_endpoints": [ - "/v1/responses" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true - }, - "github_copilot/gpt-5.2": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], + "output_cost_per_token": 2e-06, + "source": "https://github.blog/changelog/2026-10-19-github-copilot-models-deprecated-on-october-19-2026", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 1.4e-05, + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.4": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.4-mini": { + "cache_read_input_token_cost": 7.5e-08, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 7.5e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 4.5e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.5": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_200k_tokens": 5e-07, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_200k_tokens": 4e-08, + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_200k_tokens": 4e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_200k_tokens": 1.8e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.6-sol": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.6-terra": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-6-astra": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 917504, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/mai-code-1.1-flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.2e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], @@ -30584,38 +33683,6 @@ "supports_response_schema": true, "supports_vision": true }, - "github_copilot/mai-code-1-flash": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 4.5e-06, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true - }, - "github_copilot/mai-code-1-flash-internal": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 4.5e-06, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true - }, "github_copilot/text-embedding-3-small": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, @@ -30634,6 +33701,90 @@ "max_tokens": 8191, "mode": "embedding" }, + "chatgpt/gpt-6-sol": { + "litellm_provider": "chatgpt", + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6-luna": { + "litellm_provider": "chatgpt", + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6-astra": { + "litellm_provider": "chatgpt", + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6.1-sol": { + "litellm_provider": "chatgpt", + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, "chatgpt/gpt-5.5": { "litellm_provider": "chatgpt", "source": "https://platform.openai.com/docs/models/gpt-5.5", @@ -31099,24 +34250,28 @@ "output_cost_per_token": 1.2e-06 }, "baseten/MiniMaxAI/MiniMax-M2.5": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 1.2e-06 }, "baseten/nvidia/Nemotron-120B-A12B": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 7.5e-07 }, "baseten/zai-org/GLM-5": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 9.5e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 3.15e-06 }, "baseten/zai-org/GLM-4.7": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "baseten", @@ -31134,24 +34289,28 @@ "supports_vision": false }, "baseten/zai-org/GLM-4.6": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 2.2e-06 }, "baseten/moonshotai/Kimi-K2.5": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 3e-06 }, "baseten/moonshotai/Kimi-K2-Thinking": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 2.5e-06 }, "baseten/moonshotai/Kimi-K2-Instruct-0905": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", @@ -31175,12 +34334,14 @@ "supports_vision": false }, "baseten/deepseek-ai/DeepSeek-V3.1": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 5e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 1.5e-06 }, "baseten/deepseek-ai/DeepSeek-V3-0324": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 7.7e-07, "litellm_provider": "baseten", "mode": "chat", @@ -31206,14 +34367,21 @@ "output_cost_per_token": 2e-06 }, "google.gemma-3-12b-it": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 9e-08, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.9e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_flex": 1.5e-07, + "output_cost_per_token_priority": 5.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -31221,14 +34389,21 @@ "supports_vision": true }, "google.gemma-3-27b-it": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.3e-07, + "input_cost_per_token_batches": 1.2e-07, + "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 3.8e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.9e-07, + "output_cost_per_token_flex": 1.9e-07, + "output_cost_per_token_priority": 6.7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -31236,14 +34411,21 @@ "supports_vision": true }, "google.gemma-3-4b-it": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4e-08, + "input_cost_per_token_batches": 2e-08, + "input_cost_per_token_flex": 2e-08, + "input_cost_per_token_priority": 7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-08, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 4e-08, + "output_cost_per_token_flex": 4e-08, + "output_cost_per_token_priority": 1.4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -31264,6 +34446,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -31290,7 +34473,11 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, "output_cost_per_token_batches": 7.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -31302,7 +34489,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -31323,7 +34510,11 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.25e-06, @@ -31351,17 +34542,27 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-07, - "output_cost_per_token_batches": 2.5e-06 + "output_cost_per_token_batches": 2.5e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "global.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_priority": 1.3125e-07, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -31584,6 +34785,7 @@ "gpt-4.1-2025-04-14": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, + "deprecation_date": "2027-01-14", "input_cost_per_token": 2e-06, "input_cost_per_token_priority": 3.5e-06, "input_cost_per_token_batches": 1e-06, @@ -31670,6 +34872,7 @@ "gpt-4.1-mini-2025-04-14": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, + "deprecation_date": "2027-01-14", "input_cost_per_token": 4e-07, "input_cost_per_token_priority": 7e-07, "input_cost_per_token_batches": 2e-07, @@ -31835,6 +35038,7 @@ "gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, + "deprecation_date": "2027-01-14", "input_cost_per_token": 2.5e-06, "input_cost_per_token_priority": 4.25e-06, "input_cost_per_token_batches": 1.25e-06, @@ -31859,6 +35063,7 @@ "gpt-4o-2024-11-20": { "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, + "deprecation_date": "2027-01-14", "input_cost_per_token": 2.5e-06, "input_cost_per_token_priority": 4.25e-06, "input_cost_per_token_batches": 1.25e-06, @@ -32064,6 +35269,44 @@ "supports_tool_choice": true, "supports_vision": false }, + "gpt-audio-mini-2025-10-06": { + "deprecation_date": "2026-07-23", + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 6e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://developers.openai.com/api/docs/models/gpt-audio-mini", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "gpt-audio-mini-2025-12-15": { "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, @@ -32134,6 +35377,7 @@ "gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.25e-07, + "deprecation_date": "2027-01-14", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 2.5e-07, "input_cost_per_token_batches": 7.5e-08, @@ -32224,6 +35468,34 @@ "supports_vision": true, "supports_web_search": true }, + "gpt-4o-mini-search-preview-2025-03-11": { + "deprecation_date": "2026-07-23", + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.025, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.025 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-search-preview" + }, "gpt-4o-mini-transcribe": { "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, @@ -32258,6 +35530,26 @@ "audio" ] }, + "gpt-4o-mini-tts-2025-03-20": { + "deprecation_date": "2027-01-06", + "input_cost_per_token": 6e-07, + "litellm_provider": "openai", + "mode": "audio_speech", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_second": 0.00025, + "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "audio" + ] + }, "gpt-4o-search-preview": { "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, @@ -32284,6 +35576,34 @@ "supports_vision": true, "supports_web_search": true }, + "gpt-4o-search-preview-2025-03-11": { + "deprecation_date": "2026-07-23", + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.025, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.025 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://developers.openai.com/api/docs/models/gpt-4o-search-preview" + }, "gpt-4o-transcribe": { "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, @@ -32379,10 +35699,13 @@ "gpt-image-2.5-flare": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_batches": 6.25e-07, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, + "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ "/v1/images/generations", @@ -32411,10 +35734,13 @@ "gpt-image-2.5-sunburst": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_batches": 6.25e-07, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, + "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ "/v1/images/generations", @@ -32933,7 +36259,8 @@ "output_cost_per_token_flex": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": false + "supports_minimal_reasoning_effort": false, + "deprecation_date": "2027-04-01" }, "gpt-5.1-codex-mini": { "cache_read_input_token_cost": 2.5e-08, @@ -33155,6 +36482,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -33272,6 +36600,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -33383,16 +36712,22 @@ "cache_read_input_token_cost_above_272k_tokens_batches": 1e-06, "cache_creation_input_token_cost_batches": 6.25e-06, "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015, + "cache_creation_input_token_cost_ultrafast": 7.5e-05, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05, "cache_read_input_token_cost_flex": 5e-07, "cache_read_input_token_cost_priority": 2e-06, + "cache_read_input_token_cost_ultrafast": 6e-06, "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, "input_cost_per_token_above_272k_tokens_flex": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 4e-05, "input_cost_per_token_batches": 5e-06, "input_cost_per_token_above_272k_tokens_batches": 1e-05, + "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012, "input_cost_per_token_flex": 5e-06, "input_cost_per_token_priority": 2e-05, + "input_cost_per_token_ultrafast": 6e-05, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -33404,8 +36739,10 @@ "output_cost_per_token_above_272k_tokens_priority": 0.00015, "output_cost_per_token_batches": 2.5e-05, "output_cost_per_token_above_272k_tokens_batches": 3.75e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045, "output_cost_per_token_flex": 2.5e-05, "output_cost_per_token_priority": 0.0001, + "output_cost_per_token_ultrafast": 0.0003, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { @@ -33440,6 +36777,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true @@ -33516,19 +36854,24 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_decisions": 1e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens_decisions": 2e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-07, "cache_creation_input_token_cost_flex": 6.25e-08, "cache_creation_input_token_cost_priority": 2.5e-07, "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_decisions": 1e-07, "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "cache_read_input_token_cost_above_272k_tokens_decisions": 2e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 4e-08, "cache_read_input_token_cost_batches": 5e-09, @@ -33538,7 +36881,9 @@ "cache_read_input_token_cost_flex": 5e-09, "cache_read_input_token_cost_priority": 2e-08, "input_cost_per_token": 1e-07, + "input_cost_per_token_decisions": 1e-07, "input_cost_per_token_above_272k_tokens": 2e-07, + "input_cost_per_token_above_272k_tokens_decisions": 2e-07, "input_cost_per_token_above_272k_tokens_flex": 1e-07, "input_cost_per_token_above_272k_tokens_priority": 4e-07, "input_cost_per_token_batches": 5e-08, @@ -33551,7 +36896,9 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, + "output_cost_per_token_decisions": 0.0, "output_cost_per_token_above_272k_tokens": 7.5e-07, + "output_cost_per_token_above_272k_tokens_decisions": 0.0, "output_cost_per_token_above_272k_tokens_flex": 3.75e-07, "output_cost_per_token_above_272k_tokens_priority": 1.5e-06, "output_cost_per_token_batches": 2.5e-07, @@ -33593,6 +36940,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true @@ -33666,6 +37014,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true @@ -33741,6 +37090,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true @@ -33815,6 +37165,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true @@ -33889,6 +37240,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true @@ -34174,6 +37526,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -34236,6 +37589,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -34290,6 +37644,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -34341,6 +37696,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -34395,6 +37751,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", @@ -34452,6 +37809,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", @@ -34505,6 +37863,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -34557,6 +37916,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -34612,6 +37972,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -34666,6 +38027,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -34723,7 +38085,8 @@ "default_reasoning_effort": "none", "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_minimal_reasoning_effort": false, + "deprecation_date": "2027-04-01" }, "gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-08, @@ -36404,6 +39767,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -36430,7 +39794,11 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -36458,7 +39826,11 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "crusoe/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 3e-06, @@ -36583,6 +39955,736 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "inferenceapis/deepseek-ai/DeepSeek-V3": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-ai/DeepSeek-V4-Flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-ai/DeepSeek-V4-Pro": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1.72e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1.72e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-chat": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-reasoner": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-v3": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-v4-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-v4-pro": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1.72e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/glm-5.3": { + "cache_read_input_token_cost": 3.4e-07, + "input_cost_per_token": 1.82e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 5.72e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/glm-5.3-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/gpt-oss-120b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 8.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.42e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/llama-3.1-8b-instant": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/llama-3.3-70b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/llama-3.3-70b-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/llama-3.3-70b-versatile": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/minimax-m3": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 3.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 1.56e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/MiniMaxAI/MiniMax-M3": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 3.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 1.56e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/moonshotai/Kimi-K2.7-Code": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 8.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.42e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/openai/gpt-oss-120b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/openai/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/Qwen/Qwen3-VL-235B-A22B-Instruct": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "inferenceapis/Qwen/Qwen3.8-Flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/qwen3-vl": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "inferenceapis/qwen3-vl-235b": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "inferenceapis/qwen3.8-flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/zai-org/GLM-5.3": { + "cache_read_input_token_cost": 3.4e-07, + "input_cost_per_token": 1.82e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 5.72e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "text-completion-inception/mercury-edit-2": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, @@ -37035,51 +41137,64 @@ "source": "https://aws.amazon.com/bedrock/pricing/" }, "meta.llama3-1-405b-instruct-v1:0": { - "input_cost_per_token": 5.32e-06, + "deprecation_date": "2026-07-07", + "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.6e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-1-70b-instruct-v1:0": { - "input_cost_per_token": 9.9e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 9.9e-07, - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-1-8b-instruct-v1:0": { - "input_cost_per_token": 2.2e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2.2e-07, - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-2-11b-instruct-v1:0": { - "input_cost_per_token": 3.5e-07, + "deprecation_date": "2027-03-30", + "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.5e-07, + "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-1-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "output_cost_per_token_batches": 1.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-2-11b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "input_cost_per_token": 1.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.6e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true }, "meta.llama3-2-1b-instruct-v1:0": { + "deprecation_date": "2026-07-07", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -37087,10 +41202,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-2-3b-instruct-v1:0": { + "deprecation_date": "2026-07-07", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -37098,60 +41215,73 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-2-90b-instruct-v1:0": { - "input_cost_per_token": 2e-06, + "deprecation_date": "2026-07-07", + "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 7.2e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true }, "meta.llama3-3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.5e-06 + "output_cost_per_token": 3.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-07 + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "meta.llama4-maverick-17b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9.7e-07, "output_cost_per_token_batches": 4.85e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", "supported_modalities": [ "text", "image" @@ -37164,15 +41294,17 @@ "supports_tool_choice": false }, "meta.llama4-scout-17b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.7e-07, "input_cost_per_token_batches": 8.5e-08, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 10000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_batches": 3.3e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", "supported_modalities": [ "text", "image" @@ -37405,6 +41537,49 @@ ], "supports_audio_input": true }, + "meta/muse-wonder-1.0": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "meta", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://dev.meta.ai/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "meta_llama/Llama-3.3-70B-Instruct": { "litellm_provider": "meta_llama", "max_input_tokens": 128000, @@ -37472,14 +41647,21 @@ "supports_tool_choice": true }, "minimax.minimax-m2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -37488,33 +41670,46 @@ "supports_vision": false }, "minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 196000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 196000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -37644,31 +41839,96 @@ "max_input_tokens": 1000000, "max_output_tokens": 128000 }, + "minimax/MiniMax-H3": { + "litellm_provider": "minimax", + "mode": "video_generation", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "output_cost_per_second_2k": 0.13, + "input_cost_per_image": 0.04, + "provider_specific_entry": { + "minimax_free_input_images": 5 + }, + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "metadata": { + "comment": "V2 async task API. Pay-as-you-go list price $0.08/s at 768P and $0.13/s at 2K, plus $0.04 per input image beyond the first 5. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." + } + }, + "minimax/MiniMax-H3-Max": { + "litellm_provider": "minimax", + "mode": "video_generation", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "input_cost_per_image": 0.074, + "provider_specific_entry": { + "minimax_free_input_images": 2 + }, + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "metadata": { + "comment": "V2 async task API, fast tier. Pay-as-you-go list price $0.05/s at 480P and $0.08/s at 768P; no 2K. Plus $0.074 per input image beyond the first 2. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." + } + }, "mistral.devstral-2-123b": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_flex": 2e-07, + "input_cost_per_token_priority": 7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "output_cost_per_token_flex": 1e-06, + "output_cost_per_token_priority": 3.5e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "mistral.magistral-small-2509": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 40000, "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.63e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, @@ -37678,13 +41938,19 @@ }, "mistral.ministral-3-14b-instruct": { "input_cost_per_token": 2e-07, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "input_cost_per_token_priority": 3.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1e-07, + "output_cost_per_token_flex": 1e-07, + "output_cost_per_token_priority": 3.5e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -37694,13 +41960,19 @@ }, "mistral.ministral-3-3b-instruct": { "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 5e-08, + "output_cost_per_token_flex": 5e-08, + "output_cost_per_token_priority": 1.7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -37710,13 +41982,19 @@ }, "mistral.ministral-3-8b-instruct": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 7e-08, + "output_cost_per_token_flex": 7e-08, + "output_cost_per_token_priority": 2.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -37725,47 +42003,55 @@ "supports_vision": true }, "mistral.mistral-7b-instruct-v0:2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "mistral.mistral-large-2407-v1:0": { - "input_cost_per_token": 3e-06, + "input_cost_per_token": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 9e-06, + "output_cost_per_token": 6e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": true }, "mistral.mistral-large-3-675b-instruct": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.63e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -37778,47 +42064,62 @@ "input_cost_per_token_batches": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-small.md", "supports_function_calling": true }, "mistral.mixtral-8x7b-instruct-v0:1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "mistral.voxtral-mini-3b-2507": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4e-08, + "input_cost_per_token_batches": 2e-08, + "input_cost_per_token_flex": 2e-08, + "input_cost_per_token_priority": 7e-08, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, + "max_input_tokens": 32768, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-08, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 2e-08, + "output_cost_per_token_flex": 2e-08, + "output_cost_per_token_priority": 7e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true }, "mistral.voxtral-small-24b-2507": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.7e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, + "max_input_tokens": 32768, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_flex": 1.5e-07, + "output_cost_per_token_priority": 5.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true @@ -38038,7 +42339,6 @@ }, "mistral/voxtral-small-2507": { "cache_read_input_token_cost": 1e-08, - "input_cost_per_second": 6.666666666666667e-05, "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 32768, @@ -38054,7 +42354,6 @@ }, "mistral/voxtral-small-latest": { "cache_read_input_token_cost": 1e-08, - "input_cost_per_second": 6.666666666666667e-05, "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 32768, @@ -38070,6 +42369,7 @@ }, "mistral/zai-glm-5-2": { "cache_read_input_token_cost": 1.4e-07, + "deprecation_date": "2026-10-31", "input_cost_per_token": 1.4e-06, "litellm_provider": "mistral", "max_input_tokens": 1048576, @@ -38200,6 +42500,7 @@ "source": "https://mistral.ai/pricing#api-pricing" }, "mistral/mistral-ocr-4-0": { + "deprecation_date": "2026-09-30", "litellm_provider": "mistral", "ocr_cost_per_page": 0.004, "ocr_cost_per_page_batches": 0.002, @@ -38295,6 +42596,48 @@ "max_tokens": 8192, "mode": "embedding" }, + "mistral/mistral-large-4": { + "cache_read_input_token_cost": 6.8e-08, + "input_cost_per_token": 6.8e-07, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.09e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/mistral-large-4", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-large-4-0": { + "cache_read_input_token_cost": 6.8e-08, + "input_cost_per_token": 6.8e-07, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.09e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/mistral-large-4", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "mistral/mistral-large-latest": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 5e-07, @@ -38585,14 +42928,19 @@ "supports_vision": true }, "moonshot.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.38e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, @@ -38603,17 +42951,23 @@ }, "moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true }, @@ -39346,6 +43700,7 @@ "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { "input_cost_per_token": 1.32e-06, "litellm_provider": "nebius", + "max_input_tokens": 979000, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813", @@ -39355,12 +43710,14 @@ "nebius/deepseek-ai/DeepSeek-V4.1-Flash": { "input_cost_per_token": 3e-07, "litellm_provider": "nebius", - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "max_tokens": 1048576, + "max_input_tokens": 1048000, + "max_output_tokens": 384000, + "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://tokenfactory.nebius.com/endpoints?modals=endpoint-details&model-id=deepseek-ai/DeepSeek-V4.1-Flash", + "supports_function_calling": true, + "supports_reasoning": true, "supports_vision": true }, "nebius/MiniMaxAI/MiniMax-M2.5": { @@ -39605,6 +43962,16 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.5-397B-A17B" }, + "nebius/Qwen/Qwen3.8-27B": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "nebius", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.8-27B", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/zai-org/GLM-5.1": { "max_tokens": 202752, "max_input_tokens": 202752, @@ -39632,8 +43999,8 @@ "nebius/zai-org/GLM-5.3": { "input_cost_per_token": 1.4e-06, "litellm_provider": "nebius", - "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_input_tokens": 1024000, + "max_tokens": 1024000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", @@ -39650,7 +44017,8 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash" + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash", + "supports_vision": true }, "nebius/BAAI/bge-en-icl": { "max_tokens": 32768, @@ -39689,14 +44057,21 @@ "source": "https://tokenfactory.nebius.com/models/catalog/embedding/Qwen%2FQwen3-Embedding-8B" }, "nvidia.nemotron-nano-12b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2e-07, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "input_cost_per_token_priority": 3.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -39704,14 +44079,21 @@ "supports_vision": true }, "nvidia.nemotron-nano-9b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.3e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.2e-07, + "output_cost_per_token_flex": 1.2e-07, + "output_cost_per_token_priority": 4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -39720,16 +44102,22 @@ }, "nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.4e-07, + "output_cost_per_token_batches": 1.2e-07, + "output_cost_per_token_flex": 1.2e-07, + "output_cost_per_token_priority": 4.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_native_structured_output": true, "supports_response_schema": true, @@ -39737,13 +44125,19 @@ }, "nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.5e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3.25e-07, + "output_cost_per_token_flex": 3.25e-07, + "output_cost_per_token_priority": 1.1375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, @@ -39913,6 +44307,39 @@ "supports_web_search": true }, "o3-deep-research": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "source": "https://developers.openai.com/api/docs/models/o3-deep-research", + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_pdf_input": true, + "deprecation_date": "2026-07-23" + }, + "o3-deep-research-2025-06-26": { + "deprecation_date": "2026-07-23", "cache_read_input_token_cost": 2.5e-06, "input_cost_per_token": 1e-05, "litellm_provider": "openai", @@ -40142,6 +44569,39 @@ "supports_web_search": true }, "o4-mini-deep-research": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-06, + "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_pdf_input": true, + "deprecation_date": "2026-07-23" + }, + "o4-mini-deep-research-2025-06-26": { + "deprecation_date": "2026-07-23", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "openai", @@ -40616,6 +45076,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, + "reasoning_effort_levels": [], "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false @@ -40632,6 +45093,72 @@ "supports_function_calling": true, "supports_response_schema": false }, + "oci/xai.grok-4.20-0309-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true + }, + "oci/xai.grok-4.20-0309-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_reasoning": true + }, + "oci/xai.grok-4.20-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true + }, + "oci/xai.grok-4.20-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_reasoning": true + }, "oci/xai.grok-code-fast-1": { "input_cost_per_token": 5e-06, "litellm_provider": "oci", @@ -40689,6 +45216,32 @@ "supports_response_schema": true, "supports_vision": true }, + "oci/openai.gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true + }, + "oci/openai.gpt-oss-20b": { + "input_cost_per_token": 7e-08, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true + }, "oci/cohere.embed-english-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "oci", @@ -41070,28 +45623,50 @@ "output_cost_per_token": 0.0 }, "openai.gpt-oss-120b-1:0": { + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "openai.gpt-oss-20b-1:0": { + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3.5e-08, + "input_cost_per_token_flex": 3.5e-08, + "input_cost_per_token_priority": 1.225e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_flex": 1.5e-07, + "output_cost_per_token_priority": 5.25e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -41099,14 +45674,21 @@ }, "openai.gpt-oss-safeguard-120b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, @@ -41114,2303 +45696,26 @@ }, "openai.gpt-oss-safeguard-20b": { "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1e-07, + "output_cost_per_token_flex": 1e-07, + "output_cost_per_token_priority": 3.5e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": false }, - "openrouter/anthropic/claude-3-haiku": { - "cache_creation_input_token_cost": 3e-07, - "cache_creation_input_token_cost_above_1hr": 5e-07, - "cache_read_input_token_cost": 3e-08, - "input_cost_per_image": 0.0004, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_web_search": true - }, - "openrouter/anthropic/claude-3.5-sonnet": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/anthropic/claude-3.7-sonnet": { - "input_cost_per_image": 0.0048, - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/anthropic/claude-opus-4.1": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": false, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-4": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost": 3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": false, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-4.6": { - "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost": 3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_max_reasoning_effort": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.5": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_output_config": true, - "prompt_cache_min_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.6": { - "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_max_reasoning_effort": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 4096, - "supports_response_schema": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-4.5": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-haiku-4.5": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_1hr": 2e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.7": { - "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_max_reasoning_effort": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "prompt_cache_min_tokens": 2048, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-5": { - "prompt_cache_min_tokens": 512, - "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": false, - "supports_audio_input": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_max_reasoning_effort": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true - }, - "openrouter/anthropic/claude-opus-5.5": { - "cache_creation_input_token_cost": 5e-06, - "cache_creation_input_token_cost_above_1hr": 8e-06, - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/bytedance/ui-tars-1.5-7b": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-chat": { - "input_cost_per_token": 3.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 8.9e-07, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-chat-v3-0324": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 147456, - "max_tokens": 147456, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-chat-v3.1": { - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_cache_hit": 2e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 9.5e-07, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "cache_read_input_token_cost": 1.3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v3.2": { - "cache_read_input_token_cost": 1.345e-07, - "deprecation_date": "2026-09-28", - "input_cost_per_token": 2.69e-07, - "input_cost_per_token_cache_hit": 1.345e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 4e-07, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v3.2-exp": { - "cache_read_input_token_cost": 2e-08, - "deprecation_date": "2026-09-28", - "input_cost_per_token": 2.7e-07, - "input_cost_per_token_cache_hit": 2e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 4.1e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": true, - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-r1": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 7e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 64000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": true, - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-r1-0528": { - "cache_read_input_token_cost": 3.5e-07, - "input_cost_per_token": 5e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 2.15e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": true, - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v4-pro": { - "input_cost_per_token": 8.44944e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 1.689888e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "cache_read_input_token_cost": 7.0412e-08, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v4.1-flash": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 6e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 393216, - "max_tokens": 393216, - "mode": "chat", - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9}, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v4-pro-0813": { - "input_cost_per_token": 4.62e-07, - "input_cost_per_token_cache_hit": 1.9272e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 1.386e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "cache_read_input_token_cost": 1.54e-08, - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":0.00000132,"output_cost_per_token":0.00000396,"cache_read_input_token_cost":4.4e-8}, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/fireworks/ember-1": { - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/google/gemini-2.5-flash": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 1e-07, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_image_size": false, - "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-10-20", - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_pdf_input": true, - "supports_reasoning": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-2.5-pro": { - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 1.25e-07, - "input_cost_per_audio_token": 1.25e-06, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "deprecation_date": "2026-10-20", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_pdf_input": true, - "supports_reasoning": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3-pro-preview": { - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "output_cost_per_token_batches": 6e-06, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/google/gemini-3-flash-preview": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 1e-07, - "cache_read_input_token_cost": 5e-08, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 3e-06, - "output_cost_per_token": 3e-06, - "rpm": 2000, - "source": "https://openrouter.ai/api/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000, - "supports_video_input": true - }, - "openrouter/google/gemini-3.1-flash-lite-preview": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 5e-08, - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 1.5e-06, - "output_cost_per_token": 1.5e-06, - "rpm": 2000, - "source": "https://openrouter.ai/api/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000 - }, - "openrouter/google/gemini-3.1-flash-lite": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 5e-08, - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 1.5e-06, - "output_cost_per_token": 1.5e-06, - "rpm": 2000, - "source": "https://openrouter.ai/api/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000 - }, - "openrouter/google/gemini-3.1-pro-preview": { - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, - "cache_read_input_audio_token_cost": 2e-07, - "input_cost_per_audio_token": 2e-06, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/gryphe/mythomax-l2-13b": { - "input_cost_per_token": 8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 3686, - "max_tokens": 3686, - "mode": "chat", - "output_cost_per_token": 1.1e-07, - "supports_tool_choice": false, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mancer/weaver": { - "input_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_tokens": 6000, - "mode": "chat", - "output_cost_per_token": 7.5e-07, - "supports_tool_choice": false, - "max_input_tokens": 8000, - "max_output_tokens": 6000, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/meta-llama/llama-3-70b-instruct": { - "input_cost_per_token": 5.9e-07, - "litellm_provider": "openrouter", - "max_tokens": 8000, - "mode": "chat", - "output_cost_per_token": 7.9e-07, - "supports_tool_choice": true, - "max_input_tokens": 8192, - "max_output_tokens": 8000 - }, - "openrouter/minimax/minimax-m2": { - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mistralai/devstral-2512": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_image": 0, - "input_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mistralai/ministral-3b-2512": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_image": 0, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, - "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/ministral-8b-2512": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_image": 0, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/ministral-14b-2512": { - "cache_read_input_token_cost": 2e-08, - "input_cost_per_image": 0, - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-7b-instruct": { - "input_cost_per_token": 1.3e-07, - "litellm_provider": "openrouter", - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 1.3e-07, - "supports_tool_choice": true, - "max_input_tokens": 32768, - "max_output_tokens": 8191 - }, - "openrouter/mistralai/mistral-large": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_tokens": 102400, - "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_tool_choice": true, - "max_input_tokens": 128000, - "max_output_tokens": 102400, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-small-3.1-24b-instruct": { - "input_cost_per_token": 3.51e-07, - "litellm_provider": "openrouter", - "max_tokens": 102400, - "mode": "chat", - "output_cost_per_token": 5.55e-07, - "supports_tool_choice": true, - "max_input_tokens": 128000, - "max_output_tokens": 102400, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "input_cost_per_token": 9.375e-08, - "litellm_provider": "openrouter", - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "supports_tool_choice": true, - "max_input_tokens": 256000, - "max_output_tokens": 16384, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mixtral-8x22b-instruct": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_tokens": 52428, - "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_tool_choice": true, - "max_input_tokens": 65536, - "max_output_tokens": 52428, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k2.5": { - "cache_read_input_token_cost": 7e-08, - "input_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 2.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3.5-lightning": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_token": 8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-3.5-turbo": { - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_tool_choice": true, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-3.5-turbo-16k": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 4e-06, - "supports_tool_choice": true, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-4": { - "input_cost_per_token": 3e-05, - "litellm_provider": "openrouter", - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-05, - "supports_tool_choice": true, - "max_input_tokens": 8191, - "max_output_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-4.1": { - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4.1-mini": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4.1-nano": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4o": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 1.25e-06, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4o-2024-05-13": { - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-chat": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_reasoning": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-5-codex": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_reasoning": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-5.2-codex": { - "cache_read_input_token_cost": 1.75e-07, - "input_cost_per_token": 1.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-mini": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-nano": { - "cache_read_input_token_cost": 5e-09, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.1-codex-max": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.2": { - "input_cost_per_image": 0, - "cache_read_input_token_cost": 1.75e-07, - "input_cost_per_token": 1.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.2-chat": { - "input_cost_per_image": 0, - "cache_read_input_token_cost": 1.75e-07, - "input_cost_per_token": 1.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.2-pro": { - "input_cost_per_image": 0, - "input_cost_per_token": 2.1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.000168, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "default_reasoning_effort": "medium", - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "reasoning_effort_levels": [ - "none", - "low", - "medium", - "high", - "xhigh", - "max" - ], - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-sol-pro": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-oss-120b": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-oss-120b:batch": { - "input_cost_per_token": 2.96e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 1.36e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-oss-20b": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 1.8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 9e-08, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/o1": { - "cache_read_input_token_cost": 7.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 6e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/o3-mini": { - "input_cost_per_token": 1.1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 4.4e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": false, - "cache_read_input_token_cost": 5.5e-07, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/openai/o3-mini-high": { - "input_cost_per_token": 1.1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 4.4e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": false, - "cache_read_input_token_cost": 5.5e-07, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/qwen/qwen-2.5-coder-32b-instruct": { - "input_cost_per_token": 6.6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen-vl-plus": { - "input_cost_per_token": 2.1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 6.3e-07, - "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/qwen/qwen3-coder": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_tool_choice": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-coder-plus": { - "cache_creation_input_token_cost": 8.125e-07, - "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06, - "cache_read_input_token_cost_above_128k_tokens": 3.9e-07, - "input_cost_per_token_above_32k_tokens": 1.17e-06, - "cache_creation_input_token_cost_above_32k_tokens": 1.4625e-06, - "cache_read_input_token_cost_above_32k_tokens": 2.34e-07, - "output_cost_per_token_above_32k_tokens": 5.85e-06, - "cache_read_input_token_cost": 1.3e-07, - "input_cost_per_token": 6.5e-07, - "input_cost_per_token_above_128k_tokens": 1.95e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 3.25e-06, - "output_cost_per_token_above_128k_tokens": 9.75e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-235b-a22b-2507": { - "cache_read_input_token_cost": 1.75e-08, - "input_cost_per_token": 8.75e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 3.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-235b-a22b-thinking-2507": { - "input_cost_per_token": 2.3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 2.3e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.6-plus": { - "cache_creation_input_token_cost": 4.0625e-07, - "input_cost_per_token_above_256k_tokens": 1.3e-06, - "cache_creation_input_token_cost_above_256k_tokens": 1.625e-06, - "output_cost_per_token_above_256k_tokens": 3.9e-06, - "input_cost_per_token": 3.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.95e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-35b-a3b": { - "input_cost_per_token": 3.125e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 1.5625e-07, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-27b": { - "input_cost_per_token": 1.95e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.56e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-122b-a10b": { - "input_cost_per_token": 2.6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 2.08e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-flash-02-23": { - "input_cost_per_token": 6.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 2.6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-plus-02-15": { - "input_cost_per_token": 2.6e-07, - "input_cost_per_token_above_256k_tokens": 3.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.56e-06, - "output_cost_per_token_above_256k_tokens": 1.95e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-397b-a17b": { - "cache_read_input_token_cost": 2.25e-07, - "input_cost_per_token": 5.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 3.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/switchpoint/router": { - "input_cost_per_token": 8.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3.4e-06, - "source": "https://openrouter.ai/switchpoint/router", - "supports_tool_choice": true - }, - "openrouter/undi95/remm-slerp-l2-13b": { - "input_cost_per_token": 3.5e-07, - "litellm_provider": "openrouter", - "max_tokens": 5529, - "mode": "chat", - "output_cost_per_token": 6.5e-07, - "supports_tool_choice": false, - "max_input_tokens": 6144, - "max_output_tokens": 5529, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/x-ai/grok-4": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/x-ai/grok-4", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "openrouter/z-ai/glm-4.6": { - "input_cost_per_token": 4.3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.75e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "cache_read_input_token_cost": 8e-08, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.6:exacto": { - "input_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 202800, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 1.9e-06, - "source": "https://openrouter.ai/z-ai/glm-4.6:exacto", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "openrouter/xiaomi/mimo-v2-flash": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 1e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true - }, - "openrouter/xiaomi/mimo-v2.5-pro": { - "input_cost_per_token": 4.35e-07, - "output_cost_per_token": 8.7e-07, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 3.6e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/xiaomi/mimo-v2.5": { - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 2.8e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_pdf_input": false, - "supports_video_input": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.7": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.75e-06, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_assistant_prefill": true, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_response_schema": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.7-flash": { - "input_cost_per_token": 6.05e-08, - "output_cost_per_token": 4e-07, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 1e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": false, - "supports_response_schema": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5": { - "cache_read_input_token_cost": 1.2e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.92e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.1": { - "input_cost_per_token": 9.66e-07, - "output_cost_per_token": 3.036e-06, - "cache_read_input_token_cost": 1.794e-07, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m2.1": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-10-08", - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_computer_use": false, - "supports_pdf_input": false, - "supports_response_schema": true, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m2.5": { - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 1.08e-06, - "cache_read_input_token_cost": 2.7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_computer_use": false, - "supports_pdf_input": false, - "supports_response_schema": true, - "supports_web_search": false - }, - "openrouter/openrouter/auto": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_tokens": 2000000, - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true - }, - "openrouter/openrouter/free": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_tokens": 200000, - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true - }, - "openrouter/openrouter/bodybuilder": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_tokens": 128000, - "mode": "chat" - }, "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { "input_cost_per_token": 6.7e-07, "litellm_provider": "ovhcloud", @@ -43613,66 +45918,6 @@ "supports_response_schema": true, "supports_tool_choice": false }, - "palm/chat-bison": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/chat-bison-001": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "completion", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-001": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "completion", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-safety-off": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "completion", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-safety-recitation-off": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "completion", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, "parallel_ai/search": { "input_cost_per_query": 0.005, "litellm_provider": "parallel_ai", @@ -43794,6 +46039,54 @@ "mode": "chat", "output_cost_per_token": 2.8e-07 }, + "perplexity/pplx-decider-v1-27b": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/api-reference/decisions-post" + }, + "perplexity/pplx-decider-v1.1-27b": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/getting-started/pricing" + }, + "perplexity/pplx-decider-v1.2": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, + "perplexity/pplx-decider-latest": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, + "perplexity/pplx-decider-flash-v1.2": { + "input_cost_per_token": 1e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, + "perplexity/pplx-decider-flash-latest": { + "input_cost_per_token": 1e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, "perplexity/sonar": { "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", @@ -44160,6 +46453,14 @@ "supports_reasoning": true, "supports_function_calling": true }, + "perplexity/perplexity/deepseek-v4-pro-0813": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1.32e-06, + "output_cost_per_token": 3.96e-06, + "cache_read_input_token_cost": 4.4e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/perplexity/glm-5.2": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, @@ -44260,42 +46561,52 @@ "supports_reasoning": true }, "qwen.qwen3-coder-480b-a35b-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 262000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.8e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-west-2/index.json" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html" }, "qwen.qwen3-235b-a22b-2507-v1:0": { "input_cost_per_token": 2.2e-07, + "input_cost_per_token_flex": 1.1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8.8e-07, + "output_cost_per_token_flex": 4.4e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "input_cost_per_token_batches": 1.1e-07, - "output_cost_per_token_batches": 4.4e-07 + "output_cost_per_token_batches": 4.4e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html" }, "qwen.qwen3-coder-30b-a3b-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -44303,12 +46614,19 @@ }, "qwen.qwen3-32b-v1:0": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -44333,12 +46651,12 @@ "bedrock/ap-northeast-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44349,12 +46667,12 @@ "bedrock/ap-south-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44365,12 +46683,12 @@ "bedrock/ap-southeast-2/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.545e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.236e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44381,12 +46699,12 @@ "bedrock/eu-west-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44397,12 +46715,12 @@ "bedrock/eu-west-2/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 2.3e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.86e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44413,12 +46731,12 @@ "bedrock/sa-east-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44428,13 +46746,17 @@ }, "qwen.qwen3-vl-235b-a22b": { "input_cost_per_token": 5.3e-07, + "input_cost_per_token_batches": 2.6e-07, + "input_cost_per_token_priority": 9.3e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.66e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.33e-06, + "output_cost_per_token_priority": 4.66e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -44444,16 +46766,22 @@ }, "qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.75e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -45157,6 +47485,53 @@ "supports_vision": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, + "scx-ai/DeepSeek-V4.1-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "scx-ai", + "max_input_tokens": 1000000, + "max_output_tokens": 375000, + "max_tokens": 375000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://scx.ai/models/deepseek-v4-1-flash", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "scx-ai/GLM-5.3": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 9.8e-07, + "litellm_provider": "scx-ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.08e-06, + "source": "https://scx.ai/models/glm-5-3", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "scx-ai/Kimi-K3": { + "cache_read_input_token_cost": 2.8e-07, + "input_cost_per_token": 2.83e-06, + "litellm_provider": "scx-ai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.413e-05, + "source": "https://scx.ai/models/kimi-k3", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, "scx-ai/GLM-5.2": { "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 6.1e-07, @@ -45607,78 +47982,169 @@ "mode": "image_edit", "output_cost_per_image": 0.4 }, + "us.stability.stable-conservative-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.4, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-creative-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.6 }, + "us.stability.stable-creative-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.6, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-fast-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.03 }, + "us.stability.stable-fast-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.03, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-outpaint-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.06 }, + "us.stability.stable-outpaint-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.06, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-control-sketch-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-control-sketch-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-control-structure-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-control-structure-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-erase-object-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-erase-object-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-inpaint-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-inpaint-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-remove-background-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-remove-background-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-search-recolor-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-search-recolor-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-search-replace-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-search-replace-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-style-guide-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-style-guide-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-style-transfer-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.08 }, + "us.stability.stable-style-transfer-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.08, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-core-v1:1": { "litellm_provider": "bedrock", "max_input_tokens": 77, @@ -45909,14 +48375,6 @@ "mode": "embedding", "output_cost_per_token": 0.0 }, - "together_ai/baai/bge-base-en-v1.5": { - "input_cost_per_token": 8e-09, - "litellm_provider": "together_ai", - "max_input_tokens": 512, - "mode": "embedding", - "output_cost_per_token": 0.0, - "output_vector_size": 768 - }, "together_ai/BAAI/bge-base-en-v1.5": { "input_cost_per_token": 8e-09, "litellm_provider": "together_ai", @@ -45960,6 +48418,7 @@ "supports_tool_choice": true }, "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "deprecation_date": "2026-10-22", "input_cost_per_token": 1.04e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -46082,7 +48541,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 4.5e-06, - "source": "https://api.together.ai/v1/models", + "source": "https://www.together.ai/pricing", "supports_prompt_caching": true }, "together_ai/Qwen/Qwen3.7-Plus": { @@ -46116,7 +48575,7 @@ }, "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-09-29", + "deprecation_date": "2026-10-22", "input_cost_per_token": 1.4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -46146,7 +48605,6 @@ }, "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { "cache_read_input_token_cost": 1.3e-07, - "deprecation_date": "2026-09-29", "input_cost_per_token": 1.32e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -46171,6 +48629,19 @@ "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, + "together_ai/meta-models/Muse-Spark-Open-816B-A42B": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "source": "https://docs.together.ai/docs/serverless-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, "together_ai/moonshotai/Kimi-K3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -46261,6 +48732,7 @@ "supports_vision": true }, "tts-1": { + "deprecation_date": "2027-01-06", "input_cost_per_character": 1.5e-05, "litellm_provider": "openai", "mode": "audio_speech", @@ -46270,6 +48742,7 @@ ] }, "tts-1-hd": { + "deprecation_date": "2027-01-06", "input_cost_per_character": 3e-05, "litellm_provider": "openai", "mode": "audio_speech", @@ -46327,12 +48800,15 @@ "us.amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, + "output_cost_per_token_batches": 1.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -46343,12 +48819,15 @@ "us.amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 8.75e-09, "input_cost_per_token": 3.5e-08, + "input_cost_per_token_batches": 1.75e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, + "output_cost_per_token_batches": 7e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, @@ -46356,13 +48835,22 @@ }, "us.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 8e-07, + "input_cost_per_token_batches": 4e-07, + "input_cost_per_token_flex": 4e-07, + "input_cost_per_token_priority": 1.4e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -46414,7 +48902,11 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -46512,7 +49004,11 @@ "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-1-20250805-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, @@ -46524,6 +49020,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -46550,7 +49047,11 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -46581,7 +49082,11 @@ "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "us-gov.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -46606,6 +49111,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -46615,7 +49121,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -46640,6 +49151,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -46649,7 +49161,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -46682,7 +49199,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -46717,7 +49239,12 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.5e-05, @@ -46751,7 +49278,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-fable-5-1", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, @@ -46771,6 +49303,7 @@ "supports_vision": false }, "us-gov.nvidia.nemotron-nano-12b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.4e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -46778,6 +49311,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, @@ -46785,6 +49319,7 @@ "supports_response_schema": true }, "us-gov.nvidia.nemotron-nano-9b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -46792,6 +49327,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, @@ -46819,10 +49355,16 @@ "input_cost_per_token": 8.4e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -46832,19 +49374,31 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "us-gov.xai.grok-4.6": { + "supports_regex_lookaround": false, "input_cost_per_token": 2.64e-06, "output_cost_per_token": 7.92e-06, "cache_read_input_token_cost": 6.6e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, @@ -46882,7 +49436,11 @@ "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, "output_cost_per_token_batches": 2.75e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -46941,7 +49499,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -46974,7 +49536,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.875e-06, @@ -47007,7 +49573,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -47019,7 +49589,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -47040,29 +49610,41 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "us.deepseek.r1-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.35e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", "supports_function_calling": false, "supports_reasoning": true, "supports_tool_choice": false }, "us.deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, + "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, + "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -47073,12 +49655,14 @@ }, "eu.deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -47088,51 +49672,64 @@ "supports_vision": false }, "us.meta.llama3-1-405b-instruct-v1:0": { - "input_cost_per_token": 5.32e-06, + "deprecation_date": "2026-07-07", + "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.6e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-1-70b-instruct-v1:0": { - "input_cost_per_token": 9.9e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 9.9e-07, - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-1-8b-instruct-v1:0": { - "input_cost_per_token": 2.2e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2.2e-07, - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-2-11b-instruct-v1:0": { - "input_cost_per_token": 3.5e-07, + "deprecation_date": "2027-03-30", + "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.5e-07, + "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-1-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "output_cost_per_token_batches": 1.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-2-11b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "input_cost_per_token": 1.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.6e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true }, "us.meta.llama3-2-1b-instruct-v1:0": { + "deprecation_date": "2026-07-07", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -47140,10 +49737,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-2-3b-instruct-v1:0": { + "deprecation_date": "2026-07-07", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -47151,42 +49750,51 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-2-90b-instruct-v1:0": { - "input_cost_per_token": 2e-06, + "deprecation_date": "2026-07-07", + "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 7.2e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true }, "us.meta.llama3-3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama4-maverick-17b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9.7e-07, "output_cost_per_token_batches": 4.85e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", "supported_modalities": [ "text", "image" @@ -47199,15 +49807,17 @@ "supports_tool_choice": false }, "us.meta.llama4-scout-17b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.7e-07, "input_cost_per_token_batches": 8.5e-08, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 10000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_batches": 3.3e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", "supported_modalities": [ "text", "image" @@ -47223,11 +49833,11 @@ "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md", "supports_function_calling": true, "supports_tool_choice": false }, @@ -47617,7 +50227,7 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -49389,7 +51999,8 @@ "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_creation_input_token_cost_batches": 1.88e-06 }, "vertex_ai/claude-sonnet-5": { "deprecation_date": "2026-12-24", @@ -49446,7 +52057,7 @@ "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -49497,7 +52108,8 @@ "supports_vision": true, "supports_native_streaming": true, "prompt_cache_min_tokens": 1024, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_creation_input_token_cost_batches": 1.88e-06 }, "vertex_ai/mistralai/codestral-2@001": { "input_cost_per_token": 3e-07, @@ -49618,7 +52230,7 @@ "supported_regions": [ "global" ], - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -49639,7 +52251,7 @@ "supported_regions": [ "us-central1" ], - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -49666,7 +52278,8 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -49723,7 +52336,14 @@ "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "supports_reasoning": false, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ] + }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -49750,17 +52370,26 @@ "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "supports_reasoning": false, - "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" + "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ] + }, "vertex_ai/gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, + "cache_read_input_token_cost_priority": 9e-08, "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -49771,8 +52400,17 @@ "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.4e-06, + "regional_endpoint_uplift_multiplier": 1.1, "supports_reasoning": false, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ] + }, "vertex_ai/gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -49790,16 +52428,26 @@ "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "supports_reasoning": false, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ] + }, "vertex_ai/gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2027-06-28", "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, @@ -49810,10 +52458,12 @@ "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.7e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -49880,6 +52530,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -49942,6 +52593,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -49990,6 +52642,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -50002,6 +52655,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -50015,7 +52669,7 @@ "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, - "mode": "image_generation", + "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, @@ -50900,6 +53554,26 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, + "voyage/rerank-1": { + "input_cost_per_token": 5e-08, + "litellm_provider": "voyage", + "max_input_tokens": 8000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://docs.voyageai.com/docs/pricing" + }, + "voyage/rerank-lite-1": { + "input_cost_per_token": 2e-08, + "litellm_provider": "voyage", + "max_input_tokens": 4000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://docs.voyageai.com/docs/pricing" + }, "voyage/rerank-2.5": { "input_cost_per_token": 5e-08, "litellm_provider": "voyage", @@ -51036,6 +53710,16 @@ "mode": "embedding", "output_cost_per_token": 0.0 }, + "voyage/voyage-large-2-instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.voyageai.com/docs/pricing" + }, "voyage/voyage-law-2": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", @@ -51585,13 +54269,16 @@ }, "xai/grok-4.20-0309-reasoning": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, @@ -51599,8 +54286,11 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true @@ -51629,9 +54319,13 @@ "xai/grok-4.3": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_image_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, @@ -51639,6 +54333,8 @@ "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -51651,9 +54347,13 @@ "xai/grok-4.3-latest": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_image_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, @@ -51661,6 +54361,8 @@ "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -51781,53 +54483,71 @@ "supports_web_search": true }, "zai.glm-4.7": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_flex": 1.1e-06, + "output_cost_per_token_priority": 3.85e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "zai.glm-5": { "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "input_cost_per_token_priority": 1.75e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "zai.glm-4.7-flash": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3.5e-08, + "input_cost_per_token_flex": 3.5e-08, + "input_cost_per_token_priority": 1.225e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_flex": 2e-07, + "output_cost_per_token_priority": 7e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -52036,6 +54756,70 @@ "litellm_provider": "vertex_ai", "mode": "vector_store" }, + "vertex_ai/semantic-ranker-default": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-default-002": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-default-003": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-default-004": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-default@latest": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-fast": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-fast-004": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-fast@latest": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, "openai/container": { "code_interpreter_cost_per_session": 0.03, "litellm_provider": "openai", @@ -52084,7 +54868,7 @@ ] }, "azure/sora-2": { - "deprecation_date": "2026-10-15", + "deprecation_date": "2026-11-02", "litellm_provider": "azure", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, @@ -52794,7 +55578,7 @@ }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt": { "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, @@ -52803,7 +55587,7 @@ }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt": { "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, @@ -53263,7 +56047,7 @@ }, "fireworks_ai/accounts/fireworks/models/minimax-m2": { "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 196608, "max_output_tokens": 4096, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, @@ -53434,7 +56218,7 @@ }, "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl": { "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, @@ -53497,7 +56281,7 @@ }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2": { "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -53506,7 +56290,7 @@ }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2": { "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -54102,7 +56886,7 @@ }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16": { "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, @@ -54127,15 +56911,6 @@ "litellm_provider": "fireworks_ai", "mode": "embedding" }, - "fireworks_ai/accounts/fireworks/models/": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai", - "mode": "embedding" - }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct": { "max_tokens": 4096, "max_input_tokens": 4096, @@ -54229,7 +57004,7 @@ }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct": { "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -56098,6 +58873,7 @@ ] }, "gpt-4o-mini-tts-2025-12-15": { + "deprecation_date": "2027-01-06", "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", @@ -56316,6 +59092,7 @@ ] }, "gemini-2.0-flash-exp-image-generation": { + "deprecation_date": "2025-11-14", "input_cost_per_token": 0.0, "litellm_provider": "gemini", "max_input_tokens": 32768, @@ -56336,6 +59113,7 @@ "supports_vision": true }, "gemini/gemini-2.0-flash-exp-image-generation": { + "deprecation_date": "2025-11-14", "input_cost_per_token": 0.0, "litellm_provider": "gemini", "max_input_tokens": 32768, @@ -56410,6 +59188,7 @@ "gemini_native_audio": true }, "gemini-2.5-flash-native-audio-preview-12-2025": { + "deprecation_date": "2026-11-17", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", @@ -56440,6 +59219,7 @@ "supports_web_search": true }, "gemini-3.1-flash-live-preview": { + "deprecation_date": "2026-11-17", "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, @@ -56601,6 +59381,7 @@ "gemini_native_audio": true }, "gemini/gemini-2.5-flash-native-audio-preview-12-2025": { + "deprecation_date": "2026-11-17", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", @@ -56630,9 +59411,11 @@ "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_reasoning": true }, "gemini/gemini-3.1-flash-live-preview": { + "deprecation_date": "2026-11-17", "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, @@ -56668,9 +59451,11 @@ "rpm": 10, "gemini_audio_only_live": true, "input_cost_per_second": 8.33333333333e-05, - "supports_response_schema": false + "supports_response_schema": false, + "supports_reasoning": true }, "gemini/gemini-3.1-flash-tts-preview": { + "deprecation_date": "2026-11-17", "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", @@ -56713,7 +59498,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" - ] + ], + "supports_prompt_caching": true }, "gemini/gemini-3.8-flash-lite-tts": { "cache_read_input_token_cost": 1.25e-07, @@ -56737,9 +59523,11 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" - ] + ], + "supports_prompt_caching": true }, "gemini-2.5-flash-preview-tts": { + "deprecation_date": "2026-11-17", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", @@ -57101,7 +59889,7 @@ "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -57130,12 +59918,19 @@ }, "bedrock_mantle/openai.gpt-oss-120b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, + "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -57148,12 +59943,19 @@ }, "bedrock_mantle/openai.gpt-oss-20b": { "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3.5e-08, + "input_cost_per_token_flex": 3.5e-08, + "input_cost_per_token_priority": 1.225e-07, "output_cost_per_token": 3e-07, + "output_cost_per_token_flex": 1.5e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_priority": 5.25e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -57166,12 +59968,19 @@ }, "bedrock_mantle/openai.gpt-oss-safeguard-120b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "output_cost_per_token": 6e-07, + "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], @@ -57182,12 +59991,19 @@ }, "bedrock_mantle/openai.gpt-oss-safeguard-20b": { "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.2e-07, "output_cost_per_token": 2e-07, + "output_cost_per_token_flex": 1e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 1e-07, + "output_cost_per_token_priority": 3.5e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], @@ -57231,6 +60047,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57274,6 +60091,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57288,10 +60106,11 @@ "cache_read_input_token_cost": 1.375e-06, "output_cost_per_token": 8.25e-05, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 272000, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-cyber.html", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" @@ -57306,6 +60125,7 @@ "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57382,6 +60202,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57391,6 +60212,7 @@ "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html" }, "us.openai.gpt-5.6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 4.4e-06, "input_cost_per_token_above_272k_tokens": 8.8e-06, "cache_creation_input_token_cost": 5.5e-06, @@ -57400,11 +60222,12 @@ "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ "text", "image" @@ -57421,10 +60244,12 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "global.openai.gpt-5.6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "cache_creation_input_token_cost": 5e-06, @@ -57434,11 +60259,12 @@ "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ "text", "image" @@ -57455,10 +60281,12 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-5.6-terra": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "cache_creation_input_token_cost": 2.75e-06, @@ -57468,11 +60296,12 @@ "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ "text", "image" @@ -57489,10 +60318,12 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "global.openai.gpt-5.6-terra": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "cache_creation_input_token_cost": 2.5e-06, @@ -57502,11 +60333,12 @@ "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ "text", "image" @@ -57523,10 +60355,12 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-5.6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, "cache_creation_input_token_cost": 2.75e-07, @@ -57536,11 +60370,12 @@ "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ "text", "image" @@ -57557,6 +60392,7 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, @@ -57568,7 +60404,8 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_above_272k_tokens": 2.475e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -57599,7 +60436,8 @@ "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -57630,7 +60468,8 @@ "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -57661,7 +60500,8 @@ "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -57685,6 +60525,7 @@ ] }, "global.openai.gpt-5.6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, "cache_creation_input_token_cost": 2.5e-07, @@ -57694,11 +60535,12 @@ "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ "text", "image" @@ -57715,6 +60557,7 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, @@ -57723,8 +60566,14 @@ "input_cost_per_token_above_272k_tokens": 2.2e-05, "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.000165, + "cache_creation_input_token_cost_ultrafast": 8.25e-05, "cache_read_input_token_cost": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-05, + "cache_read_input_token_cost_ultrafast": 6.6e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 0.000132, + "input_cost_per_token_ultrafast": 6.6e-05, "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, "litellm_provider": "bedrock_mantle", @@ -57732,6 +60581,8 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", + "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495, + "output_cost_per_token_ultrafast": 0.00033, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -57749,6 +60600,7 @@ "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57785,8 +60637,9 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57823,8 +60676,9 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57833,19 +60687,29 @@ "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html" }, "us.openai.gpt-6-astra": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1.1e-05, "input_cost_per_token_above_272k_tokens": 2.2e-05, "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.000165, + "cache_creation_input_token_cost_ultrafast": 8.25e-05, "cache_read_input_token_cost": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-05, + "cache_read_input_token_cost_ultrafast": 6.6e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 0.000132, + "input_cost_per_token_ultrafast": 6.6e-05, "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495, + "output_cost_per_token_ultrafast": 0.00033, "supported_modalities": [ "text", "image" @@ -57862,12 +60726,15 @@ "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_sampling_params": false, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "cache_creation_input_token_cost": 2.75e-06, @@ -57877,6 +60744,7 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -57891,18 +60759,21 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1.1e-07, "input_cost_per_token_above_272k_tokens": 2.2e-07, "cache_creation_input_token_cost": 1.375e-07, @@ -57912,6 +60783,7 @@ "output_cost_per_token": 5.5e-07, "output_cost_per_token_above_272k_tokens": 8.25e-07, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -57926,31 +60798,43 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "global.openai.gpt-6-astra": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015, + "cache_creation_input_token_cost_ultrafast": 7.5e-05, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05, + "cache_read_input_token_cost_ultrafast": 6e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012, + "input_cost_per_token_ultrafast": 6e-05, "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045, + "output_cost_per_token_ultrafast": 0.0003, "supported_modalities": [ "text", "image" @@ -57967,8 +60851,10 @@ "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_sampling_params": false, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, @@ -57982,6 +60868,7 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -57996,15 +60883,17 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.openai.gpt-6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "cache_creation_input_token_cost": 2.5e-06, @@ -58014,6 +60903,7 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -58028,14 +60918,16 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, @@ -58049,6 +60941,7 @@ "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -58063,15 +60956,17 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.openai.gpt-6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1e-07, "input_cost_per_token_above_272k_tokens": 2e-07, "cache_creation_input_token_cost": 1.25e-07, @@ -58081,6 +60976,7 @@ "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -58095,14 +60991,16 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, @@ -58188,12 +61086,19 @@ }, "bedrock_mantle/google.gemma-4-31b": { "input_cost_per_token": 1.4e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.45e-07, "output_cost_per_token": 4e-07, + "output_cost_per_token_flex": 2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_priority": 7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58207,12 +61112,19 @@ }, "bedrock_mantle/google.gemma-4-26b-a4b": { "input_cost_per_token": 1.3e-07, + "input_cost_per_token_batches": 6.5e-08, + "input_cost_per_token_flex": 6.5e-08, + "input_cost_per_token_priority": 2.275e-07, "output_cost_per_token": 4e-07, + "output_cost_per_token_flex": 2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_priority": 7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58226,12 +61138,19 @@ }, "bedrock_mantle/google.gemma-4-e2b": { "input_cost_per_token": 4e-08, + "input_cost_per_token_batches": 2e-08, + "input_cost_per_token_flex": 2e-08, + "input_cost_per_token_priority": 7e-08, "output_cost_per_token": 8e-08, + "output_cost_per_token_flex": 4e-08, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 4e-08, + "output_cost_per_token_priority": 1.4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58248,11 +61167,20 @@ "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_flex": 6.25e-07, + "input_cost_per_token_priority": 2.1875e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 1048576, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.375e-06, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -58262,18 +61190,24 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/xai.grok-4.6": { "use_openai_responses_path": true, "input_cost_per_token": 2.2e-06, "output_cost_per_token": 6.6e-06, "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, "max_tokens": 500000, "mode": "chat", + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -58314,15 +61248,108 @@ "input_cost_per_token_batches": 5e-07, "output_cost_per_token_batches": 2.5e-06 }, + "bedrock_mantle/anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_1hr": 8.8e-06, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 4.4e-06, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html", + "thinking_always_on": true, + "supports_forced_tool_use": false + }, + "bedrock_mantle/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, "us.xai.grok-4.6": { + "supports_regex_lookaround": false, "input_cost_per_token": 2.2e-06, "output_cost_per_token": 6.6e-06, "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, "max_tokens": 500000, "mode": "chat", + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_prompt_caching": false, @@ -58331,14 +61358,26 @@ "supports_vision": true }, "global.xai.grok-4.6": { + "supports_regex_lookaround": false, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, "max_tokens": 500000, "mode": "chat", + "output_cost_per_token_flex": 3e-06, + "output_cost_per_token_priority": 1.05e-05, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_prompt_caching": false, @@ -58400,6 +61439,41 @@ "supports_tool_choice": false, "supports_vision": true }, + "volcengine/doubao-seed-2-1-pro-260915": { + "cache_read_input_token_cost": 1.725e-07, + "input_cost_per_token": 8.625e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 1024000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4.3125e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "volcengine/doubao-seed-2-1-lite-260915": { + "cache_read_input_audio_token_cost": 3.45e-07, + "cache_read_input_token_cost": 2.3e-08, + "input_cost_per_audio_token": 1.725e-06, + "input_cost_per_token": 1.15e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 1024000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 3.88126e-07, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, "volcengine/doubao-seed-2-1-turbo-260628": { "cache_read_input_token_cost": 8.625e-08, "input_cost_per_token": 4.3125e-07, @@ -58530,6 +61604,61 @@ } ] }, + "volcengine/doubao-seedance-2-5-260628": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.216, + "output_cost_per_second_480p": 0.096075, + "output_cost_per_second_720p": 0.216, + "output_cost_per_second_1080p": 0.5346, + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "854x480", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "480x854", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s). List 70 CNY per million tokens at 480p and 720p and 77 at 1080p without a video input, matching Ark's per-resolution table and its 1080p 16:9 example of 3.74 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Accepts up to 50 reference assets (30 images, 10 videos, 10 audios) and clips of 4-30s; per-asset billing beyond the free allowance is not encoded. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, + "volcengine/doubao-seedance-2-0-260128": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.141942857, + "output_cost_per_second_480p": 0.066003429, + "output_cost_per_second_720p": 0.141942857, + "output_cost_per_second_1080p": 0.354085714, + "output_cost_per_second_4k": 0.722057143, + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 46 CNY per million tokens at 480p and 720p, 51 at 1080p, and 26 at 4k without a video input, matching Ark's per-resolution table and its 1080p and 4k 16:9 examples of 2.48 and 5.05 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s; 4k is exclusive to this tier. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, + "volcengine/doubao-seedance-2-0-fast-260128": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.114171429, + "output_cost_per_second_480p": 0.053089714, + "output_cost_per_second_720p": 0.114171429, + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 37 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, + "volcengine/doubao-seedance-2-0-mini-260615": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.070971429, + "output_cost_per_second_480p": 0.033001714, + "output_cost_per_second_720p": 0.070971429, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 23 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Only text and image inputs are declared; the mini tier's reference video and audio caps were not verified. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, "output_cost_per_token": 3.2e-06, @@ -58590,7 +61719,11 @@ "supports_native_structured_output": true, "supports_pdf_input": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, @@ -58616,7 +61749,11 @@ "supports_native_structured_output": true, "supports_pdf_input": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "snowflake/claude-sonnet-4-5": { "max_tokens": 16384, @@ -59418,16 +62555,16 @@ }, "tencent/deepseek-v4-pro": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 3.625e-09, - "input_cost_per_token": 4.35e-07, - "input_cost_per_token_cache_hit": 3.625e-09, + "cache_read_input_token_cost": 1.45e-07, + "input_cost_per_token": 1.74e-06, + "input_cost_per_token_cache_hit": 1.45e-07, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 8.7e-07, - "source": "https://www.tencentcloud.com/products/tokenhub", + "output_cost_per_token": 3.48e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], @@ -59453,7 +62590,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, - "source": "https://www.tencentcloud.com/products/tokenhub", + "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], @@ -59468,6 +62605,310 @@ "supports_reasoning": true, "supports_vision": false }, + "tencent/deepseek-v4-pro-0813": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 1.32e-06, + "input_cost_per_token_cache_hit": 4.4e-08, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 6.6e-07, + "output_cost_per_token": 1.98e-06, + "weekday_timezone": "Asia/Shanghai", + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 3.96e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "tencent/deepseek-v4.1-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_cache_hit": 6e-09, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "weekday_timezone": "Asia/Shanghai", + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 1.2e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": true + }, + "tencent/glm-5.3-flashx": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 3.7e-07, + "input_cost_per_token_cache_hit": 7.5e-08, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "tencent/glm-5.3-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_cache_hit": 3e-08, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "tencent/glm-5.3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "input_cost_per_token_cache_hit": 2.6e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/glm-5.2": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "input_cost_per_token_cache_hit": 2.6e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_cache_hit": 3e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k2.8-preview": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_cache_hit": 2.5e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k2.7-code-highspeed": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3.8e-07, + "input_cost_per_token": 1.9e-06, + "input_cost_per_token_cache_hit": 3.8e-07, + "litellm_provider": "tencent", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k2.7-code": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "input_cost_per_token_cache_hit": 1.9e-07, + "litellm_provider": "tencent", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "tencent/minimax-m3": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-08, @@ -59477,7 +62918,7 @@ "max_input_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://www.tencentcloud.com/products/tokenhub", + "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], @@ -59632,13 +63073,16 @@ }, "xai/grok-4.20-0309-non-reasoning": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -59646,20 +63090,26 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-multi-agent-0309": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": false, "supports_prompt_caching": true, @@ -59668,8 +63118,11 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true, "supported_endpoints": [ @@ -59901,6 +63354,9 @@ "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 1e-06, "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 5e-06, "search_context_cost_per_query": { @@ -59923,6 +63379,7 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, @@ -59950,6 +63407,7 @@ "supports_vision": true }, "mistral/labs-leanstral-1-5": { + "deprecation_date": "2026-09-30", "input_cost_per_token": 0.0, "litellm_provider": "mistral", "max_input_tokens": 262144, @@ -60095,8 +63553,8 @@ { "name": "claude-tool-search", "pattern": "claude-[a-z]+-(?:4[-._](?:[5-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", - "fill_missing_for_providers": ["anthropic", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], - "description": "Claude at version 4.5 or higher, in any id shape that contains claude--: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is left out on purpose: Anthropic documents tool search as unavailable on Azure-hosted Foundry deployments, and the azure_ai/ key cannot tell those from Anthropic-hosted ones.", + "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "description": "Claude at version 4.5 or higher, in any id shape that contains claude--: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is included because Microsoft Foundry runs tool search for Claude on both Anthropic-hosted and Azure-hosted deployments.", "model_info": { "supports_tool_search": true } @@ -60170,6 +63628,9 @@ "input_cost_per_audio_token": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "gemini", + "max_input_tokens": 98304, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "audio_transcription", "output_cost_per_token": 1.2e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -60192,6 +63653,9 @@ "input_cost_per_audio_token": 3.5e-06, "input_cost_per_token": 3.5e-06, "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "audio_transcription", "output_cost_per_token": 2.1e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -60248,7 +63712,7 @@ }, "vertex_ai/gemini-3.5-live-translate-preview": { "input_cost_per_audio_token": 3.5e-06, - "input_cost_per_second": 8.83333333333e-05, + "input_cost_per_second": 8.75e-05, "input_cost_per_token": 3.5e-06, "litellm_provider": "vertex_ai", "mode": "realtime", @@ -60370,18 +63834,18 @@ "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": { - "cache_read_input_token_cost": 7e-09, - "cache_read_input_token_cost_priority": 8.75e-09, - "input_cost_per_token": 2.2e-07, - "input_cost_per_token_priority": 2.75e-07, + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 6.6e-07, - "output_cost_per_token_priority": 8.25e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -60391,13 +63855,16 @@ }, "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-us": { "cache_read_input_token_cost": 9e-09, + "cache_read_input_token_cost_priority": 1.125e-08, "input_cost_per_token": 4.5e-07, + "input_cost_per_token_priority": 5.625e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.8e-06, + "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -60408,13 +63875,16 @@ }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp": { "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, "deprecation_date": "2026-09-25", "input_cost_per_token": 2.2e-07, + "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, + "output_cost_per_token_priority": 8.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, @@ -60466,18 +63936,18 @@ "supports_vision": false }, "fireworks_ai/deepseek-v4p1-flash": { - "cache_read_input_token_cost": 7e-09, - "cache_read_input_token_cost_priority": 8.75e-09, - "input_cost_per_token": 2.2e-07, - "input_cost_per_token_priority": 2.75e-07, + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 6.6e-07, - "output_cost_per_token_priority": 8.25e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -60487,13 +63957,16 @@ }, "fireworks_ai/deepseek-v4p1-flash-us": { "cache_read_input_token_cost": 9e-09, + "cache_read_input_token_cost_priority": 1.125e-08, "input_cost_per_token": 4.5e-07, + "input_cost_per_token_priority": 5.625e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.8e-06, + "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -60504,13 +63977,16 @@ }, "fireworks_ai/deepseek-v4-flash-vision-exp": { "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, "deprecation_date": "2026-09-25", "input_cost_per_token": 2.2e-07, + "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, + "output_cost_per_token_priority": 8.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, @@ -60639,14 +64115,17 @@ }, "fireworks_ai/muse-glimmer-30b": { "cache_read_input_token_cost": 4e-08, + "cache_read_input_token_cost_priority": 6e-08, "deprecation_date": "2026-09-25", "input_cost_per_token": 3.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, + "output_cost_per_token_priority": 2.25e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, @@ -60656,14 +64135,18 @@ }, "fireworks_ai/nemotron-lightning-3p5-30b-a3b": { "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_priority": 1.25e-08, + "deprecation_date": "2026-11-07", "input_cost_per_token": 5e-08, + "input_cost_per_token_priority": 6.25e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 2.5e-07, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60672,14 +64155,18 @@ }, "fireworks_ai/nemotron-3-ultra-nvfp4": { "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_priority": 1.5e-07, + "deprecation_date": "2026-11-07", "input_cost_per_token": 6e-07, + "input_cost_per_token_priority": 7.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "output_cost_per_token_priority": 3e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60688,14 +64175,17 @@ }, "fireworks_ai/accounts/fireworks/models/muse-glimmer-30b": { "cache_read_input_token_cost": 4e-08, + "cache_read_input_token_cost_priority": 6e-08, "deprecation_date": "2026-09-25", "input_cost_per_token": 3.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, + "output_cost_per_token_priority": 2.25e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, @@ -60703,16 +64193,31 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/accounts/fireworks/models/muse-spark-open": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "source": "https://fireworks.ai/models/fireworks/muse-spark-open", + "supports_function_calling": true, + "supports_vision": true + }, "fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": { "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_priority": 1.25e-08, + "deprecation_date": "2026-11-07", "input_cost_per_token": 5e-08, + "input_cost_per_token_priority": 6.25e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 2.5e-07, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60721,14 +64226,18 @@ }, "fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4": { "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_priority": 1.5e-07, + "deprecation_date": "2026-11-07", "input_cost_per_token": 6e-07, + "input_cost_per_token_priority": 7.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "output_cost_per_token_priority": 3e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -62352,6 +65861,7 @@ "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_vision": true, "source": "https://deepinfra.com/pricing", "supports_audio_input": true @@ -62836,6 +66346,40 @@ "supports_vision": false, "source": "https://deepinfra.com/pricing" }, + "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash": { + "max_tokens": 131072, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4.2e-07, + "cache_read_input_token_cost": 4.2e-09, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash" + }, + "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "max_tokens": 131072, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4.2e-07, + "cache_read_input_token_cost": 4.2e-09, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash-1017" + }, "deepinfra/openai/gpt-oss-120b-Ultra": { "max_tokens": 131072, "max_input_tokens": 131072, @@ -62944,13 +66488,16 @@ }, "xai/grok-4.20": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, @@ -62958,21 +66505,27 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-reasoning": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, @@ -62980,21 +66533,27 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-reasoning-latest": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, @@ -63002,8 +66561,11 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true @@ -63158,6 +66720,23 @@ "video" ] }, + "xai/grok-imagine-video-1.5-lite": { + "input_cost_per_image": 0.01, + "litellm_provider": "xai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "output_cost_per_second_1080p": 0.14, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_720p": 0.03, + "source": "https://docs.x.ai/developers/pricing", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, "xai/grok-imagine-video-1.5-2026-05-30": { "input_cost_per_image": 0.01, "litellm_provider": "xai", @@ -63195,6 +66774,7 @@ ] }, "xai/grok-voice-transcribe-1.0": { + "deprecation_date": "2026-10-02", "input_cost_per_second": 2.778e-05, "litellm_provider": "xai", "metadata": { @@ -63240,13 +66820,16 @@ }, "xai/grok-4.20-non-reasoning": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -63254,20 +66837,26 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-non-reasoning-latest": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -63275,20 +66864,26 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-multi-agent": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supported_endpoints": [ "/v1/responses" @@ -63300,20 +66895,26 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-multi-agent-latest": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supported_endpoints": [ "/v1/responses" @@ -63325,15 +66926,18 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "groq/qwen/qwen3.8-27b": { "input_cost_per_token": 8e-07, "litellm_provider": "groq", - "max_input_tokens": 131042, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -63595,13 +67199,16 @@ }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-us": { "cache_read_input_token_cost": 3.9e-07, + "cache_read_input_token_cost_priority": 4.875e-07, "input_cost_per_token": 2.1e-06, + "input_cost_per_token_priority": 2.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.6e-06, + "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_reasoning": true, @@ -63630,13 +67237,16 @@ }, "fireworks_ai/glm-5p3-us": { "cache_read_input_token_cost": 3.9e-07, + "cache_read_input_token_cost_priority": 4.875e-07, "input_cost_per_token": 2.1e-06, + "input_cost_per_token_priority": 2.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.6e-06, + "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_reasoning": true, @@ -63659,6 +67269,33 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/auto": { + "litellm_provider": "fireworks_ai", + "mode": "chat", + "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/routers/auto-instant": { + "litellm_provider": "fireworks_ai", + "mode": "chat", + "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/routers/firerouter": { + "litellm_provider": "fireworks_ai", + "mode": "chat", + "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "fireworks_ai/glm-5p3-fast": { "cache_read_input_token_cost": 3.9e-07, "input_cost_per_token": 2.1e-06, @@ -63693,12 +67330,16 @@ }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us": { "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_priority": 5.625e-08, + "deprecation_date": "2026-11-07", "input_cost_per_token": 2.25e-07, + "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, + "output_cost_per_token_priority": 9.375e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_response_schema": true, @@ -63724,12 +67365,16 @@ }, "fireworks_ai/glm-5p3-flash-us": { "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_priority": 5.625e-08, + "deprecation_date": "2026-11-07", "input_cost_per_token": 2.25e-07, + "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, + "output_cost_per_token_priority": 9.375e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_response_schema": true, @@ -63738,13 +67383,17 @@ }, "fireworks_ai/accounts/fireworks/models/inkling": { "cache_read_input_token_cost": 1.7e-07, + "cache_read_input_token_cost_priority": 1.7e-07, + "deprecation_date": "2026-11-07", "input_cost_per_token": 1e-06, + "input_cost_per_token_priority": 1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.05e-06, - "source": "https://fireworks.ai/models/fireworks/inkling", + "output_cost_per_token_priority": 4.05e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -63776,12 +67425,12 @@ "supports_tool_choice": true }, "together_ai/Qwen/Qwen3.8-Flash": { - "input_cost_per_token": 9e-08, + "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 2.82e-07, + "output_cost_per_token": 4.7e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/moonshotai/Kimi-K2.5-fp4": { @@ -63818,6 +67467,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { + "deprecation_date": "2026-02-25", "input_cost_per_token": 6e-08, "output_cost_per_token": 2.5e-07, "litellm_provider": "together_ai", @@ -63889,7 +67539,7 @@ }, "azure_ai/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, - "deprecation_date": "2026-10-03", + "deprecation_date": "2027-04-16", "input_cost_per_token": 9.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, @@ -63912,52 +67562,26 @@ "supports_vision": true }, "azure_ai/deepseek-v4.1-flash": { - "cache_read_input_token_cost": 8e-09, - "input_cost_per_token": 3.75e-07, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 1.5e-06, + "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "deprecation_date": "2026-12-15", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure_ai/muse-spark-1.3": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 4.25e-06, - "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/deepseek-v4-1-flash-is-coming-to-microsoft-foundry/4556431" }, "azure_ai/MAI-Image-2.6": { "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", + "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image_token": 3.8e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -63970,6 +67594,7 @@ "input_cost_per_image_token": 2.5e-06, "input_cost_per_token": 1.75e-06, "litellm_provider": "azure_ai", + "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image_token": 1.9e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -64090,6 +67715,7 @@ "supports_vision": true }, "azure_ai/deepseek-r1": { + "deprecation_date": "2026-08-13", "input_cost_per_token": 1.35e-06, "output_cost_per_token": 5.4e-06, "litellm_provider": "azure_ai", @@ -64097,6 +67723,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure_ai/deepseek-v3-0324": { + "deprecation_date": "2026-07-13", "input_cost_per_token": 1.14e-06, "output_cost_per_token": 4.56e-06, "litellm_provider": "azure_ai", @@ -64104,6 +67731,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure_ai/deepseek-v3.1": { + "deprecation_date": "2026-07-13", "input_cost_per_token": 1.23e-06, "output_cost_per_token": 4.94e-06, "litellm_provider": "azure_ai", @@ -64111,6 +67739,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure_ai/grok-3": { + "deprecation_date": "2026-05-01", "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "litellm_provider": "azure_ai", @@ -64118,6 +67747,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure_ai/grok-3-mini": { + "deprecation_date": "2026-05-01", "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.27e-06, "litellm_provider": "azure_ai", @@ -64125,6 +67755,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure_ai/grok-4-fast-non-reasoning": { + "deprecation_date": "2026-05-01", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", @@ -64132,6 +67763,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure_ai/grok-4-fast-reasoning": { + "deprecation_date": "2026-05-01", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", @@ -64156,6 +67788,7 @@ "supports_vision": false }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.4e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -64163,6 +67796,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, @@ -64170,6 +67804,7 @@ "supports_response_schema": true }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-9b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -64177,6 +67812,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, @@ -64204,10 +67840,16 @@ "input_cost_per_token": 8.4e-08, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64217,10 +67859,16 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64248,6 +67896,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64257,7 +67906,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -64281,6 +67935,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64290,7 +67945,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -64322,7 +67982,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -64357,7 +68022,12 @@ "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, "supports_forced_tool_use": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.5e-05, @@ -64390,7 +68060,12 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "token_count_model": { + "model": "anthropic.claude-fable-5-1", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, @@ -64410,6 +68085,7 @@ "supports_vision": false }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.4e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -64417,6 +68093,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, @@ -64424,6 +68101,7 @@ "supports_response_schema": true }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-9b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -64431,6 +68109,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, @@ -64458,10 +68137,16 @@ "input_cost_per_token": 8.4e-08, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64471,10 +68156,16 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64502,6 +68193,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64535,6 +68227,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64672,14 +68365,15 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "input_cost_per_token": 2.64e-06, - "input_cost_per_token_above_272k_tokens": 5.28e-06, - "cache_creation_input_token_cost": 3.3e-06, - "cache_creation_input_token_cost_above_272k_tokens": 6.6e-06, - "cache_read_input_token_cost": 2.64e-07, - "cache_read_input_token_cost_above_272k_tokens": 5.28e-07, - "output_cost_per_token": 1.584e-05, - "output_cost_per_token_above_272k_tokens": 2.376e-05 + "input_cost_per_token": 2.7e-06, + "input_cost_per_token_above_272k_tokens": 5.4e-06, + "cache_creation_input_token_cost": 3.375e-06, + "cache_creation_input_token_cost_above_272k_tokens": 6.75e-06, + "cache_read_input_token_cost": 2.7e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.4e-07, + "output_cost_per_token": 1.62e-05, + "output_cost_per_token_above_272k_tokens": 2.43e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html" }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna": { "litellm_provider": "bedrock_mantle", @@ -64707,14 +68401,15 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "input_cost_per_token": 2.64e-07, - "input_cost_per_token_above_272k_tokens": 5.28e-07, - "cache_creation_input_token_cost": 3.3e-07, - "cache_creation_input_token_cost_above_272k_tokens": 6.6e-07, - "cache_read_input_token_cost": 2.64e-08, - "cache_read_input_token_cost_above_272k_tokens": 5.28e-08, - "output_cost_per_token": 1.584e-06, - "output_cost_per_token_above_272k_tokens": 2.376e-06 + "input_cost_per_token": 2.7e-07, + "input_cost_per_token_above_272k_tokens": 5.4e-07, + "cache_creation_input_token_cost": 3.375e-07, + "cache_creation_input_token_cost_above_272k_tokens": 6.75e-07, + "cache_read_input_token_cost": 2.7e-08, + "cache_read_input_token_cost_above_272k_tokens": 5.4e-08, + "output_cost_per_token": 1.62e-06, + "output_cost_per_token_above_272k_tokens": 2.43e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html" }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.4": { "litellm_provider": "bedrock_mantle", @@ -64741,9 +68436,10 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "input_cost_per_token": 3.3e-06, - "cache_read_input_token_cost": 3.3e-07, - "output_cost_per_token": 1.98e-05 + "input_cost_per_token": 3.375e-06, + "cache_read_input_token_cost": 3.375e-07, + "output_cost_per_token": 2.025e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html" }, "bedrock_mantle/us-gov-west-1/xai.grok-4.3": { "use_openai_responses_path": true, @@ -64849,9 +68545,10 @@ "output_cost_per_token": 3.6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -64867,9 +68564,10 @@ "output_cost_per_token": 7.2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -64880,6 +68578,77 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "bedrock_mantle/us-gov-west-1/anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 6e-06, + "cache_creation_input_token_cost_above_1hr": 9.6e-06, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 4.8e-06, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html" + }, + "bedrock_mantle/us-gov-west-1/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, "bedrock_mantle/us-gov-east-1/openai.gpt-5.4": { "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, @@ -64935,9 +68704,10 @@ "output_cost_per_token": 3.6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -64953,9 +68723,10 @@ "output_cost_per_token": 7.2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -64967,91 +68738,131 @@ "supports_tool_choice": true }, "bedrock_mantle/deepseek.v3.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 5.8e-07, + "input_cost_per_token_batches": 2.9e-07, + "input_cost_per_token_flex": 2.9e-07, + "input_cost_per_token_priority": 1.015e-06, "output_cost_per_token": 1.68e-06, + "output_cost_per_token_flex": 8.4e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 8.4e-07, + "output_cost_per_token_priority": 2.94e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.38e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-235b-a22b-2507": { "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "input_cost_per_token_flex": 1.1e-07, + "input_cost_per_token_priority": 3.85e-07, "output_cost_per_token": 8.8e-07, + "output_cost_per_token_flex": 4.4e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 4.4e-07, + "output_cost_per_token_priority": 1.54e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-32b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, + "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 32000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-32b.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, + "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-30b-a3b-instruct.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.5e-07, + "input_cost_per_token_batches": 2.25e-07, + "input_cost_per_token_flex": 2.25e-07, + "input_cost_per_token_priority": 7.875e-07, "output_cost_per_token": 1.8e-06, + "output_cost_per_token_flex": 9e-07, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 9e-07, + "output_cost_per_token_priority": 3.15e-06, "supported_endpoints": [ "/v1/chat/completions" ], @@ -65061,35 +68872,47 @@ }, "bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct": { "input_cost_per_token": 1.4e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct": { "input_cost_per_token": 5.3e-07, + "input_cost_per_token_batches": 2.6e-07, + "input_cost_per_token_flex": 2.6e-07, + "input_cost_per_token_priority": 9.3e-07, "output_cost_per_token": 2.66e-06, + "output_cost_per_token_flex": 1.33e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 1.33e-06, + "output_cost_per_token_priority": 4.66e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-vl-235b-a22b.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "azure/us-gov/gpt-5.1": { "cache_read_input_token_cost": 1.71875e-07, @@ -65232,7 +69055,7 @@ "gemini/lyria-3.5": { "input_cost_per_token": 0, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", @@ -65340,12 +69163,12 @@ "mode": "responses", "supports_web_search": true, "supports_function_calling": true, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 3e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token_above_272k_tokens": 1e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token_above_272k_tokens": 8e-06, + "output_cost_per_token_above_272k_tokens": 3e-05, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.6-terra": { @@ -65428,6 +69251,22 @@ "cache_read_input_token_cost": 1.25e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, + "perplexity/openai/gpt-5-nano": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 5e-09, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.3-codex": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 3.5e-06, + "output_cost_per_token": 2.8e-05, + "cache_read_input_token_cost": 3.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/google/gemini-3.1-pro-preview": { "litellm_provider": "perplexity", "mode": "responses", @@ -65464,6 +69303,7 @@ "perplexity/google/gemini-3.5-flash-lite": { "litellm_provider": "perplexity", "mode": "responses", + "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 3e-07, @@ -65474,6 +69314,7 @@ "perplexity/google/gemini-3.6-flash": { "litellm_provider": "perplexity", "mode": "responses", + "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1.5e-06, @@ -65484,6 +69325,7 @@ "perplexity/google/gemini-3.7-flash": { "litellm_provider": "perplexity", "mode": "responses", + "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 7.5e-07, @@ -65607,675 +69449,6 @@ "cache_read_input_token_cost": 2.5e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, - "openrouter/anthropic/claude-fable-5": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 1e-06, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_1hr": 2e-05, - "prompt_cache_min_tokens": 512, - "supports_web_search": true - }, - "openrouter/anthropic/claude-fable-5.1": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2.5e-07, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_1hr": 2e-05, - "prompt_cache_min_tokens": 512, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.8": { - "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-07, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-5": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "supports_web_search": true - }, - "openrouter/google/gemini-2.5-flash-lite": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 3e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 1e-08, - "deprecation_date": "2026-10-20", - "input_cost_per_audio_token": 3e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.5-flash": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 3e-07, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 9e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_audio_token": 3e-06, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.5-flash-lite": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 3e-08, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 3e-08, - "input_cost_per_audio_token": 3e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.6-flash": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 3.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 7.5e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.7-flash": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 3.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 7.5e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.8-flash": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 3.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 7.5e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/openai/gpt-4o-mini": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.1": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 1.25e-07, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.3-codex": { - "input_cost_per_token": 1.75e-06, - "output_cost_per_token": 1.4e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 1.75e-07, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4": { - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 5e-07, - "input_cost_per_token_above_272k_tokens": 5e-06, - "output_cost_per_token_above_272k_tokens": 2.25e-05, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4-mini": { - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 4.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4-nano": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-08, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.5": { - "input_cost_per_token": 5e-06, - "output_cost_per_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-luna": { - "cache_creation_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost_above_272k_tokens": 5e-07, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-08, - "cache_read_input_token_cost_above_272k_tokens": 4e-08, - "input_cost_per_token_above_272k_tokens": 4e-07, - "output_cost_per_token_above_272k_tokens": 1.8e-06, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-luna-pro": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 2e-08, - "cache_creation_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost_above_272k_tokens": 5e-07, - "input_cost_per_token_above_272k_tokens": 4e-07, - "output_cost_per_token_above_272k_tokens": 1.8e-06, - "cache_read_input_token_cost_above_272k_tokens": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-terra": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token_above_272k_tokens": 4e-06, - "output_cost_per_token_above_272k_tokens": 1.8e-05, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-terra-pro": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "output_cost_per_token_above_272k_tokens": 1.8e-05, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/o3": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-07, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/o4-mini": { - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2.75e-07, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/x-ai/grok-4.20": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_output_tokens": 1800000, - "max_tokens": 1800000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/x-ai/grok-4.20-multi-agent": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_output_tokens": 1800000, - "max_tokens": 1800000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/x-ai/grok-4.3": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 900000, - "max_tokens": 900000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/x-ai/grok-4.5": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "input_cost_per_token_above_200k_tokens": 4e-06, - "output_cost_per_token_above_200k_tokens": 1.2e-05, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/x-ai/grok-4.6": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "output_cost_per_token_above_200k_tokens": 1.2e-05, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/x-ai/grok-build-0.1": { - "input_cost_per_token": 1e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 230400, - "max_tokens": 230400, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token_above_200k_tokens": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "supports_prompt_caching": true, - "supports_web_search": true - }, "baseten/zai-org/GLM-5.3": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, @@ -66324,2794 +69497,21 @@ "supports_tool_choice": true, "supports_vision": true }, - "openrouter/minimax/minimax-m3": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 512000, - "max_tokens": 512000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "cache_read_input_token_cost": 6e-08, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.7-plus": { - "input_cost_per_token": 3.2e-07, - "input_cost_per_token_above_256k_tokens": 9.6e-07, - "cache_creation_input_token_cost_above_256k_tokens": 1.2e-06, - "cache_read_input_token_cost_above_256k_tokens": 1.92e-07, - "output_cost_per_token_above_256k_tokens": 3.84e-06, - "output_cost_per_token": 1.28e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "cache_read_input_token_cost": 6.4e-08, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 4e-07, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-6-astra": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "cache_read_input_token_cost": 1e-06, - "cache_creation_input_token_cost": 1.25e-05, - "input_cost_per_token_above_272k_tokens": 2e-05, - "output_cost_per_token_above_272k_tokens": 7.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 2e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-astra-pro": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "cache_read_input_token_cost": 1e-06, - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, - "input_cost_per_token_above_272k_tokens": 2e-05, - "output_cost_per_token_above_272k_tokens": 7.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/qwen/qwen3.8-flash": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 4.7e-07, - "cache_read_input_token_cost": 1.6e-08, - "cache_creation_input_token_cost": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.3-flash": { - "input_cost_per_token": 4.5e-08, - "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 2.85e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v4-flash-vision-exp": { - "input_cost_per_token": 2.2e-07, - "output_cost_per_token": 6.6e-07, - "cache_read_input_token_cost": 7e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.3": { - "input_cost_per_token": 1.4e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943717, - "max_tokens": 943717, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.8-27b": { - "input_cost_per_token": 4.2e-07, - "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 8.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.8-2.4t-a95b": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3.5-lightning:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.8-max": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.8-max", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true - }, - "openrouter/qwen/qwen3.8-max-0902": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.8-max-prime": { - "input_cost_per_token": 4e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_video_input": true, - "supports_prompt_caching": true - }, - "openrouter/deepseek/deepseek-v4-flash-0731": { - "input_cost_per_token": 3e-08, - "output_cost_per_token": 3.2e-07, - "cache_read_input_token_cost": 1.6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.7-flash": { - "input_cost_per_token": 3e-08, - "input_cost_per_token_above_32k_tokens": 1e-07, - "cache_creation_input_token_cost_above_32k_tokens": 1.25e-07, - "cache_read_input_token_cost_above_32k_tokens": 2e-08, - "output_cost_per_token_above_32k_tokens": 4e-07, - "output_cost_per_token": 1.3e-07, - "cache_read_input_token_cost": 6e-09, - "cache_creation_input_token_cost": 3.8e-08, - "input_cost_per_token_above_256k_tokens": 2e-07, - "output_cost_per_token_above_256k_tokens": 8e-07, - "cache_read_input_token_cost_above_256k_tokens": 4e-08, - "cache_creation_input_token_cost_above_256k_tokens": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/poolside/laguna-s-2.1": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 1.8e-07, - "cache_read_input_token_cost": 9e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_web_search": false - }, - "openrouter/poolside/laguna-s-2.1:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k3": { - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/poolside/laguna-xs-2.1": { - "input_cost_per_token": 6e-08, - "output_cost_per_token": 1.2e-07, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_web_search": false - }, - "openrouter/poolside/laguna-xs-2.1:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/google/gemini-3.1-flash-lite-image": { - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.5e-06, - "output_cost_per_image_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 58982, - "max_tokens": 58982, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/google/gemini-3.1-flash-image": { - "input_cost_per_token": 5e-07, - "output_cost_per_token": 3e-06, - "output_cost_per_image_token": 6e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/google/gemini-3-pro-image": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 2e-07, - "input_cost_per_audio_token": 2e-06, - "output_cost_per_image_token": 0.00012, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/z-ai/glm-5.2": { - "input_cost_per_token": 6.496e-07, - "output_cost_per_token": 2.0416e-06, - "cache_read_input_token_cost": 1.2064e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.2:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k2.7-code": { - "input_cost_per_token": 6.562e-07, - "output_cost_per_token": 3.3e-06, - "cache_read_input_token_cost": 1.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3.5-content-safety": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3.5-content-safety:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3-ultra-550b-a55b": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.4e-06, - "cache_read_input_token_cost": 1.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 182520, - "max_tokens": 182520, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m3:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m3:free", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true - }, - "openrouter/qwen/qwen3.7-max": { - "input_cost_per_token": 1.475e-06, - "output_cost_per_token": 4.425e-06, - "cache_read_input_token_cost": 2.95e-07, - "cache_creation_input_token_cost": 1.84375e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-medium-3-5": { - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 7.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_response_schema": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-plus-20260420": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.8e-06, - "cache_creation_input_token_cost": 3.75e-07, - "input_cost_per_token_above_256k_tokens": 3.75e-07, - "output_cost_per_token_above_256k_tokens": 2.25e-06, - "cache_creation_input_token_cost_above_256k_tokens": 4.6875e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.6-flash": { - "input_cost_per_token": 1.875e-07, - "output_cost_per_token": 1.125e-06, - "cache_creation_input_token_cost": 2.34375e-07, - "input_cost_per_token_above_256k_tokens": 7.5e-07, - "output_cost_per_token_above_256k_tokens": 3e-06, - "cache_creation_input_token_cost_above_256k_tokens": 9.375e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.6-35b-a3b": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1e-06, - "cache_read_input_token_cost": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.6-max-preview": { - "input_cost_per_token": 1.027e-06, - "output_cost_per_token": 6.162e-06, - "cache_creation_input_token_cost": 1.28375e-06, - "input_cost_per_token_above_128k_tokens": 1.58e-06, - "output_cost_per_token_above_128k_tokens": 9.48e-06, - "cache_creation_input_token_cost_above_128k_tokens": 1.975e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.6-27b": { - "input_cost_per_token": 3.2e-07, - "output_cost_per_token": 2.7e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262140, - "max_tokens": 262140, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/openai/gpt-5.5-pro": { - "input_cost_per_token": 3e-05, - "output_cost_per_token": 0.00018, - "input_cost_per_token_above_272k_tokens": 6e-05, - "output_cost_per_token_above_272k_tokens": 0.00027, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": true - }, - "openrouter/openai/gpt-chat-latest": { - "input_cost_per_token": 5e-06, - "output_cost_per_token": 3e-05, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/deepseek/deepseek-v4-flash": { - "input_cost_per_token": 4.9e-08, - "output_cost_per_token": 9.8e-08, - "cache_read_input_token_cost": 9.8e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k2.6": { - "input_cost_per_token": 9.5e-07, - "output_cost_per_token": 4e-06, - "cache_read_input_token_cost": 1.6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/google/gemma-4-26b-a4b-it": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 9e-08, - "output_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/google/gemma-4-26b-a4b-it:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/google/gemma-4-31b-it": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 3.4e-07, - "cache_read_input_token_cost": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/google/gemma-4-31b-it:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5v-turbo": { - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 4e-06, - "cache_read_input_token_cost": 2.4e-07, - "deprecation_date": "2098-12-31", - "litellm_provider": "openrouter", - "max_input_tokens": 202752, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m2.7": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m2.7:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 196608, - "max_output_tokens": 176947, - "max_tokens": 176947, - "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m2.7:free", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false - }, - "openrouter/mistralai/mistral-small-2603": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 1.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5-turbo": { - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 4e-06, - "cache_read_input_token_cost": 2.4e-07, - "deprecation_date": "2098-12-31", - "litellm_provider": "openrouter", - "max_input_tokens": 202752, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3-super-120b-a12b": { - "input_cost_per_token": 8e-08, - "output_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3-super-120b-a12b:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-9b": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/openai/gpt-5.4-pro": { - "input_cost_per_token": 3e-05, - "output_cost_per_token": 0.00018, - "input_cost_per_token_above_272k_tokens": 6e-05, - "output_cost_per_token_above_272k_tokens": 0.00027, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": true - }, - "openrouter/google/gemini-3.1-flash-image-preview": { - "input_cost_per_token": 5e-07, - "output_cost_per_token": 3e-06, - "output_cost_per_image_token": 6e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 58982, - "max_tokens": 58982, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/google/gemini-3.1-pro-preview-customtools": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 2e-07, - "input_cost_per_audio_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/qwen/qwen3-max-thinking": { - "input_cost_per_token": 7.8e-07, - "input_cost_per_token_above_32k_tokens": 1.56e-06, - "output_cost_per_token_above_32k_tokens": 7.8e-06, - "output_cost_per_token": 3.9e-06, - "input_cost_per_token_above_128k_tokens": 1.95e-06, - "output_cost_per_token_above_128k_tokens": 9.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-coder-next": { - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 8e-07, - "cache_read_input_token_cost": 7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m2-her": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-audio": { - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "input_cost_per_audio_token": 3.2e-05, - "output_cost_per_audio_token": 6.4e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_audio_input": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-audio-mini": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.4e-06, - "input_cost_per_audio_token": 6e-07, - "output_cost_per_audio_token": 2.4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_audio_input": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3-nano-30b-a3b": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2e-07, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.6v": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 9e-07, - "cache_read_input_token_cost": 5.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/google/gemini-3-pro-image-preview": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 2e-07, - "input_cost_per_audio_token": 2e-06, - "output_cost_per_image_token": 0.00012, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.1-codex": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.1-codex-mini": { - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/moonshotai/kimi-k2-thinking": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.5e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/mistralai/voxtral-small-24b-2507": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 0.0001, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 26214, - "max_tokens": 26214, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-oss-safeguard-20b": { - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, - "cache_read_input_token_cost": 3.75e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-vl-32b-instruct": { - "input_cost_per_token": 1.04e-07, - "output_cost_per_token": 4.16e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-vl-8b-thinking": { - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 2.1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-vl-8b-instruct": { - "input_cost_per_token": 1.17e-07, - "output_cost_per_token": 4.55e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/google/gemini-2.5-flash-image": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 1e-07, - "deprecation_date": "2027-03-15", - "input_cost_per_audio_token": 1e-06, - "output_cost_per_image_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": true - }, - "openrouter/qwen/qwen3-vl-30b-a3b-thinking": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-vl-30b-a3b-instruct": { - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 5.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/openai/gpt-5-pro": { - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 0.00012, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": true - }, - "openrouter/qwen/qwen3-vl-235b-a22b-thinking": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-vl-235b-a22b-instruct": { - "input_cost_per_token": 2.1e-07, - "output_cost_per_token": 1.9e-06, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-max": { - "input_cost_per_token": 7.8e-07, - "input_cost_per_token_above_32k_tokens": 1.56e-06, - "cache_creation_input_token_cost_above_32k_tokens": 1.95e-06, - "cache_read_input_token_cost_above_32k_tokens": 3.12e-07, - "output_cost_per_token_above_32k_tokens": 7.8e-06, - "output_cost_per_token": 3.9e-06, - "cache_read_input_token_cost": 1.56e-07, - "cache_creation_input_token_cost": 9.75e-07, - "input_cost_per_token_above_128k_tokens": 1.95e-06, - "output_cost_per_token_above_128k_tokens": 9.75e-06, - "cache_read_input_token_cost_above_128k_tokens": 3.9e-07, - "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v3.1-terminus": { - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 1e-06, - "cache_read_input_token_cost": 1.35e-07, - "deprecation_date": "2026-09-28", - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-coder-flash": { - "input_cost_per_token": 1.95e-07, - "input_cost_per_token_above_32k_tokens": 3.25e-07, - "cache_creation_input_token_cost_above_32k_tokens": 4.0625e-07, - "cache_read_input_token_cost_above_32k_tokens": 6.5e-08, - "output_cost_per_token_above_32k_tokens": 1.625e-06, - "output_cost_per_token": 9.75e-07, - "cache_read_input_token_cost": 3.9e-08, - "cache_creation_input_token_cost": 2.4375e-07, - "input_cost_per_token_above_128k_tokens": 5.2e-07, - "output_cost_per_token_above_128k_tokens": 2.6e-06, - "cache_read_input_token_cost_above_128k_tokens": 1.04e-07, - "cache_creation_input_token_cost_above_128k_tokens": 6.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-next-80b-a3b-thinking": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-next-80b-a3b-instruct": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1.1e-06, - "cache_read_input_token_cost": 7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen-plus-2025-07-28": { - "cache_creation_input_token_cost": 3.25e-07, - "cache_read_input_token_cost": 5.2e-08, - "input_cost_per_token": 2.6e-07, - "output_cost_per_token": 7.8e-07, - "input_cost_per_token_above_256k_tokens": 7.8e-07, - "output_cost_per_token_above_256k_tokens": 2.34e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k2-0905": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-30b-a3b-thinking-2507": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 81920, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-medium-3.1": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.5v": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 1.8e-06, - "cache_read_input_token_cost": 1.1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/mistralai/codestral-2508": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 9e-07, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 204800, - "max_tokens": 204800, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-coder-30b-a3b-instruct": { - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-30b-a3b-instruct-2507": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.5": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.2e-06, - "cache_read_input_token_cost": 1.1e-07, - "deprecation_date": "2026-12-31", - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.5-air": { - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 8.5e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k2": { - "input_cost_per_token": 5.7e-07, - "output_cost_per_token": 2.3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m1": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/o3-pro": { - "input_cost_per_token": 2e-05, - "output_cost_per_token": 8e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": true - }, - "openrouter/google/gemini-2.5-pro-preview": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 1.25e-07, - "input_cost_per_audio_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/mistralai/mistral-medium-3": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/google/gemini-2.5-pro-preview-05-06": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost": 3.75e-07, - "input_cost_per_audio_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "source": "https://openrouter.ai/google/gemini-2.5-pro-preview-05-06", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true - }, - "openrouter/meta-llama/llama-guard-4-12b": { - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 1.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-30b-a3b": { - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-8b": { - "input_cost_per_token": 1.17e-07, - "output_cost_per_token": 4.55e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-14b": { - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-32b": { - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-235b-a22b": { - "input_cost_per_token": 4.55e-07, - "output_cost_per_token": 1.82e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/o4-mini-high": { - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/meta-llama/llama-4-maverick": { - "input_cost_per_token": 1.875e-07, - "output_cost_per_token": 6.525e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/meta-llama/llama-4-scout": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/openai/o1-pro": { - "input_cost_per_token": 0.00015, - "output_cost_per_token": 0.0006, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": true - }, - "openrouter/google/gemma-3-4b-it": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/google/gemma-3-12b-it": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/google/gemma-3-27b-it": { - "input_cost_per_token": 8e-08, - "output_cost_per_token": 4.5e-07, - "cache_read_input_token_cost": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-saba": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 2e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 26214, - "max_tokens": 26214, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen2.5-vl-72b-instruct": { - "input_cost_per_token": 8e-07, - "output_cost_per_token": 1e-06, - "cache_read_input_token_cost": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 115200, - "max_tokens": 115200, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen-plus": { - "input_cost_per_token": 2.6e-07, - "output_cost_per_token": 7.8e-07, - "cache_read_input_token_cost": 5.2e-08, - "cache_creation_input_token_cost": 3.25e-07, - "input_cost_per_token_above_256k_tokens": 7.8e-07, - "output_cost_per_token_above_256k_tokens": 2.34e-06, - "cache_read_input_token_cost_above_256k_tokens": 1.56e-07, - "cache_creation_input_token_cost_above_256k_tokens": 9.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-small-24b-instruct-2501": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-r1-distill-llama-70b": { - "deprecation_date": "2026-09-28", - "input_cost_per_token": 8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 7372, - "max_tokens": 7372, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/minimax/minimax-01": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000192, - "max_output_tokens": 900172, - "max_tokens": 900172, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/meta-llama/llama-3.3-70b-instruct": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-4o-2024-11-20": { - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_web_search": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false - }, - "openrouter/mistralai/mistral-large-2407": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen-2.5-7b-instruct": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/meta-llama/llama-3.2-1b-instruct": { - "input_cost_per_token": 2.7e-08, - "output_cost_per_token": 2.01e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 60000, - "max_output_tokens": 54000, - "max_tokens": 54000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/meta-llama/llama-3.2-3b-instruct": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 3.3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen-2.5-72b-instruct": { - "input_cost_per_token": 3.6e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-4o-2024-08-06": { - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_web_search": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false - }, - "openrouter/meta-llama/llama-3.1-70b-instruct": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/meta-llama/llama-3.1-8b-instruct": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-nemo": { - "input_cost_per_token": 1.9e-08, - "output_cost_per_token": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-4o-mini-2024-07-18": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_web_search": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false - }, - "openrouter/google/gemma-2-27b-it": { - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 6.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-4-turbo": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/openai/gpt-4-turbo-preview": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-4-turbo-preview", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false - }, - "openrouter/openai/gpt-3.5-turbo-instruct": { - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 4095, - "max_output_tokens": 3685, - "max_tokens": 3685, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, "together_ai/arcee-ai/trinity-mini": { "input_cost_per_token": 4.5e-08, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 1.5e-07, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 128000, + "max_tokens": 128000 }, "vertex_ai/gemini-2.5-flash-native-audio": { "deprecation_date": "2026-12-13", "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 3e-06, "input_cost_per_token": 5e-07, + "input_cost_per_video_token": 3e-06, "litellm_provider": "vertex_ai", "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, @@ -69146,7 +69546,7 @@ }, "vertex_ai/gemini-3.5-transcribe-live": { "input_cost_per_audio_token": 3.5e-06, - "input_cost_per_second": 8.33333333333e-05, + "input_cost_per_second": 8.75e-05, "litellm_provider": "vertex_ai", "mode": "audio_transcription", "output_cost_per_token": 2.1e-05, @@ -69204,6 +69604,15 @@ "source": "https://developers.openai.com/api/docs/pricing", "supports_reasoning": true }, + "gpt-5.5-cyber-preview": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 1.25e-05, + "litellm_provider": "openai", + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_reasoning": true + }, "gpt-rosalind-research": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, @@ -69217,45 +69626,75 @@ "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 3.5e-06, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 4096, + "max_tokens": 4096 }, "together_ai/meta-llama/Llama-3.2-1B-Instruct": { "input_cost_per_token": 6e-08, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 6e-08, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 131072, + "max_tokens": 131072 }, "together_ai/meta-llama/Llama-3.2-3B-Instruct": { "input_cost_per_token": 6e-08, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 6e-08, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 131072, + "max_tokens": 131072 }, "together_ai/Qwen/Qwen2-1.5B-Instruct": { "input_cost_per_token": 2e-08, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 2e-08, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 32768, + "max_tokens": 32768 }, "together_ai/Qwen/Qwen2.5-14B-Instruct": { "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 32768, + "max_tokens": 32768 }, "together_ai/Qwen/Qwen2.5-72B-Instruct": { "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 32768, + "max_tokens": 32768 + }, + "together_ai/Salesforce/Llama-Rank-V1": { + "deprecation_date": "2026-02-06", + "input_cost_per_token": 1e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "rerank", + "output_cost_per_token": 0.0, "source": "https://api.together.ai/v1/models" }, + "together_ai/meta-llama/Meta-Llama-3.1-8B": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 16384, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 2e-07, + "source": "https://api.together.xyz/v1/models" + }, "together_ai/together/Tev1-4B-experimental": { - "cache_read_input_token_cost": 4.2e-08, "input_cost_per_token": 4.2e-08, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -69465,7 +69904,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/google/gemma-4-31B-it": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -69598,6 +70037,7 @@ }, "together_ai/nvidia/nemotron-3-ultra-550b-a55b": { "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 512288, @@ -69607,7 +70047,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/openai/gpt-oss-20b": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69662,7 +70102,7 @@ "cache_read_input_token_cost": 4.13e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 6.6e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -69717,6 +70157,9 @@ "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, @@ -69742,7 +70185,7 @@ "cache_read_input_token_cost": 1.38e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -69778,7 +70221,7 @@ "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" @@ -69788,7 +70231,7 @@ "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -69812,7 +70255,7 @@ "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -69820,7 +70263,7 @@ "input_cost_per_token": 2.31e-05, "input_cost_per_token_batches": 1.155e-05, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" @@ -69832,7 +70275,7 @@ "input_cost_per_token": 1.925e-06, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" @@ -69871,7 +70314,7 @@ "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, "input_cost_per_token_batches": 1.65e-05, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 0.000198, "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, @@ -70030,12 +70473,29 @@ "output_cost_per_token_batches": 2.42e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, + "azure/eu/o3": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "azure/eu/o3-2025-04-16": { "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, @@ -70050,12 +70510,29 @@ "output_cost_per_token": 4.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, + "azure/eu/o4-mini": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 3.03e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "azure/eu/o4-mini-2025-04-16": { "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 3.03e-07, "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -70101,7 +70578,8 @@ "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_reasoning": true }, "gemini/gemini-3.8-live-extended-thinking": { "input_cost_per_audio_token": 3e-06, @@ -70122,14 +70600,15 @@ "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_reasoning": true }, "azure/us/codex-mini": { "deprecation_date": "2026-11-15", "cache_read_input_token_cost": 4.13e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 6.6e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -70184,6 +70663,9 @@ "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, @@ -70209,7 +70691,7 @@ "cache_read_input_token_cost": 1.38e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -70245,7 +70727,7 @@ "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" @@ -70255,7 +70737,7 @@ "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -70279,7 +70761,7 @@ "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -70287,7 +70769,7 @@ "input_cost_per_token": 2.31e-05, "input_cost_per_token_batches": 1.155e-05, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" @@ -70299,7 +70781,7 @@ "input_cost_per_token": 1.925e-06, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" @@ -70338,7 +70820,7 @@ "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, "input_cost_per_token_batches": 1.65e-05, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 0.000198, "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, @@ -70480,7 +70962,7 @@ "supports_audio_input": true }, "azure/gpt-realtime-translate": { - "deprecation_date": "2027-05-06", + "deprecation_date": "2027-11-09", "input_cost_per_second": 0.000566666666667, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -70935,6 +71417,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_vision": true, "supports_web_search": true }, @@ -70952,6 +71435,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_vision": true, "supports_web_search": true }, @@ -71623,26 +72107,150 @@ "supports_reasoning": true, "supports_vision": true }, - "openrouter/typesafe/jev-1.13": { - "input_cost_per_token": 4.2e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 32000, - "max_output_tokens": 28800, - "max_tokens": 28800, + "bespoke/nimble-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "bespoke", + "max_input_tokens": 8192, "mode": "evaluation", "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/typesafe/jev-1.13" + "source": "https://github.com/bespokelabsai/nimble", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "bespoke/nimble": { + "input_cost_per_token": 0.0, + "litellm_provider": "bespoke", + "max_input_tokens": 8192, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://ollama.com/library/nimble", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model under the name Ollama serves it as; infrastructure costs are paid separately" + } + }, + "bespoke/bespokelabs/Bespoke-Nimble-9B": { + "input_cost_per_token": 0.0, + "litellm_provider": "bespoke", + "max_input_tokens": 8192, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/bespokelabsai/nimble", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "laya/english": { + "input_cost_per_token": 0.0, + "litellm_provider": "laya", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/NandhaKishorM/laya", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "laya/multilingual": { + "input_cost_per_token": 0.0, + "litellm_provider": "laya", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/NandhaKishorM/laya", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "laya/typed-decisions": { + "input_cost_per_token": 0.0, + "litellm_provider": "laya", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/NandhaKishorM/laya", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "strands_decider/strands-decider-2B-hobson-v19": { + "input_cost_per_token": 0.0, + "litellm_provider": "strands_decider", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v19", + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "nace/drex-v1.0": { + "input_cost_per_token": 4e-08, + "litellm_provider": "nace", + "max_input_tokens": 32768, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" + }, + "nace/drex-v1.5": { + "input_cost_per_token": 5e-08, + "litellm_provider": "nace", + "max_input_tokens": 131072, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" + }, + "nace/drex-v2.0": { + "input_cost_per_token": 6e-08, + "litellm_provider": "nace", + "max_input_tokens": 131072, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" + }, + "nace/drex-latest": { + "input_cost_per_token": 6e-08, + "litellm_provider": "nace", + "max_input_tokens": 131072, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" }, "typesafe/jev-1.13.0": { "input_cost_per_token": 4.2e-08, "litellm_provider": "typesafe", + "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.typesafe.ai/models" }, + "typesafe/jev-1.14.0": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "typesafe", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.typesafe.ai/models", + "supports_box_questions": true + }, "typesafe/jev-latest": { "input_cost_per_token": 4.2e-08, "litellm_provider": "typesafe", + "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.typesafe.ai/models" @@ -71650,9 +72258,11 @@ "typesafe/jev-preview": { "input_cost_per_token": 4.2e-08, "litellm_provider": "typesafe", + "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, - "source": "https://docs.typesafe.ai/models" + "source": "https://docs.typesafe.ai/models", + "supports_box_questions": true }, "wandb/deepseek-ai/DeepSeek-V4.1-Flash": { "cache_read_input_token_cost": 3e-08, @@ -71689,4109 +72299,109 @@ "max_input_tokens": 1049000, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://wandb.ai/site/pricing/tokens/", + "source": "https://docs.wandb.ai/inference/models.md", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true - }, - "openrouter/~anthropic/claude-fable-latest": { - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_1hr": 2e-05, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~anthropic/claude-haiku-latest": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_1hr": 2e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~anthropic/claude-opus-latest": { - "cache_creation_input_token_cost": 5e-06, - "cache_creation_input_token_cost_above_1hr": 8e-06, - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~anthropic/claude-sonnet-latest": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~deepseek/deepseek-flash-latest": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/~deepseek/deepseek-pro-latest": { - "cache_read_input_token_cost": 4.4e-08, - "input_cost_per_token": 1.32e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":6.6e-7,"output_cost_per_token":0.00000198,"cache_read_input_token_cost":2.2e-8}, - "output_cost_per_token": 3.96e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/~deepseek/deepseek-v4-flash-latest": { - "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 6.4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/~google/gemini-flash-latest": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 7.5e-08, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 7.5e-07, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 3.75e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~google/gemini-pro-latest": { - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 2e-07, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_audio_token": 2e-06, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~moonshotai/kimi-latest": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/~openai/gpt-astra-latest": { - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, - "cache_read_input_token_cost": 1e-06, - "cache_read_input_token_cost_above_272k_tokens": 2e-06, - "input_cost_per_token": 1e-05, - "input_cost_per_token_above_272k_tokens": 2e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-05, - "output_cost_per_token_above_272k_tokens": 7.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~openai/gpt-luna-latest": { - "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_272k_tokens": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~openai/gpt-mini-latest": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 4.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~openai/gpt-sol-latest": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~openai/gpt-terra-latest": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_272k_tokens": 1.8e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~x-ai/grok-latest": { - "cache_read_input_token_cost": 4e-07, - "cache_read_input_token_cost_above_200k_tokens": 8e-07, - "input_cost_per_token": 1.6e-06, - "input_cost_per_token_above_200k_tokens": 3.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, - "mode": "chat", - "output_cost_per_token": 4.8e-06, - "output_cost_per_token_above_200k_tokens": 9.6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~z-ai/glm-flash-latest": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/~z-ai/glm-latest": { - "cache_read_input_token_cost": 1.2142e-07, - "input_cost_per_token": 6.538e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.0548e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/aion-labs/aion-2.0": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/aion-labs/aion-3.0": { - "cache_read_input_token_cost": 7.5e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/aion-labs/aion-3.0-mini": { - "cache_read_input_token_cost": 1.8e-07, - "input_cost_per_token": 7e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/aion-labs/aion-3.5": { - "cache_read_input_token_cost": 7.5e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/aion-labs/aion-3.5-mini": { - "cache_read_input_token_cost": 1.8e-07, - "input_cost_per_token": 7e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/aion-labs/aion-rp-llama-3.1-8b": { - "input_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, - "mode": "chat", - "output_cost_per_token": 1.6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/amazon/nova-2-lite-v1": { - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/amazon/nova-lite-v1": { - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 300000, - "max_output_tokens": 5120, - "max_tokens": 5120, - "mode": "chat", - "output_cost_per_token": 2.4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/amazon/nova-micro-v1": { - "input_cost_per_token": 3.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 5120, - "max_tokens": 5120, - "mode": "chat", - "output_cost_per_token": 1.4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/amazon/nova-premier-v1": { - "cache_read_input_token_cost": 6.25e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/amazon/nova-pro-v1": { - "input_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 300000, - "max_output_tokens": 5120, - "max_tokens": 5120, - "mode": "chat", - "output_cost_per_token": 3.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/anthracite-org/magnum-v4-72b": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/anthropic/claude-fable-5:batch": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-fable-5.1:batch": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-haiku-4.5:batch": { - "cache_creation_input_token_cost": 6.25e-07, - "cache_creation_input_token_cost_above_1hr": 1e-06, - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.1:batch": { - "cache_creation_input_token_cost": 9.375e-06, - "cache_creation_input_token_cost_above_1hr": 1.5e-05, - "cache_read_input_token_cost": 7.5e-07, - "input_cost_per_token": 7.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 3.75e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.5:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.6:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.7:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.8:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-5:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-4.5:batch": { - "cache_creation_input_token_cost": 1.875e-06, - "cache_creation_input_token_cost_above_1hr": 3e-06, - "cache_creation_input_token_cost_above_200k_tokens": 3.75e-06, - "cache_read_input_token_cost": 1.5e-07, - "cache_read_input_token_cost_above_200k_tokens": 3e-07, - "input_cost_per_token": 1.5e-06, - "input_cost_per_token_above_200k_tokens": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 7.5e-06, - "output_cost_per_token_above_200k_tokens": 1.125e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-4.6:batch": { - "cache_creation_input_token_cost": 1.875e-06, - "cache_creation_input_token_cost_above_1hr": 3e-06, - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-5:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_1hr": 2e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/arcee-ai/trinity-large-thinking": { - "cache_read_input_token_cost": 6e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 80000, - "max_tokens": 80000, - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/baidu/ernie-4.5-vl-424b-a47b": { - "deprecation_date": "2026-10-08", - "input_cost_per_token": 4.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 123000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/bytedance-seed/seed-1.6": { - "deprecation_date": "2026-11-11", - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_above_128k_tokens": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 2e-06, - "output_cost_per_token_above_128k_tokens": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/bytedance-seed/seed-1.6-flash": { - "deprecation_date": "2026-11-11", - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 3e-07, - "output_cost_per_token_above_128k_tokens": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/bytedance-seed/seed-2-1-turbo": { - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/bytedance-seed/seed-2.0-code": { - "deprecation_date": "2026-11-11", - "input_cost_per_token": 5e-07, - "input_cost_per_token_above_128k_tokens": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3e-06, - "output_cost_per_token_above_128k_tokens": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/bytedance-seed/seed-2.0-lite": { - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_above_128k_tokens": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-06, - "output_cost_per_token_above_128k_tokens": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/bytedance-seed/seed-2.0-mini": { - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_128k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 4e-07, - "output_cost_per_token_above_128k_tokens": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition": { - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 9e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/cohere/command-a": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/cohere/command-r-08-2024": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/cohere/command-r-plus-08-2024": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/cohere/command-r7b-12-2024": { - "input_cost_per_token": 3.75e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/cohere/north-mini-code:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/dots-studio/dots-3-note-preview:free": { - "deprecation_date": "2026-12-31", - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 512000, - "max_output_tokens": 460800, - "max_tokens": 460800, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/google/gemini-2.5-flash-lite:batch": { - "cache_read_input_audio_token_cost": 3e-08, - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 1.5e-07, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-2.5-flash:batch": { - "cache_read_input_audio_token_cost": 1e-07, - "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-10-20", - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-2.5-pro:batch": { - "cache_read_input_audio_token_cost": 1.25e-07, - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "deprecation_date": "2026-10-20", - "input_cost_per_audio_token": 6.25e-07, - "input_cost_per_token": 6.25e-07, - "input_cost_per_token_above_200k_tokens": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_200k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3-flash-preview:batch": { - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.1-flash-lite:batch": { - "cache_read_input_audio_token_cost": 2.5e-08, - "cache_read_input_token_cost": 1.25e-08, - "input_cost_per_audio_token": 2.5e-07, - "input_cost_per_token": 1.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.1-pro-preview:batch": { - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_200k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_200k_tokens": 9e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.5-flash-lite:batch": { - "cache_read_input_audio_token_cost": 1.5e-08, - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_audio_token": 1.5e-07, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.5-flash:batch": { - "cache_read_input_audio_token_cost": 1.5e-07, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 1.5e-06, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 4.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.6-flash:batch": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 3.75e-08, - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_audio_token": 3.75e-07, - "input_cost_per_token": 3.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.875e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.7-flash:batch": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 3.75e-08, - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_audio_token": 3.75e-07, - "input_cost_per_token": 3.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.875e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.8-flash:batch": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 3.75e-08, - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_audio_token": 3.75e-07, - "input_cost_per_token": 3.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.875e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/ibm-granite/granite-4.0-h-micro": { - "input_cost_per_token": 1.7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131000, - "max_output_tokens": 117900, - "max_tokens": 117900, - "mode": "chat", - "output_cost_per_token": 1.12e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/ibm-granite/granite-4.2-8b": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inception/mercury-2": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 50000, - "max_tokens": 50000, - "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inception/mercury-2.5": { - "cache_read_input_token_cost": 4e-09, - "input_cost_per_token": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 260000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inclusionai/ling-3.0-flash": { - "cache_read_input_token_cost": 4.2e-09, - "input_cost_per_token": 2.1e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6.3e-08, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inclusionai/ling-3.0-flash-fin": { - "cache_read_input_token_cost": 1.2e-08, - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inclusionai/ling-3.0-flash-fin:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inclusionai/ling-3.0-flash-sante:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inclusionai/ling-3.0-flash-vl": { - "cache_read_input_token_cost": 1.2e-08, - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/inclusionai/ling-3.0-flash-vl:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/inference-net/schematron-v2-small": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 2.3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inference-net/schematron-v2-turbo": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/kwaipilot/kat-coder-pro-v2.5": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 7.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 2.96e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/liquid/lfm-2.5-2.6b:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/meituan/longcat-2.0": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048756, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/meta/muse-glimmer-30b": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/meta/muse-spark-1.1": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 4.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/meta/muse-spark-1.2": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 4.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/meta/muse-spark-1.2-contributor": { - "cache_read_input_token_cost": 2e-09, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/meta/muse-spark-1.3": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 4.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/meta/muse-spark-1.3-contributor": { - "cache_read_input_token_cost": 2e-09, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/microsoft/phi-4": { - "input_cost_per_token": 7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 16384, - "max_output_tokens": 14745, - "max_tokens": 14745, - "mode": "chat", - "output_cost_per_token": 1.4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/microsoft/wizardlm-2-8x22b": { - "input_cost_per_token": 6.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 65535, - "max_output_tokens": 8000, - "max_tokens": 8000, - "mode": "chat", - "output_cost_per_token": 6.2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mistralai/codestral-2508:batch": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 204800, - "max_tokens": 204800, - "mode": "chat", - "output_cost_per_token": 4.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mistralai/ministral-8b-2512:batch": { - "cache_read_input_token_cost": 7.5e-09, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 7.5e-08, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-large-2512": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-large-2512:batch": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-medium-3-5:batch": { - "input_cost_per_token": 7.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 3.75e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-medium-3.1:batch": { - "cache_read_input_token_cost": 2e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-small-2603:batch": { - "cache_read_input_token_cost": 7.5e-09, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k3:batch": { - "cache_read_input_token_cost": 2.28e-07, - "input_cost_per_token": 2.28e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.14e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/morph/morph-v3-fast": { - "input_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 81920, - "max_output_tokens": 38000, - "max_tokens": 38000, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/morph/morph-v3-large": { - "input_cost_per_token": 9e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.9e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/nex-agi/nex-n2.5-mini:free": { - "deprecation_date": "2026-09-25", - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nex-agi/nex-n2.5-pro:free": { - "deprecation_date": "2026-09-25", - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nousresearch/hermes-3-llama-3.1-405b": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/nousresearch/hermes-3-llama-3.1-70b": { - "input_cost_per_token": 7e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 7e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/nousresearch/hermes-4-405b": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-3.5-turbo-0613": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 4095, - "max_output_tokens": 3685, - "max_tokens": 3685, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-3.5-turbo:batch": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": true - }, - "openrouter/openai/gpt-4-turbo:batch": { - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4.1-mini:batch": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4.1-nano:batch": { - "cache_read_input_token_cost": 1.25e-08, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4.1:batch": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4o-mini:batch": { - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4o:batch": { - "cache_read_input_token_cost": 6.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-image": { - "cache_read_input_token_cost": 1.25e-06, - "input_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-image-mini": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-mini:batch": { - "cache_read_input_token_cost": 1.25e-08, - "input_cost_per_token": 1.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-nano:batch": { - "cache_read_input_token_cost": 2.5e-09, - "input_cost_per_token": 2.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-pro:batch": { - "input_cost_per_token": 7.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5:batch": { - "cache_read_input_token_cost": 6.25e-08, - "input_cost_per_token": 6.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.1:batch": { - "cache_read_input_token_cost": 6.25e-08, - "input_cost_per_token": 6.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.2-pro:batch": { - "input_cost_per_token": 1.05e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 8.4e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.2:batch": { - "cache_read_input_token_cost": 8.75e-08, - "input_cost_per_token": 8.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 7e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4-image-2": { - "cache_read_input_token_cost": 2e-06, - "input_cost_per_token": 8e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4-mini:batch": { - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_token": 3.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4-nano:batch": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6.25e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4-pro:batch": { - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_above_272k_tokens": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 9e-05, - "output_cost_per_token_above_272k_tokens": 0.000135, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4:batch": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_272k_tokens": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_272k_tokens": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 7.5e-06, - "output_cost_per_token_above_272k_tokens": 1.125e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.5-pro:batch": { - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_above_272k_tokens": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 9e-05, - "output_cost_per_token_above_272k_tokens": 0.000135, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.5:batch": { - "cache_read_input_token_cost": 2.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 5e-07, - "input_cost_per_token": 2.5e-06, - "input_cost_per_token_above_272k_tokens": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_272k_tokens": 2.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-luna-pro:batch": { - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-07, - "output_cost_per_token_above_272k_tokens": 9e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-luna:batch": { - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-07, - "output_cost_per_token_above_272k_tokens": 9e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-sol-pro:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-sol:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-terra-pro:batch": { - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_272k_tokens": 9e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-terra:batch": { - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_272k_tokens": 9e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-astra-pro:batch": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "output_cost_per_token_above_272k_tokens": 3.75e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-astra:batch": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "output_cost_per_token_above_272k_tokens": 3.75e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-luna": { - "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_272k_tokens": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-luna-pro": { - "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_272k_tokens": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-sol-pro": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/o3-mini:batch": { - "cache_read_input_token_cost": 2.75e-07, - "input_cost_per_token": 5.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 2.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": true - }, - "openrouter/openai/o3:batch": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/o4-mini:batch": { - "cache_read_input_token_cost": 1.375e-07, - "input_cost_per_token": 5.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 2.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/perceptron/perceptron-mk1": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/perplexity/sonar": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 127072, - "max_output_tokens": 114364, - "max_tokens": 114364, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/perplexity/sonar-deep-research": { - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 115200, - "max_tokens": 115200, - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": true - }, - "openrouter/perplexity/sonar-pro": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 8000, - "max_tokens": 8000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/perplexity/sonar-pro-search": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 8000, - "max_tokens": 8000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/perplexity/sonar-reasoning-pro": { - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 115200, - "max_tokens": 115200, - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/qwen/qwen3.8-27b:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/rekaai/reka-edge": { - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 16384, - "max_output_tokens": 14745, - "max_tokens": 14745, - "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/rekaai/reka-flash-3": { - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 58982, - "max_tokens": 58982, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/relace/relace-apply-3": { - "input_cost_per_token": 8.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/relace/relace-search": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/sakana/fugu-max": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/sakana/fugu-ultra": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/sakana/fugu-ultra-v2": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/sakana/sakana-namazu": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 9.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/sao10k/l3-lunaris-8b": { - "input_cost_per_token": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 7372, - "max_tokens": 7372, - "mode": "chat", - "output_cost_per_token": 5e-08, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/sao10k/l3.1-euryale-70b": { - "input_cost_per_token": 8.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 8.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/sao10k/l3.3-euryale-70b": { - "input_cost_per_token": 6.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/stealth/space-bunny-alpha": { - "deprecation_date": "2098-12-31", - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_reasoning": true, "supports_tool_choice": true, - "supports_video_input": true, "supports_vision": true }, - "openrouter/stepfun/step-3.5-flash": { - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/stepfun/step-3.7-flash": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 230400, - "max_tokens": 230400, - "mode": "chat", - "output_cost_per_token": 1.15e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/tencent/hunyuan-a13b-instruct": { - "input_cost_per_token": 1.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 5.7e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/tencent/hy-mt2-1.8b": { - "input_cost_per_token": 4.4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.77e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/tencent/hy-mt2-30b-a3b": { - "input_cost_per_token": 7.4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 2.95e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/tencent/hy-mt2-7b": { - "input_cost_per_token": 7.4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 2.95e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/tencent/hy3": { - "cache_read_input_token_cost": 3.3e-08, - "input_cost_per_token": 1.32e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "off_peak_pricing": {"hours_utc":"16:00-00:00","input_cost_per_token":8.25e-8,"output_cost_per_token":3.3e-7,"cache_read_input_token_cost":2.0625e-8}, - "output_cost_per_token": 5.28e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/tencent/hy3-preview": { - "cache_read_input_token_cost": 6e-08, - "input_cost_per_token": 1.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/tencent/hy4-preview": { - "cache_read_input_token_cost": 4.2e-08, - "input_cost_per_token": 8.34e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 2.501e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/thedrummer/cydonia-24b-v4.1": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/thedrummer/skyfall-36b-v2": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 5.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/thedrummer/unslopnemo-12b": { - "input_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1024000, - "max_output_tokens": 819200, - "max_tokens": 819200, - "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/thinkingmachines/inkling": { - "cache_read_input_token_cost": 1.7e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 471859, - "max_tokens": 471859, - "mode": "chat", - "output_cost_per_token": 4.05e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/thinkingmachines/inkling-small": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/thinkingmachines/inkling-small:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/thinkingmachines/inkling:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/unbiased/pareto": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/upstage/solar-pro-3": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/upstage/solar-pro4": { - "cache_read_input_token_cost": 1.8e-08, - "input_cost_per_token": 9e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 524288, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3.6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/upstage/solar-mini4": { - "cache_read_input_token_cost": 5e-09, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 524288, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/writer/palmyra-x5": { - "input_cost_per_token": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1040000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/x-ai/grok-4.3:batch": { - "cache_read_input_token_cost": 1.6e-07, - "cache_read_input_token_cost_above_200k_tokens": 3.2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_200k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 900000, - "max_tokens": 900000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/z-ai/glm-5.3-flash:batch": { - "cache_read_input_token_cost": 1.2e-08, - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.3:batch": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/prism-ml/ternary-bonsai-2-27b": { - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.3-prime": { - "cache_read_input_token_cost": 5.6e-07, - "input_cost_per_token": 2.8e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 8.8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.3-flashx": { - "cache_read_input_token_cost": 9e-08, - "deprecation_date": "2098-12-31", - "input_cost_per_token": 3.7e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/x-ai/grok-4.7": { - "cache_read_input_token_cost": 4e-07, - "cache_read_input_token_cost_above_200k_tokens": 8e-07, - "input_cost_per_token": 1.6e-06, - "input_cost_per_token_above_200k_tokens": 3.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, - "mode": "chat", - "output_cost_per_token": 4.8e-06, - "output_cost_per_token_above_200k_tokens": 9.6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, "moonshotai.kimi-k3": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "token_count_framing": 64, - "token_count_tokenizer": "kimi_k3" - }, - "global.moonshotai.kimi-k3": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "token_count_framing": 64, - "token_count_tokenizer": "kimi_k3" - }, - "us.moonshotai.kimi-k3": { + "supports_regex_lookaround": false, "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_flex": 2.0625e-06, + "cache_creation_input_token_cost_priority": 7.21875e-06, "cache_read_input_token_cost": 3.3e-07, + "cache_read_input_token_cost_flex": 1.65e-07, + "cache_read_input_token_cost_priority": 5.775e-07, "input_cost_per_token": 3.3e-06, + "input_cost_per_token_flex": 1.65e-06, + "input_cost_per_token_priority": 5.775e-06, "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.65e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_flex": 8.25e-06, + "output_cost_per_token_priority": 2.8875e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, + "supports_vision": true + }, + "global.moonshotai.kimi-k3": { + "supports_regex_lookaround": false, + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_flex": 1.875e-06, + "cache_creation_input_token_cost_priority": 6.5625e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_flex": 1.5e-07, + "cache_read_input_token_cost_priority": 5.25e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_flex": 1.5e-06, + "input_cost_per_token_priority": 5.25e-06, + "litellm_provider": "bedrock_converse", "token_count_framing": 64, - "token_count_tokenizer": "kimi_k3" - }, - "openrouter/xiaomi/mimo-v2.6-flash": { - "cache_read_input_token_cost": 2.8e-09, - "input_cost_per_token": 1.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "token_count_tokenizer": "kimi_k3", + "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_flex": 7.5e-06, + "output_cost_per_token_priority": 2.625e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/xiaomi/mimo-v2.6-pro": { - "cache_read_input_token_cost": 3.6e-09, - "input_cost_per_token": 4.35e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "us.moonshotai.kimi-k3": { + "supports_regex_lookaround": false, + "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_flex": 2.0625e-06, + "cache_creation_input_token_cost_priority": 7.21875e-06, + "cache_read_input_token_cost": 3.3e-07, + "cache_read_input_token_cost_flex": 1.65e-07, + "cache_read_input_token_cost_priority": 5.775e-07, + "input_cost_per_token": 3.3e-06, + "input_cost_per_token_flex": 1.65e-06, + "input_cost_per_token_priority": 5.775e-06, + "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", + "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 8.7e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_flex": 8.25e-06, + "output_cost_per_token_priority": 2.8875e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/xiaomi/mimo-v2.6-pro-ultraspeed": { - "cache_read_input_token_cost": 3.6e-08, - "input_cost_per_token": 4.35e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 8.7e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, "xiaomi_mimo/mimo-v2.6-pro": { "cache_read_input_token_cost": 3.6e-09, @@ -75841,13 +72451,16 @@ }, "xai/grok-4.20-0309": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, @@ -75855,8 +72468,11 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true @@ -76261,53 +72877,13 @@ "supports_prompt_caching": true, "supports_response_schema": true }, - "openrouter/nex-agi/nex-n2.5-mini": { - "cache_read_input_token_cost": 2.5e-09, - "input_cost_per_token": 2.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nex-agi/nex-n2.5-pro": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, "baseten/deepseek-ai/DeepSeek-V4.1-Flash": { "cache_read_input_token_cost": 7e-09, "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "max_input_tokens": 1048576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://inference.baseten.co/v1/models", @@ -76319,6 +72895,7 @@ "supports_vision": true }, "baseten/moonshotai/Kimi-K2.6": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "baseten", @@ -76336,6 +72913,7 @@ "supports_vision": true }, "baseten/moonshotai/Kimi-K2.7-Code": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "baseten", @@ -76387,6 +72965,7 @@ "supports_vision": false }, "baseten/thinkingmachines/inkling": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1e-06, "litellm_provider": "baseten", @@ -76404,6 +72983,7 @@ "supports_vision": true }, "baseten/thinkingmachines/inkling-small": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "baseten", @@ -76472,6 +73052,7 @@ "supports_vision": false }, "baseten/deepseek-ai/DeepSeek-V4-Pro": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.45e-07, "input_cost_per_token": 1.74e-06, "litellm_provider": "baseten", @@ -76620,13 +73201,25 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "fireworks_ai/accounts/fireworks/routers/rune": { + "cache_read_input_token_cost": 8.4e-09, + "input_cost_per_token": 4.2e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.fireworks.ai" + }, "fireworks_ai/accounts/fireworks/models/ember-1": { "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_priority": 3.75e-07, "input_cost_per_token": 3e-06, + "input_cost_per_token_priority": 3.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_priority": 1.875e-05, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, @@ -76634,224 +73227,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "openrouter/anthropic/claude-opus-5.5:batch": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/cohere/command-a-plus": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 192000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v4.1-flash:batch": { - "cache_read_input_token_cost": 3.36e-09, - "input_cost_per_token": 1.12e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3.36e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/openai/gpt-6-luna-pro:batch": { - "cache_creation_input_token_cost": 6.25e-08, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-07, - "cache_read_input_token_cost": 5e-09, - "cache_read_input_token_cost_above_272k_tokens": 1e-08, - "input_cost_per_token": 5e-08, - "input_cost_per_token_above_272k_tokens": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "output_cost_per_token_above_272k_tokens": 3.75e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-luna:batch": { - "cache_creation_input_token_cost": 6.25e-08, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-07, - "cache_read_input_token_cost": 5e-09, - "cache_read_input_token_cost_above_272k_tokens": 1e-08, - "input_cost_per_token": 5e-08, - "input_cost_per_token_above_272k_tokens": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "output_cost_per_token_above_272k_tokens": 3.75e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-sol-pro:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-sol:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-oss-20b:batch": { - "input_cost_per_token": 2.4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 1.12e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.8-omni-flash": { - "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 4.7e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/perceptron/perceptron-mk1.5": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 36864, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true - }, "vertex_ai/gemini-2.0-flash": { "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 1e-06, @@ -77126,7 +73501,12 @@ "cache_read_input_token_cost": 1.1e-06, "output_cost_per_token": 5.5e-05, "cache_creation_input_token_cost_above_1hr": 2.2e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-mythos-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "apac.anthropic.claude-fable-5": { "litellm_provider": "bedrock_converse", @@ -77148,7 +73528,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77181,7 +73561,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77225,7 +73605,12 @@ "input_cost_per_token": 5.5e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "apac.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -77249,6 +73634,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77259,7 +73645,12 @@ "output_cost_per_token": 2.75e-05, "cache_read_input_token_cost": 5.5e-07, "cache_creation_input_token_cost": 6.875e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "apac.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -77292,7 +73683,12 @@ "input_cost_per_token": 5.5e-06, "cache_read_input_token_cost": 5.5e-07, "output_cost_per_token": 2.75e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "apac.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -77327,7 +73723,12 @@ "input_cost_per_token": 4.4e-06, "output_cost_per_token": 2.2e-05, "cache_read_input_token_cost": 2.2e-07, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "apac.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -77338,7 +73739,7 @@ "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -77357,7 +73758,11 @@ "cache_read_input_token_cost": 3.3e-07, "cache_creation_input_token_cost": 4.125e-06, "input_cost_per_token": 3.3e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "apac.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -77381,6 +73786,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77391,7 +73797,12 @@ "input_cost_per_token": 2.2e-06, "output_cost_per_token": 1.1e-05, "cache_read_input_token_cost": 2.2e-07, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "us.anthropic.claude-mythos-preview": { "litellm_provider": "bedrock_converse", @@ -77454,6 +73865,7 @@ "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "deepseek.r1-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.35e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -77461,7 +73873,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", "supports_function_calling": false, "supports_reasoning": true, "supports_tool_choice": false @@ -77478,64 +73890,1369 @@ "supports_function_calling": true, "supports_tool_choice": false }, - "cloudflare/clef": { - "input_cost_per_token": 2.4e-07, - "litellm_provider": "cloudflare", - "max_input_tokens": 65536, - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + "azure_ai/MAI-Cyber-1-Flash": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 256000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true }, - "cloudflare/clef-flash": { - "input_cost_per_token": 9e-08, - "litellm_provider": "cloudflare", - "max_input_tokens": 65536, - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + "azure_ai/mistral-ocr-2505": { + "litellm_provider": "azure_ai", + "mode": "ocr", + "ocr_cost_per_page": 0.001, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/" }, - "cloudflare/@cf/cloudflare/clef": { - "input_cost_per_token": 2.4e-07, - "litellm_provider": "cloudflare", - "max_input_tokens": 65536, - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + "azure_ai/mistral-ocr-2512": { + "litellm_provider": "azure_ai", + "mode": "ocr", + "ocr_cost_per_page": 0.002, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/" }, - "cloudflare/@cf/cloudflare/clef-flash": { - "input_cost_per_token": 9e-08, - "litellm_provider": "cloudflare", - "max_input_tokens": 65536, - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + "anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "perplexity/pplx-decider-v1-27b": { - "input_cost_per_token": 4e-08, - "litellm_provider": "perplexity", - "max_input_tokens": 262144, - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://docs.perplexity.ai/api-reference/decisions-post" + "apac.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_creation_input_token_cost": 2.75e-06, + "input_cost_per_token": 2.2e-06, + "output_cost_per_token": 1.1e-05, + "cache_read_input_token_cost": 1.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "strands_decider/strands-decider-2B-hobson-v19": { - "input_cost_per_token": 0.0, - "litellm_provider": "strands_decider", - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v19", - "metadata": { - "notes": "Self-hosted decision model; infrastructure costs are paid separately" + "au.anthropic.claude-sonnet-5-5": { + "token_count_model": { + "model": "au.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + }, + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "azure_ai/claude-sonnet-5-5": { + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2027-09-29", + "input_cost_per_token": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" + }, + "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" } }, - "azure_ai/Microsoft-Decision-1": { - "input_cost_per_token": 4.2e-08, - "litellm_provider": "azure_ai", - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=productName eq 'Microsoft Decision Models'" + "eu.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "claude-haiku-5-5": { + "global.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "global.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "jp.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "perplexity/anthropic/claude-sonnet-5-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_adaptive_thinking": true, + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-fable-5-1": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 2.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-opus-5-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, + "cache_read_input_token_cost": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6.1-sol": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6-sol": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6-astra": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_creation_input_token_cost": 1.25e-05, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6-luna": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token_above_272k_tokens": 2e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.8-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_sampling_params": false, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "cache_read_input_token_cost": 7.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.7": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "us-gov.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } + }, + "us.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "us.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "vertex_ai/claude-sonnet-5-5": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-sonnet-5-5@default": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "prism/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 1.7e-07, + "litellm_provider": "prism", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 6.3e-07, + "source": "https://prisminference.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "prism/deepseek-v4-flash": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 1.7e-07, + "litellm_provider": "prism", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.1e-07, + "source": "https://prisminference.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "global.xai.grok-4.7": { + "supports_regex_lookaround": false, + "supported_endpoints": ["/v1/chat/completions"], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_flex": 3e-06, + "output_cost_per_token_priority": 1.05e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html", + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.xai.grok-4.7": { + "supports_regex_lookaround": false, + "supported_endpoints": ["/v1/chat/completions"], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html", + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_creation_input_token_cost_ultrafast": 1.5e-05, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 2e-07, + "cache_read_input_token_cost_ultrafast": 6e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_batches": 2e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 4e-06, + "input_cost_per_token_ultrafast": 1.2e-05, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 2e-05, + "output_cost_per_token_ultrafast": 6e-05, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "global.openai.gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05, + "cache_creation_input_token_cost_ultrafast": 1.5e-05, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06, + "cache_read_input_token_cost_ultrafast": 6e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05, + "input_cost_per_token_ultrafast": 1.2e-05, + "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05, + "output_cost_per_token_ultrafast": 6e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_bedrock_runtime_chat_completions_response_format": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_sampling_params": false, + "supports_xhigh_reasoning_effort": true + }, + "bedrock_mantle/openai.gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05, + "cache_creation_input_token_cost_ultrafast": 1.65e-05, + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06, + "cache_read_input_token_cost_ultrafast": 6.6e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05, + "input_cost_per_token_ultrafast": 1.32e-05, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "responses", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05, + "output_cost_per_token_ultrafast": 6.6e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "use_openai_responses_path": true + }, + "us.openai.gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05, + "cache_creation_input_token_cost_ultrafast": 1.65e-05, + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06, + "cache_read_input_token_cost_ultrafast": 6.6e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05, + "input_cost_per_token_ultrafast": 1.32e-05, + "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05, + "output_cost_per_token_ultrafast": 6.6e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_bedrock_runtime_chat_completions_response_format": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_sampling_params": false, + "supports_xhigh_reasoning_effort": true + }, + "vertex_ai/gemini-3.8-flash-tts": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "audio_speech", + "output_cost_per_audio_token": 9e-06, + "output_cost_per_token": 9e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "vertex_ai/gemini-3.8-flash-lite-tts": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "audio_speech", + "output_cost_per_audio_token": 6e-06, + "output_cost_per_token": 6e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "vertex_ai/xai/grok-4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/kimi-k2-thinking": { + "deprecation_date": "2026-03-29", + "input_cost_per_token": 6e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_video_input": false, + "supports_vision": false + }, + "global.zai.glm-5.3": { + "cache_creation_input_token_cost": 2.1e-06, + "cache_creation_input_token_cost_batches": 1.05e-06, + "cache_creation_input_token_cost_flex": 1.05e-06, + "cache_creation_input_token_cost_priority": 3.675e-06, + "cache_read_input_token_cost": 3.12e-07, + "cache_read_input_token_cost_batches": 1.56e-07, + "cache_read_input_token_cost_flex": 1.56e-07, + "cache_read_input_token_cost_priority": 5.46e-07, + "input_cost_per_token": 1.68e-06, + "input_cost_per_token_batches": 8.4e-07, + "input_cost_per_token_flex": 8.4e-07, + "input_cost_per_token_priority": 2.94e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.28e-06, + "output_cost_per_token_batches": 2.64e-06, + "output_cost_per_token_flex": 2.64e-06, + "output_cost_per_token_priority": 9.24e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "us.zai.glm-5.3": { + "cache_creation_input_token_cost": 2.31e-06, + "cache_creation_input_token_cost_batches": 1.155e-06, + "cache_creation_input_token_cost_flex": 1.155e-06, + "cache_creation_input_token_cost_priority": 4.0425e-06, + "cache_read_input_token_cost": 3.432e-07, + "cache_read_input_token_cost_batches": 1.716e-07, + "cache_read_input_token_cost_flex": 1.716e-07, + "cache_read_input_token_cost_priority": 6.006e-07, + "input_cost_per_token": 1.848e-06, + "input_cost_per_token_batches": 9.24e-07, + "input_cost_per_token_flex": 9.24e-07, + "input_cost_per_token_priority": 3.234e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.808e-06, + "output_cost_per_token_batches": 2.904e-06, + "output_cost_per_token_flex": 2.904e-06, + "output_cost_per_token_priority": 1.0164e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "amazon.nova-2-5-sonic": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 3.3e-07, + "litellm_provider": "bedrock", + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2.75e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_audio_input": true, + "supports_audio_output": true + }, + "azure/model-router": { + "comment": "The flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it", + "deprecation_date": "2027-05-20", + "input_cost_per_token": 1.4e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/model-router/", + "supports_vision": true + }, + "azure/whisper": { + "deprecation_date": "2026-12-15", + "input_cost_per_second": 0.0001, + "litellm_provider": "azure", + "mode": "audio_transcription", + "output_cost_per_second": 0.0001, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "gemini/gemini-nano-banana-2.1": { + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, + "rpm": 1000.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000.0, + "web_search_billing_unit": "per_query" + }, + "gemini-nano-banana-2.1": { + "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_priority": 2.7e-07, + "input_cost_per_image": 0.00168, + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_priority": 1.35e-05, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "vertex_ai/gemini-nano-banana-2.1": { + "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_priority": 2.7e-07, + "input_cost_per_image": 0.00168, + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_priority": 1.35e-05, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "azure_ai/grok-4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "deprecation_date": "2027-10-05", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://docs.x.ai/developers/models/grok-4.7", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "in.moonshotai.kimi-k3": { + "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_flex": 2.0625e-06, + "cache_creation_input_token_cost_priority": 7.21875e-06, + "cache_read_input_token_cost": 3.3e-07, + "cache_read_input_token_cost_flex": 1.65e-07, + "cache_read_input_token_cost_priority": 5.775e-07, + "input_cost_per_token": 3.3e-06, + "input_cost_per_token_flex": 1.65e-06, + "input_cost_per_token_priority": 5.775e-06, + "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_flex": 8.25e-06, + "output_cost_per_token_priority": 2.8875e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3.md", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, +"claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens_batches": 2.5e-07, "output_cost_per_token_above_100k_tokens_batches": 1.25e-06, "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07, @@ -77689,6 +75406,11 @@ "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -77714,6 +75436,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77750,6 +75473,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77765,6 +75489,11 @@ "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "au.anthropic.claude-haiku-5-5": { + "token_count_model": { + "model": "au.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + }, "input_cost_per_token_above_100k_tokens": 5.5e-07, "output_cost_per_token_above_100k_tokens": 2.75e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, @@ -77801,6 +75530,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77881,6 +75611,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -77922,6 +75653,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -77931,7 +75663,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-haiku-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "eu.anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5.5e-07, @@ -77970,6 +75707,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77991,6 +75729,11 @@ "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "global.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -78016,6 +75759,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -78062,6 +75806,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -78112,6 +75857,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -78121,7 +75867,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-haiku-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us.anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5.5e-07, @@ -78135,6 +75886,11 @@ "cache_read_input_token_cost": 1.1e-08, "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "us.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -78160,6 +75916,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -78259,89 +76016,913 @@ "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "openrouter/anthropic/claude-haiku-5.5": { - "input_cost_per_token": 1e-07, + "microsoft_365_copilot/chat": { + "litellm_provider": "microsoft_365_copilot", + "mode": "chat", + "supports_mid_conversation_system": true, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0 + }, + "us.twelvelabs.pegasus-1-5-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "litellm_provider": "bedrock", + "max_input_tokens": 261120, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", + "supports_video_input": true + }, + "global.twelvelabs.pegasus-1-5-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "litellm_provider": "bedrock", + "max_input_tokens": 261120, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", + "supports_video_input": true + }, + "twelvelabs.pegasus-1-5-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "litellm_provider": "bedrock", + "max_input_tokens": 261120, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", + "supports_video_input": true + }, + "azure_ai/Microsoft-Decision-1": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "azure_ai", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=productName eq 'Microsoft Decision Models'" + }, + "gpt-rosalind-discovery": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://developers.openai.com/api/docs/pricing" + }, + "chatgpt/gpt-rosalind-discovery": { + "litellm_provider": "chatgpt", + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/responses" + ] + }, + "azure_ai/Cohere-Embed-V5-Fast": { + "deprecation_date": "2027-01-23", + "input_cost_per_image_token": 4e-07, + "input_cost_per_token": 8e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supported_modalities": [ + "text", + "image" + ], + "supports_embedding_image_input": true + }, + "azure_ai/Cohere-Embed-V5-Pro": { + "deprecation_date": "2027-01-23", + "input_cost_per_image_token": 4e-07, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supported_modalities": [ + "text", + "image" + ], + "supports_embedding_image_input": true + }, + "scaledown/extract": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_function_calling": false + }, + "scaledown/summarize": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": true, + "supports_vision": false, + "supports_function_calling": false + }, + "scaledown/compress": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": true, + "supports_function_calling": false, + "supports_vision": false + }, + "scaledown/classify": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": false, + "supports_vision": false, + "supports_function_calling": false + }, + "scaledown/decisions": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": false, + "supports_vision": false, + "supports_function_calling": false + }, + "vertex_ai/gemini-robotics-er-2-preview": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "gemini-robotics-er-2-preview": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "gemini/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 1.8e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 4096.0, + "rpm": 2000.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000.0, + "web_search_billing_unit": "per_query" + }, + "vertex_ai/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 1.8e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token": 2e-06, + "input_cost_per_audio_token_batches": 1e-06, + "input_cost_per_audio_token_priority": 3.6e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 6144.0, + "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "vertex_ai/gemini-4-argon-cyber-permissive": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token": 4e-06, + "input_cost_per_audio_token_batches": 2e-06, + "input_cost_per_audio_token_priority": 7.2e-06, + "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2e-06, + "input_cost_per_token_flex": 2e-06, + "input_cost_per_token_priority": 7.2e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 2e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, + "output_cost_per_token_flex": 1e-05, + "output_cost_per_token_priority": 3.6e-05, + "prompt_cache_min_tokens": 6144.0, + "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "github_copilot/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_vision": true + }, + "openinfer/@oi/GLM-5.3-Flash": { + "max_tokens": 393216, + "max_input_tokens": 393216, + "max_output_tokens": 393216, + "input_cost_per_token": 1.95e-07, + "output_cost_per_token": 1.56e-06, + "litellm_provider": "openinfer", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://api.openinfer.ai/v1/models" + }, + "openinfer/@oi/Qwen3.5-27B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1.95e-07, + "output_cost_per_token": 1.56e-06, + "litellm_provider": "openinfer", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://api.openinfer.ai/v1/models" + }, + "openinfer/@oi/Qwen3.5-9B": { + "max_tokens": 100000, + "max_input_tokens": 100000, + "max_output_tokens": 100000, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "openinfer", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://api.openinfer.ai/v1/models" + }, + "xai/grok-voice-3.0": { + "input_cost_per_second": 0.001333333333333, + "input_cost_per_text_message": 0.004, + "litellm_provider": "xai", + "mode": "realtime", + "source": "https://docs.x.ai/developers/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "xai/grok-voice-latest": { + "input_cost_per_second": 0.001333333333333, + "input_cost_per_text_message": 0.004, + "litellm_provider": "xai", + "mode": "realtime", + "source": "https://docs.x.ai/developers/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "xai/grok-voice-2.0": { + "input_cost_per_second": 0.001333333333333, + "input_cost_per_text_message": 0.004, + "litellm_provider": "xai", + "mode": "realtime", + "source": "https://docs.x.ai/developers/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "together_ai/nvidia/NVIDIA-Nemotron-3.5-Super-VL": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", "output_cost_per_token": 5e-07, - "cache_read_input_token_cost": 1e-08, - "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_1hr": 2e-07, - "input_cost_per_token_above_100k_tokens": 5e-07, - "output_cost_per_token_above_100k_tokens": 2.5e-06, - "cache_read_input_token_cost_above_100k_tokens": 5e-08, - "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, - "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, - "litellm_provider": "openrouter", + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "jp.amazon.nova-2-lite-v1:0": { + "cache_read_input_token_cost": 9.9e-08, + "cache_read_input_token_cost_flex": 4.95e-08, + "cache_read_input_token_cost_priority": 1.7325e-07, + "input_cost_per_token": 3.96e-07, + "input_cost_per_token_batches": 1.98e-07, + "input_cost_per_token_flex": 1.98e-07, + "input_cost_per_token_priority": 6.93e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.311e-06, + "output_cost_per_token_batches": 1.6555e-06, + "output_cost_per_token_flex": 1.6555e-06, + "output_cost_per_token_priority": 5.79425e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-northeast-1/index.json", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-deepseek_models", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_regions": [ + "global" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/claude-opus-5-5-fast": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-10-01", + "input_cost_per_token": 8e-06, + "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true, + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.02,"search_context_size_low":0.02,"search_context_size_medium":0.02}, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models", "supports_adaptive_thinking": true, - "prompt_cache_min_tokens": 512, - "supports_sampling_params": false + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true }, - "gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, - "cache_creation_input_token_cost_batches": 1.25e-06, - "cache_creation_input_token_cost_flex": 1.25e-06, - "cache_creation_input_token_cost_priority": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07, - "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, - "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, - "cache_read_input_token_cost_batches": 5e-08, - "cache_read_input_token_cost_flex": 5e-08, - "cache_read_input_token_cost_priority": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "input_cost_per_token_above_272k_tokens_batches": 2e-06, - "input_cost_per_token_above_272k_tokens_flex": 2e-06, - "input_cost_per_token_above_272k_tokens_priority": 8e-06, - "input_cost_per_token_batches": 1e-06, - "input_cost_per_token_flex": 1e-06, - "input_cost_per_token_priority": 4e-06, - "litellm_provider": "openai", - "max_input_tokens": 922000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "baseten/meta-models/muse-spark-open": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, - "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, - "output_cost_per_token_above_272k_tokens_priority": 3e-05, - "output_cost_per_token_batches": 5e-06, - "output_cost_per_token_flex": 5e-06, - "output_cost_per_token_priority": 2e-05, - "regional_processing_uplift_multiplier_eu": 1.1, - "regional_processing_uplift_multiplier_us": 1.1, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://developers.openai.com/api/docs/pricing", + "output_cost_per_token": 4.25e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models/nvidia/nemotron-3.5-super-vl/endpoints", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "together_ai/reflection/Beam-1.0-501B-A23B": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "baseten/reflection/Beam-1.0": { + "cache_read_input_token_cost": 1.3e-07, + "input_cost_per_token": 1.3e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.3e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "nebius/reflection/beam": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/reflection%2Fbeam", + "supports_function_calling": true, + "supports_reasoning": true + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017": { + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "github_copilot/claude-sonnet-4.6": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-09-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_legacy_thinking": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.4-nano": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.25e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/grok-4.5": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/grok-4.6": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/grok-4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "meta/muse-image-1.0": { + "litellm_provider": "meta", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://dev.meta.ai/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits", "/v1/responses" ], "supported_modalities": [ @@ -78349,269 +76930,63 @@ "image" ], "supported_output_modalities": [ - "text" - ], - "supports_computer_use": true, + "image" + ] + }, + "fireworks_ai/accounts/fireworks/models/minimax-m3p1-flash": { + "cache_read_input_token_cost": 1.5e-08, + "cache_read_input_token_cost_priority": 2.25e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_priority": 2.25e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_priority": 9e-07, + "source": "https://platform.minimax.io/docs/guides/pricing", "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_native_streaming": true, - "supports_none_reasoning_effort": false, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_cache_breakpoint": true, - "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_vision": true }, - "azure_ai/gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 922000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "meta/sam-3.1": { + "input_cost_per_image": 0.0025, + "litellm_provider": "meta", + "mode": "responses", + "source": "https://dev.meta.ai/docs/pricing-rate-limits.md", "supported_endpoints": [ - "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", - "image" + "image", + "video" ], "supported_output_modalities": [ "text" - ], - "supports_computer_use": true, - "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_native_streaming": true, - "supports_none_reasoning_effort": false, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_cache_breakpoint": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + ] }, - "azure/gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "azure", - "max_input_tokens": 922000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us": { + "cache_read_input_token_cost": 9e-09, + "cache_read_input_token_cost_priority": 1.125e-08, + "input_cost_per_token": 4.5e-07, + "input_cost_per_token_priority": 5.625e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_computer_use": true, + "output_cost_per_token": 1.8e-06, + "output_cost_per_token_priority": 2.25e-06, + "source": "https://docs.fireworks.ai/serverless/us-only-serverless", "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_native_streaming": true, - "supports_none_reasoning_effort": false, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true - }, - "azure/gpt-6.1-sol-2026-09-29": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "azure", - "max_input_tokens": 922000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_computer_use": true, - "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_native_streaming": true, - "supports_none_reasoning_effort": false, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true - }, - "openrouter/openai/gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6.1-sol-pro": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6.1-sol-pro:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_above_272k_tokens": 1e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6.1-sol:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_above_272k_tokens": 1e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": true } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 617aabeeecf..98fee42de3c 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -99,22 +99,22 @@ "input_cost_per_token": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-large.md" }, "ai21.jamba-1-5-mini-v1:0": { "deprecation_date": "2026-11-26", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-07, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-mini.md" }, "ai21.jamba-instruct-v1:0": { "input_cost_per_token": 5e-07, @@ -293,6 +293,7 @@ "supports_nova_canvas_image_edit": true }, "us.writer.palmyra-x4-v1:0": { + "deprecation_date": "2027-03-09", "input_cost_per_token": 2.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -300,23 +301,25 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "supports_function_calling": true, "supports_pdf_input": true }, "us.writer.palmyra-x5-v1:0": { + "deprecation_date": "2027-03-21", "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "supports_function_calling": true, "supports_pdf_input": true }, "writer.palmyra-x4-v1:0": { + "deprecation_date": "2027-03-09", "input_cost_per_token": 2.5e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -324,42 +327,52 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", "supports_function_calling": true, "supports_pdf_input": true }, "writer.palmyra-x5-v1:0": { + "deprecation_date": "2027-03-21", "input_cost_per_token": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", "supports_function_calling": true, "supports_pdf_input": true }, "writer.palmyra-vision-7b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_vision": true }, "amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, + "output_cost_per_token_batches": 1.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -369,13 +382,19 @@ }, "amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_priority": 1.3125e-07, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -386,16 +405,21 @@ "supports_vision": true }, "amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_image_token": 1.25e-06, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.1875e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 1.75e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -406,14 +430,14 @@ "supports_vision": true }, "apac.amazon.nova-2-lite-v1:0": { - "cache_read_input_token_cost": 8.25e-08, - "input_cost_per_token": 3.3e-07, + "cache_read_input_token_cost": 9.9e-08, + "input_cost_per_token": 3.96e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 2.75e-06, + "output_cost_per_token": 3.311e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -424,16 +448,17 @@ "supports_vision": true }, "apac.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.4375e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_image_token": 1.375e-06, + "input_cost_per_audio_token": 1.375e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1.1e-05, + "source": "https://aws.amazon.com/nova/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -444,14 +469,14 @@ "supports_vision": true }, "eu.amazon.nova-2-lite-v1:0": { - "cache_read_input_token_cost": 8.25e-08, - "input_cost_per_token": 3.3e-07, + "cache_read_input_token_cost": 1.0725e-07, + "input_cost_per_token": 4.29e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 2.75e-06, + "output_cost_per_token": 3.597e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -462,16 +487,17 @@ "supports_vision": true }, "eu.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.4375e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_image_token": 1.375e-06, + "input_cost_per_audio_token": 1.375e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1.1e-05, + "source": "https://aws.amazon.com/nova/pricing/", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -483,13 +509,22 @@ }, "us.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_flex": 4.125e-08, + "cache_read_input_token_cost_priority": 1.44375e-07, "input_cost_per_token": 3.3e-07, + "input_cost_per_token_batches": 1.65e-07, + "input_cost_per_token_flex": 1.65e-07, + "input_cost_per_token_priority": 5.775e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-06, + "output_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_flex": 1.375e-06, + "output_cost_per_token_priority": 4.8125e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -500,16 +535,21 @@ "supports_vision": true }, "us.amazon.nova-2-pro-preview-20251202-v1:0": { - "cache_read_input_token_cost": 5.46875e-07, - "input_cost_per_token": 2.1875e-06, - "input_cost_per_image_token": 2.1875e-06, - "input_cost_per_audio_token": 2.1875e-06, + "cache_read_input_token_cost": 3.4375e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_image_token": 1.375e-06, + "input_cost_per_audio_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.40625e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "output_cost_per_token": 1.75e-05, + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 1.925e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -539,26 +579,60 @@ "amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 8.75e-09, "input_cost_per_token": 3.5e-08, + "input_cost_per_token_batches": 1.75e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, + "output_cost_per_token_batches": 7e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, + "amazon.nova-premier-v1:0": { + "cache_read_input_token_cost": 6.25e-07, + "cache_read_input_token_cost_priority": 1.09375e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_priority": 4.375e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.25e-05, + "output_cost_per_token_batches": 6.25e-06, + "output_cost_per_token_priority": 2.1875e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 8e-07, + "input_cost_per_token_batches": 4e-07, + "input_cost_per_token_flex": 4e-07, + "input_cost_per_token_priority": 1.4e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -639,16 +713,20 @@ "mode": "image_generation" }, "amazon.titan-image-generator-v2": { + "deprecation_date": "2026-06-30", "input_cost_per_image": 0.0, "output_cost_per_image": 0.008, "litellm_provider": "bedrock", - "mode": "image_generation" + "mode": "image_generation", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-image-generator-g1-v2.html" }, "amazon.titan-image-generator-v2:0": { + "deprecation_date": "2026-06-30", "input_cost_per_image": 0.0, "output_cost_per_image": 0.008, "litellm_provider": "bedrock", - "mode": "image_generation" + "mode": "image_generation", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-image-generator-g1-v2.html" }, "twelvelabs.marengo-embed-2-7-v1:0": { "deprecation_date": "2026-11-30", @@ -738,51 +816,58 @@ "supports_image_input": true }, "twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "us.twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "eu.twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md", "supports_video_input": true }, "global.twelvelabs.pegasus-1-2-v1:0": { + "deprecation_date": "2027-03-22", "input_cost_per_video_per_second": 0.00049, "output_cost_per_token": 7.5e-06, "litellm_provider": "bedrock", "mode": "chat", "supports_video_input": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-2.md" }, "amazon.titan-text-express-v1": { - "input_cost_per_token": 1.3e-06, + "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", - "output_cost_per_token": 1.7e-06 + "output_cost_per_token": 6e-07 }, "amazon.titan-text-lite-v1": { - "input_cost_per_token": 3e-07, + "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, "max_tokens": 4000, "mode": "chat", - "output_cost_per_token": 4e-07 + "output_cost_per_token": 2e-07 }, "amazon.titan-text-premier-v1:0": { "input_cost_per_token": 5e-07, @@ -837,7 +922,11 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-07, - "output_cost_per_token_batches": 2.5e-06 + "output_cost_per_token_batches": 2.5e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-haiku-4-5@20251001": { "cache_creation_input_token_cost": 1.25e-06, @@ -869,7 +958,7 @@ "anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", @@ -879,10 +968,6 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 3e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07 }, @@ -891,7 +976,7 @@ "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", @@ -903,11 +988,7 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 3e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07 + "supports_vision": true }, "anthropic.claude-3-7-sonnet-20240620-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -999,7 +1080,11 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "token_count_model": { + "model": "anthropic.claude-opus-4-1-20250805-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -1058,7 +1143,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1094,7 +1183,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1130,7 +1223,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1166,7 +1263,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1202,7 +1303,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "au.anthropic.claude-opus-4-6-v1": { "supports_adaptive_thinking": true, @@ -1238,7 +1343,11 @@ "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-6-v1", + "litellm_provider": "bedrock" + } }, "anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1276,7 +1385,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "anthropic.claude-mythos-preview": { "cache_creation_input_token_cost": 3.4375e-05, @@ -1334,7 +1448,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1372,7 +1491,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1410,7 +1534,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "au.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -1448,7 +1577,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "anthropic.claude-fable-5": { "cache_creation_input_token_cost": 1.25e-05, @@ -1480,13 +1614,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-fable-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, @@ -1557,13 +1696,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-fable-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.25e-05, @@ -1634,13 +1778,18 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-fable-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.375e-05, @@ -1711,7 +1860,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -1793,7 +1942,12 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -1833,7 +1987,12 @@ "prompt_cache_min_tokens": 512, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -1871,7 +2030,12 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -1911,7 +2075,12 @@ "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "global.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -1949,7 +2118,12 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -1989,7 +2163,12 @@ "prompt_cache_min_tokens": 512, "source": "https://aws.amazon.com/bedrock/pricing/", "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -2027,7 +2206,12 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "eu.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -2105,7 +2289,12 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "au.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -2145,7 +2334,12 @@ "prompt_cache_min_tokens": 512, "thinking_always_on": true, "supports_forced_tool_use": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "jp.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -2257,12 +2451,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2296,12 +2496,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2335,12 +2541,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2374,12 +2586,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "au.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2413,12 +2631,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "jp.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -2452,12 +2676,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "jp.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -2494,7 +2724,12 @@ "supports_minimal_reasoning_effort": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2528,12 +2763,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "global.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2567,12 +2808,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "global.anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "us.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2606,12 +2853,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "eu.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2645,12 +2898,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "eu-west-1" + } }, "au.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2684,12 +2943,18 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "jp.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -2723,6 +2988,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -2749,7 +3015,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2763,7 +3029,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2784,7 +3054,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2798,7 +3068,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2819,7 +3093,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2833,7 +3107,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2854,7 +3132,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2868,7 +3146,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "au.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2889,7 +3171,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2903,7 +3185,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "jp.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -2924,7 +3210,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -2938,7 +3224,11 @@ "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -2950,7 +3240,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -2971,18 +3261,23 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -3009,7 +3304,11 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, "output_cost_per_token_batches": 7.5e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "anthropic.claude-v1": { "input_cost_per_token": 8e-06, @@ -3180,13 +3479,16 @@ }, "apac.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.1e-07, + "cache_read_input_token_cost_flex": 1.05e-07, "input_cost_per_token": 8.4e-07, + "input_cost_per_token_flex": 4.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.36e-06, + "output_cost_per_token_flex": 1.68e-06, "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -3219,7 +3521,11 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "apac.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -3231,7 +3537,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -3252,7 +3558,11 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "assemblyai/best": { "input_cost_per_second": 3.333e-05, @@ -3276,6 +3586,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -3302,17 +3613,21 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "azure/ada": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 1e-07, + "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/codex-mini": { "cache_read_input_token_cost": 3.75e-07, @@ -3358,7 +3673,7 @@ "supports_function_calling": true }, "azure_ai/claude-haiku-4-5": { - "deprecation_date": "2026-10-19", + "deprecation_date": "2026-11-15", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_read_input_token_cost": 1e-07, @@ -3378,10 +3693,11 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-opus-4-5": { - "deprecation_date": "2026-10-19", + "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_read_input_token_cost": 5e-07, @@ -3402,7 +3718,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-opus-4-6": { "deprecation_date": "2027-02-02", @@ -3588,6 +3905,7 @@ "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2027-09-18", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, @@ -3604,7 +3922,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" }, "azure_ai/claude-opus-4-8": { "deprecation_date": "2027-09-01", @@ -3640,7 +3959,7 @@ "prompt_cache_min_tokens": 1024 }, "azure_ai/claude-sonnet-4-5": { - "deprecation_date": "2026-10-19", + "deprecation_date": "2026-11-30", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, @@ -3660,7 +3979,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule" }, "azure_ai/claude-sonnet-5": { "deprecation_date": "2027-06-30", @@ -3705,11 +4025,11 @@ "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -3720,7 +4040,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models" }, "azure/computer-use-preview": { "input_cost_per_token": 3e-06, @@ -3751,9 +4072,10 @@ "supports_vision": true }, "azure/container": { - "code_interpreter_cost_per_session": 0.03, + "code_interpreter_cost_per_session": 0.033, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/" }, "azure_ai/gpt-oss-120b": { "input_cost_per_token": 1.5e-07, @@ -3916,6 +4238,55 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure_ai/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure_ai/gpt-5.5": { "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5e-07, @@ -3927,7 +4298,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -3965,7 +4336,7 @@ }, "azure_ai/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-12-02", + "deprecation_date": "2027-05-18", "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 272000, @@ -4062,7 +4433,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4109,7 +4480,7 @@ "input_cost_per_token_priority": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4156,7 +4527,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4204,7 +4575,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -4252,7 +4623,7 @@ "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -4298,7 +4669,7 @@ "input_cost_per_token_priority": 6e-05, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "azure_ai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -4545,6 +4916,26 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/eu/gpt-4o": { + "deprecation_date": "2027-04-14", + "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/eu/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, @@ -4565,6 +4956,25 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/eu/gpt-4o-mini": { + "cache_read_input_token_cost": 8.3e-08, + "deprecation_date": "2027-04-14", + "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/eu/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", @@ -4606,6 +5016,7 @@ "azure/eu/gpt-4o-realtime-preview-2024-10-01": { "cache_creation_input_audio_token_cost": 2.2e-05, "cache_read_input_token_cost": 2.75e-06, + "deprecation_date": "2025-03-26", "input_cost_per_audio_token": 0.00011, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", @@ -4615,6 +5026,7 @@ "mode": "realtime", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 2.2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, @@ -4628,12 +5040,13 @@ "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_modalities": [ "text", "audio" @@ -4873,6 +5286,25 @@ "supports_vision": true, "cache_read_input_token_cost_batches": 2.75e-09 }, + "azure/eu/o1": { + "cache_read_input_token_cost": 8.25e-06, + "deprecation_date": "2026-11-19", + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/eu/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", @@ -4909,6 +5341,24 @@ "supports_prompt_caching": true, "supports_vision": false }, + "azure/eu/o3-mini": { + "cache_read_input_token_cost": 6.05e-07, + "deprecation_date": "2026-11-19", + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "azure/eu/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, "deprecation_date": "2026-11-19", @@ -5140,12 +5590,13 @@ "supports_tool_choice": true }, "azure/gpt-3.5-turbo-instruct-0914": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_tokens": 4097, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-35-turbo": { "input_cost_per_token": 5e-07, @@ -5184,20 +5635,22 @@ "supports_tool_choice": true }, "azure/gpt-35-turbo-instruct": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_tokens": 4097, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-35-turbo-instruct-0914": { - "input_cost_per_token": 1.5e-06, + "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, "max_tokens": 4097, "mode": "completion", - "output_cost_per_token": 2e-06 + "output_cost_per_token": 2.2e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-4": { "deprecation_date": "2025-06-06", @@ -5274,38 +5727,41 @@ "supports_tool_choice": true }, "azure/gpt-4-turbo": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-turbo-2024-04-09": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_vision": true }, "azure/gpt-4-turbo-vision-preview": { - "input_cost_per_token": 1e-05, + "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supports_tool_choice": true, "supports_vision": true }, @@ -5692,14 +6148,14 @@ }, "azure/gpt-audio-1.5": { "deprecation_date": "2027-08-24", - "input_cost_per_audio_token": 4e-05, + "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, "supported_endpoints": [ "/v1/chat/completions" @@ -5721,19 +6177,20 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/gpt-audio-1.5-2026-02-23": { "deprecation_date": "2027-08-24", - "input_cost_per_audio_token": 4e-05, + "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/chat/completions" ], @@ -5853,13 +6310,13 @@ "azure/gpt-4o-mini": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 1.65e-07, + "input_cost_per_token": 1.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6.6e-07, + "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5888,15 +6345,16 @@ "supports_vision": true }, "azure/gpt-4o-mini-audio-preview-2024-12-17": { - "input_cost_per_audio_token": 4e-05, - "input_cost_per_token": 2.5e-06, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 1.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_audio_token": 8e-05, - "output_cost_per_token": 1e-05, + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 6e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/chat/completions" ], @@ -6079,7 +6537,7 @@ "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, - "deprecation_date": "2027-07-31", + "deprecation_date": "2027-06-25", "input_cost_per_audio_token": 3.2e-05, "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, @@ -6090,7 +6548,7 @@ "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "supported_endpoints": [ "/v1/realtime" ], @@ -6114,7 +6572,7 @@ "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, - "deprecation_date": "2027-07-31", + "deprecation_date": "2027-06-25", "input_cost_per_audio_token": 1e-05, "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, @@ -6125,7 +6583,7 @@ "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule", "supported_endpoints": [ "/v1/realtime" ], @@ -6215,7 +6673,7 @@ }, "azure/gpt-4o-mini-transcribe": { "deprecation_date": "2027-06-15", - "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 16000, @@ -6228,7 +6686,7 @@ }, "azure/gpt-4o-mini-tts": { "deprecation_date": "2027-06-15", - "input_cost_per_token": 2.5e-06, + "input_cost_per_token": 6e-07, "litellm_provider": "azure", "mode": "audio_speech", "output_cost_per_audio_token": 1.2e-05, @@ -6248,6 +6706,7 @@ "azure/gpt-4o-realtime-preview-2024-10-01": { "cache_creation_input_audio_token_cost": 2e-05, "cache_read_input_token_cost": 2.5e-06, + "deprecation_date": "2025-03-26", "input_cost_per_audio_token": 0.0001, "input_cost_per_token": 5e-06, "litellm_provider": "azure", @@ -6257,6 +6716,7 @@ "mode": "realtime", "output_cost_per_audio_token": 0.0002, "output_cost_per_token": 2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, @@ -6269,12 +6729,13 @@ "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8e-05, "output_cost_per_token": 2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_modalities": [ "text", "audio" @@ -6291,27 +6752,29 @@ "supports_tool_choice": true }, "azure/gpt-4o-transcribe": { - "deprecation_date": "2026-12-31", - "input_cost_per_audio_token": 2.5e-06, + "deprecation_date": "2026-10-15", + "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/audio/transcriptions" ] }, "azure/gpt-4o-transcribe-diarize": { "deprecation_date": "2027-04-15", - "input_cost_per_audio_token": 2.5e-06, + "input_cost_per_audio_token": 6e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 2000, "mode": "audio_transcription", "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/audio/transcriptions" ] @@ -6320,6 +6783,9 @@ "deprecation_date": "2027-05-06", "input_cost_per_second": 0.0002833333333333333, "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "audio_transcription", "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-realtime-whisper", "supported_endpoints": [ @@ -7374,7 +7840,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7430,7 +7896,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7480,7 +7946,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7530,7 +7996,7 @@ "input_cost_per_token_priority": 5e-06, "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7586,7 +8052,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7636,7 +8102,7 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_priority": 3.3e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -7687,7 +8153,7 @@ "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -7736,7 +8202,7 @@ "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -8413,11 +8879,17 @@ "azure/gpt-6-sol": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_priority": 4e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_priority": 4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -8425,11 +8897,9 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -8462,11 +8932,17 @@ "azure/gpt-6-sol-2026-09-22": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_priority": 4e-07, "deprecation_date": "2028-03-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_priority": 4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -8474,11 +8950,9 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_priority": 2e-05, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -8508,9 +8982,254 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/gpt-6.1-sol-2026-09-29": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/us/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/eu/gpt-6.1-sol": { + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2.4e-06, + "input_cost_per_token_above_272k_tokens": 4.8e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "azure/apac/gpt-6.1-sol": { + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-07, + "deprecation_date": "2028-03-11", + "input_cost_per_token": 2.4e-06, + "input_cost_per_token_above_272k_tokens": 4.8e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, - "deprecation_date": "2026-12-02", + "deprecation_date": "2027-05-18", "input_cost_per_token": 5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -8906,10 +9625,16 @@ "deprecation_date": "2028-03-11", "cache_creation_input_token_cost": 2.75e-06, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05, + "cache_creation_input_token_cost_priority": 5.5e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07, + "cache_read_input_token_cost_priority": 4.4e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8.8e-06, + "input_cost_per_token_priority": 4.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -8917,11 +9642,9 @@ "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, + "output_cost_per_token_above_272k_tokens_priority": 3.3e-05, + "output_cost_per_token_priority": 2.2e-05, + "search_context_cost_per_query": {"search_context_size_high":0.01,"search_context_size_low":0.01,"search_context_size_medium":0.01}, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", @@ -8953,7 +9676,7 @@ }, "azure/us/gpt-chat-latest": { "cache_read_input_token_cost": 5.5e-07, - "deprecation_date": "2026-12-02", + "deprecation_date": "2027-05-18", "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -9228,7 +9951,7 @@ "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9287,7 +10010,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9342,7 +10065,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9394,7 +10117,7 @@ "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9454,7 +10177,7 @@ "input_cost_per_token_above_272k_tokens_priority": 2e-05, "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9513,7 +10236,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9566,7 +10289,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9620,7 +10343,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -9673,7 +10396,7 @@ "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -10001,6 +10724,7 @@ "cache_read_input_token_cost_batches": 1e-08 }, "azure/gpt-image-1": { + "cache_read_input_image_token_cost": 2.5e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-10-23", "input_cost_per_image_token": 1e-05, @@ -10008,28 +10732,32 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 4e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/hd/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 7.629e-08, + "input_cost_per_pixel": 8.39233e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/hd/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, + "input_cost_per_pixel": 7.19343e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/hd/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, + "input_cost_per_pixel": 7.19343e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/high/1024-x-1024/gpt-image-1": { "deprecation_date": "2026-10-23", @@ -10122,6 +10850,7 @@ ] }, "azure/gpt-image-1-mini": { + "cache_read_input_image_token_cost": 2.5e-07, "cache_read_input_token_cost": 2e-07, "deprecation_date": "2027-04-07", "input_cost_per_image_token": 2.5e-06, @@ -10129,12 +10858,14 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 8e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-1.5": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2026-12-16", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10142,12 +10873,15 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, + "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-1.5-2025-12-16": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2026-12-16", "input_cost_per_token": 5e-06, @@ -10155,12 +10889,15 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3.2e-05, + "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ] }, "azure/gpt-image-2": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-10-21", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10168,6 +10905,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10176,6 +10914,7 @@ "supports_pdf_input": true }, "azure/gpt-image-2.5-flare": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10183,6 +10922,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10191,6 +10931,7 @@ "supports_pdf_input": true }, "azure/gpt-image-2.5-sunburst": { + "cache_read_input_image_token_cost": 2e-06, "deprecation_date": "2027-09-09", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, @@ -10198,6 +10939,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10206,6 +10948,7 @@ "supports_pdf_input": true }, "azure/gpt-image-2-2026-04-21": { + "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", "input_cost_per_token": 5e-06, @@ -10213,6 +10956,7 @@ "litellm_provider": "azure", "mode": "image_generation", "output_cost_per_image_token": 3e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10481,7 +11225,6 @@ }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -10550,7 +11293,6 @@ "output_cost_per_token_batches": 4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -10582,7 +11324,6 @@ "output_cost_per_token_batches": 4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ - "/v1/chat/completions", "/v1/batch", "/v1/responses" ], @@ -10659,52 +11400,55 @@ "output_cost_per_token": 0.0 }, "azure/standard/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 3.81469e-08, + "input_cost_per_pixel": 4.19617e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/standard/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, + "input_cost_per_pixel": 4.79562e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/standard/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, + "input_cost_per_pixel": 4.79562e-08, "litellm_provider": "azure", "mode": "image_generation", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-3-large": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 1.3e-07, + "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", - "max_input_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 8192, + "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-3-small": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 2e-08, + "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", - "max_input_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 8192, + "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/text-embedding-ada-002": { "deprecation_date": "2028-02-09", - "input_cost_per_token": 1e-07, + "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", - "max_input_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 8192, + "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/speech/azure-tts": { "input_cost_per_character": 1.5e-05, @@ -10737,9 +11481,10 @@ }, "azure/tts-1-hd": { "deprecation_date": "2026-12-15", - "input_cost_per_character": 3e-05, + "input_cost_per_character": 3.3e-05, "litellm_provider": "azure", - "mode": "audio_speech" + "mode": "audio_speech", + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" }, "azure/us/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", @@ -10871,6 +11616,26 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/gpt-4o": { + "deprecation_date": "2027-04-14", + "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, @@ -10891,6 +11656,25 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/gpt-4o-mini": { + "cache_read_input_token_cost": 8.3e-08, + "deprecation_date": "2027-04-14", + "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", @@ -10932,6 +11716,7 @@ "azure/us/gpt-4o-realtime-preview-2024-10-01": { "cache_creation_input_audio_token_cost": 2.2e-05, "cache_read_input_token_cost": 2.75e-06, + "deprecation_date": "2025-03-26", "input_cost_per_audio_token": 0.00011, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", @@ -10941,6 +11726,7 @@ "mode": "realtime", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 2.2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_audio_input": true, "supports_audio_output": true, "supports_function_calling": true, @@ -10954,12 +11740,13 @@ "input_cost_per_audio_token": 4.4e-05, "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "max_input_tokens": 128000, + "max_input_tokens": 16000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "realtime", - "output_cost_per_audio_token": 8e-05, + "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, + "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", "supported_modalities": [ "text", "audio" @@ -11199,6 +11986,25 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/o1": { + "cache_read_input_token_cost": 8.25e-06, + "deprecation_date": "2026-11-19", + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", @@ -11235,6 +12041,39 @@ "supports_prompt_caching": true, "supports_vision": false }, + "azure/us/o3": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/o3-2025-04-16": { "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, @@ -11268,6 +12107,24 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/us/o3-mini": { + "cache_read_input_token_cost": 6.05e-07, + "deprecation_date": "2026-11-19", + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "azure/us/o3-mini-2025-01-31": { "cache_read_input_token_cost": 6.05e-07, "deprecation_date": "2026-11-19", @@ -11286,6 +12143,27 @@ "supports_tool_choice": true, "supports_vision": false }, + "azure/us/o4-mini": { + "cache_read_input_token_cost": 3.03e-07, + "deprecation_date": "2026-11-19", + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/us/o4-mini-2025-04-16": { "cache_read_input_token_cost": 3.03e-07, "deprecation_date": "2026-11-19", @@ -11358,6 +12236,8 @@ }, "azure_ai/FLUX-1.1-pro": { "litellm_provider": "azure_ai", + "max_input_tokens": 5000, + "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", @@ -11367,18 +12247,22 @@ }, "azure_ai/FLUX.1-Kontext-pro": { "litellm_provider": "azure_ai", + "max_input_tokens": 5000, + "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, - "source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", "supported_endpoints": [ "/v1/images/generations" ] }, "azure_ai/flux.2-pro": { "litellm_provider": "azure_ai", + "max_input_tokens": 32000, + "max_tokens": 32000, "mode": "image_generation", "output_cost_per_image": 0.04, - "source": "https://ai.azure.com/explore/models/flux.2-pro/version/1/registry/azureml-blackforestlabs", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_endpoints": [ "/v1/images/generations" ] @@ -11699,34 +12583,37 @@ "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", "mode": "image_generation", - "output_cost_per_image": 0.05, + "output_cost_per_image": 0.048, "output_cost_per_image_token": 4.7e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], - "deprecation_date": "2026-10-01" + "deprecation_date": "2026-10-01", + "max_input_tokens": 32000 }, "azure_ai/MAI-Image-2.5-Flash": { "input_cost_per_image_token": 1.75e-06, "input_cost_per_token": 1.75e-06, "litellm_provider": "azure_ai", "mode": "image_generation", - "output_cost_per_image": 0.0338, - "output_cost_per_image_token": 3.3e-05, + "output_cost_per_image": 0.02, + "output_cost_per_image_token": 1.95e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], - "deprecation_date": "2026-10-01" + "deprecation_date": "2026-10-01", + "max_input_tokens": 32000 }, "azure_ai/MAI-Image-2.5-Pro": { "deprecation_date": "2026-10-01", "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", + "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image": 0.1085, "output_cost_per_image_token": 0.000106, @@ -11764,11 +12651,11 @@ "input_cost_per_token": 7.1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.1e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_tool_choice": true }, @@ -11776,8 +12663,8 @@ "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11799,6 +12686,7 @@ "supports_vision": true }, "azure_ai/Meta-Llama-3-70B-Instruct": { + "deprecation_date": "2025-06-30", "input_cost_per_token": 1.1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 8192, @@ -11806,9 +12694,11 @@ "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.7e-07, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true }, "azure_ai/Meta-Llama-3.1-70B-Instruct": { + "deprecation_date": "2025-06-30", "input_cost_per_token": 2.68e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11816,10 +12706,11 @@ "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.54e-06, - "source": "https://marketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true }, "azure_ai/Phi-3-medium-128k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.7e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11827,11 +12718,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-medium-4k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.7e-07, "litellm_provider": "azure_ai", "max_input_tokens": 4096, @@ -11839,11 +12731,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-mini-128k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11851,11 +12744,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-mini-4k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 4096, @@ -11863,11 +12757,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-small-128k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11875,11 +12770,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3-small-8k-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 8192, @@ -11887,11 +12783,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3.5-MoE-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11899,11 +12796,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.4e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3.5-mini-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11911,11 +12809,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": false }, "azure_ai/Phi-3.5-vision-instruct": { + "deprecation_date": "2025-08-30", "input_cost_per_token": 1.3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -11923,7 +12822,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true, "supports_vision": true }, @@ -12058,6 +12957,7 @@ "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/" }, "azure_ai/MAI-DS-R1": { + "deprecation_date": "2026-02-27", "input_cost_per_token": 1.35e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12065,11 +12965,12 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/cohere-rerank-v3-english": { + "deprecation_date": "2025-06-30", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -12077,9 +12978,11 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "rerank", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" }, "azure_ai/cohere-rerank-v3-multilingual": { + "deprecation_date": "2025-06-30", "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", @@ -12087,7 +12990,8 @@ "max_output_tokens": 4096, "max_tokens": 4096, "mode": "rerank", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" }, "azure_ai/cohere-rerank-v4.0-pro": { "input_cost_per_query": 0.0025, @@ -12114,12 +13018,12 @@ "azure_ai/deepseek-v3.2": { "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -12129,12 +13033,12 @@ "azure_ai/deepseek-v3.2-speciale": { "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -12142,6 +13046,7 @@ "supports_tool_choice": true }, "azure_ai/deepseek-v3": { + "deprecation_date": "2025-08-31", "input_cost_per_token": 1.14e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12149,7 +13054,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true }, "azure_ai/deepseek-v4-pro": { @@ -12190,11 +13095,11 @@ "input_cost_per_token": 4.4e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 384000, + "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -12216,17 +13121,18 @@ "text", "image" ], - "supports_embedding_image_input": true + "supports_embedding_image_input": true, + "input_cost_per_image_token": 4.7e-07 }, "azure_ai/grok-4": { "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 262000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -12239,12 +13145,12 @@ "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "azure_ai", "max_input_tokens": 200000, - "max_output_tokens": 200000, - "max_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -12265,7 +13171,7 @@ "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -12315,9 +13221,9 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, @@ -12329,9 +13235,9 @@ "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, @@ -12343,18 +13249,19 @@ "azure_ai/grok-code-fast-1": { "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/jais-30b-chat": { + "deprecation_date": "2026-01-30", "input_cost_per_token": 0.0032, "litellm_provider": "azure_ai", "max_input_tokens": 8192, @@ -12362,9 +13269,10 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00971, - "source": "https://ai.azure.com/catalog/models/jais-30b-chat" + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" }, "azure_ai/jamba-instruct": { + "deprecation_date": "2025-03-01", "input_cost_per_token": 5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 70000, @@ -12372,6 +13280,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_tool_choice": true }, "azure_ai/kimi-k2.5": { @@ -12416,6 +13325,7 @@ "supports_prompt_caching": true }, "azure_ai/ministral-3b": { + "deprecation_date": "2026-12-09", "input_cost_per_token": 4e-08, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12428,6 +13338,7 @@ "supports_tool_choice": true }, "azure_ai/mistral-large": { + "deprecation_date": "2025-04-15", "input_cost_per_token": 4e-06, "litellm_provider": "azure_ai", "max_input_tokens": 32000, @@ -12435,10 +13346,12 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.2e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/mistral-large-2407": { + "deprecation_date": "2025-05-13", "input_cost_per_token": 2e-06, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12446,7 +13359,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true, "supports_tool_choice": true }, @@ -12476,6 +13389,7 @@ "supports_vision": true }, "azure_ai/mistral-medium-2505": { + "deprecation_date": "2026-12-09", "input_cost_per_token": 4e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, @@ -12488,6 +13402,7 @@ "supports_tool_choice": true }, "azure_ai/mistral-nemo": { + "deprecation_date": "2026-01-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 131072, @@ -12495,10 +13410,11 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice", + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true }, "azure_ai/mistral-small": { + "deprecation_date": "2025-07-31", "input_cost_per_token": 1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 32000, @@ -12506,10 +13422,12 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/mistral-small-2503": { + "deprecation_date": "2026-12-09", "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, @@ -12535,43 +13453,43 @@ "source": "https://developers.openai.com/api/docs/pricing" }, "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { + "cost_per_second": 0.001902, "input_cost_per_second": 0.001902, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_second": 0.001902, "supports_tool_choice": true }, "bedrock/*/1-month-commitment/cohere.command-text-v14": { + "cost_per_second": 0.011, "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_second": 0.011, "supports_tool_choice": true }, "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { + "cost_per_second": 0.0011416, "input_cost_per_second": 0.0011416, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_second": 0.0011416, "supports_tool_choice": true }, "bedrock/*/6-month-commitment/cohere.command-text-v14": { + "cost_per_second": 0.0066027, "input_cost_per_second": 0.0066027, "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_second": 0.0066027, "supports_tool_choice": true }, "bedrock/guardrails": { @@ -12590,61 +13508,61 @@ "source": "https://aws.amazon.com/bedrock/pricing/" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.01475, "input_cost_per_second": 0.01475, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.01475, "supports_tool_choice": true }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.0455, "input_cost_per_second": 0.0455, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.0455 + "mode": "chat" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.0455, "input_cost_per_second": 0.0455, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.0455, "supports_tool_choice": true }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.008194, "input_cost_per_second": 0.008194, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.008194, "supports_tool_choice": true }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.02527, "input_cost_per_second": 0.02527, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.02527 + "mode": "chat" }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.02527, "input_cost_per_second": 0.02527, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.02527, "supports_tool_choice": true }, "bedrock/ap-northeast-1/anthropic.claude-instant-v1": { @@ -12679,12 +13597,14 @@ }, "bedrock/ap-northeast-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -12692,32 +13612,36 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/ap-northeast-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/ap-northeast-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -12725,71 +13649,86 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/ap-northeast-1/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.3e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.03e-06, + "output_cost_per_token_flex": 1.52e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/ap-northeast-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_flex": 1.8e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/ap-northeast-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/moonshotai.kimi-k2-thinking": { - "input_cost_per_token": 7.3e-07, + "deprecation_date": "2027-03-30", + "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", - "output_cost_per_token": 3.03e-06, + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", - "output_cost_per_token": 3.03e-06, - "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", + "output_cost_per_token": 3e-06, + "output_cost_per_token_flex": 1.5e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -12800,31 +13739,37 @@ "supports_response_schema": true }, "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.18e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4.2e-06 + "output_cost_per_token": 4.2e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.2e-07 + "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/ap-south-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -12832,32 +13777,36 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/ap-south-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/ap-south-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -12865,59 +13814,69 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/ap-south-1/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.1e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.94e-06, + "output_cost_per_token_flex": 1.47e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/ap-south-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_flex": 1.8e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/ap-south-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/ap-southeast-2/minimax.minimax-m2.5": { - "input_cost_per_token": 3.09e-07, + "input_cost_per_token": 3.1e-07, + "input_cost_per_token_flex": 1.55e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -12925,16 +13884,19 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.236e-06 + "output_cost_per_token": 1.24e-06, + "output_cost_per_token_flex": 6.2e-07 }, "bedrock/ap-southeast-3/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -12942,32 +13904,36 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/ap-southeast-3/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/ap-southeast-3/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -12975,66 +13941,77 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/ap-southeast-3/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_flex": 1.8e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/ap-southeast-3/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.05e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4.03e-06 + "output_cost_per_token": 4.03e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6.9e-07 + "output_cost_per_token": 6.9e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-north-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13042,32 +14019,36 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/eu-north-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/eu-north-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13075,80 +14056,83 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/eu-north-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_flex": 1.8e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.01635, "input_cost_per_second": 0.01635, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.01635, "supports_tool_choice": true }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.0415, "input_cost_per_second": 0.0415, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.0415 + "mode": "chat" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.0415, "input_cost_per_second": 0.0415, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.0415, "supports_tool_choice": true }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.009083, "input_cost_per_second": 0.009083, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.009083, "supports_tool_choice": true }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.02305, "input_cost_per_second": 0.02305, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.02305 + "mode": "chat" }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.02305, "input_cost_per_second": 0.02305, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.02305, "supports_tool_choice": true }, "bedrock/eu-central-1/anthropic.claude-instant-v1": { @@ -13181,29 +14165,33 @@ "supports_tool_choice": true }, "bedrock/eu-central-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/eu-central-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13211,66 +14199,77 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/eu-central-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.86e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.78e-06 + "output_cost_per_token": 3.78e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6.5e-07 + "output_cost_per_token": 6.5e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-west-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/eu-west-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13278,66 +14277,77 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/eu-west-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.45e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 4.55e-06 + "output_cost_per_token": 4.55e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 7.8e-07 + "output_cost_per_token": 7.8e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/eu-west-2/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.7e-07, + "input_cost_per_token_flex": 2.35e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.86e-06, + "output_cost_per_token_flex": 9.3e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/eu-west-2/minimax.minimax-m2.5": { "input_cost_per_token": 4.7e-07, + "input_cost_per_token_flex": 2.35e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13345,16 +14355,19 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.86e-06 + "output_cost_per_token": 1.86e-06, + "output_cost_per_token_flex": 9.3e-07 }, "bedrock/eu-west-2/nvidia.nemotron-super-3-120b": { "input_cost_per_token": 2.3e-07, + "input_cost_per_token_flex": 1.15e-07, "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.01e-06, + "output_cost_per_token_flex": 5.05e-07, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_audio_input": false, "supports_function_calling": true, @@ -13366,75 +14379,85 @@ }, "bedrock/eu-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 7.8e-07, + "input_cost_per_token_flex": 3.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.86e-06, + "output_cost_per_token_flex": 9.3e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 5.2e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.56e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 5.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9.1e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "bedrock/eu-south-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/eu-south-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13442,23 +14465,26 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/eu-south-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -13479,31 +14505,37 @@ "cache_creation_input_token_cost": 3.75e-06 }, "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.45e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 5.88e-06 + "output_cost_per_token": 5.88e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.01e-06 + "output_cost_per_token": 1.01e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/sa-east-1/deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13511,32 +14543,36 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/sa-east-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/sa-east-1/minimax.minimax-m2.5": { "input_cost_per_token": 3.6e-07, + "input_cost_per_token_flex": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13544,107 +14580,116 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.44e-06 + "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07 }, "bedrock/sa-east-1/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.3e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.03e-06, + "output_cost_per_token_flex": 1.52e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/sa-east-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 7.2e-07, + "input_cost_per_token_flex": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3.6e-06, + "output_cost_per_token_flex": 1.8e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/sa-east-1/qwen.qwen3-coder-next": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, + "output_cost_per_token_flex": 7.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.011, "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.011, "supports_tool_choice": true }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.0175 + "mode": "chat" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.0175, "supports_tool_choice": true }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.00611, "input_cost_per_second": 0.00611, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.00611, "supports_tool_choice": true }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.00972 + "mode": "chat" }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.00972, "supports_tool_choice": true }, "bedrock/us-east-1/anthropic.claude-instant-v1": { @@ -13678,62 +14723,72 @@ "supports_tool_choice": true }, "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.5e-06 + "output_cost_per_token": 3.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-07 + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-east-1/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_flex": 3.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_flex": 9.25e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13741,29 +14796,34 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/us-east-1/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, + "input_cost_per_token_flex": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/us-east-1/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_flex": 1.5e-07, "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", @@ -13773,59 +14833,69 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" }, "bedrock/us-east-1/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/us-east-1/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_flex": 1.5e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/us-east-1/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_flex": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/us-east-2/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_flex": 3.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_flex": 9.25e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -13833,32 +14903,36 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/us-east-2/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, + "input_cost_per_token_flex": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/us-east-2/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_flex": 1.5e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, @@ -13866,50 +14940,59 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "output_cost_per_token": 1.2e-06 + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07 }, "bedrock/us-east-2/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/us-east-2/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_flex": 1.5e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/us-east-2/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_flex": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.4e-07, @@ -13995,7 +15078,11 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -14114,7 +15201,7 @@ "output_vector_size": 1536 }, "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": { - "input_cost_per_token": 2e-07, + "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_tokens": 8192, @@ -14123,13 +15210,13 @@ "output_vector_size": 1024 }, "bedrock/us-gov-west-1/amazon.titan-text-express-v1": { - "input_cost_per_token": 1.3e-06, + "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", - "output_cost_per_token": 1.7e-06 + "output_cost_per_token": 1.6e-06 }, "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": { "input_cost_per_token": 3e-07, @@ -14172,7 +15259,11 @@ "supports_vision": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -14220,79 +15311,83 @@ "supports_pdf_input": true }, "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.5e-06 + "output_cost_per_token": 3.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-07 + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.011, "input_cost_per_second": 0.011, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.011, "supports_tool_choice": true }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.0175 + "mode": "chat" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.0175, "input_cost_per_second": 0.0175, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.0175, "supports_tool_choice": true }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": { + "cost_per_second": 0.00611, "input_cost_per_second": 0.00611, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.00611, "supports_tool_choice": true }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": { + "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, - "mode": "chat", - "output_cost_per_second": 0.00972 + "mode": "chat" }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { + "cost_per_second": 0.00972, "input_cost_per_second": 0.00972, "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_second": 0.00972, "supports_tool_choice": true }, "bedrock/us-west-2/anthropic.claude-instant-v1": { @@ -14326,44 +15421,50 @@ "supports_tool_choice": true }, "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "bedrock/us-west-2/deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_flex": 3.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_flex": 9.25e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -14371,29 +15472,34 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html" }, "bedrock/us-west-2/minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, + "input_cost_per_token_flex": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-1.html" }, "bedrock/us-west-2/minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_flex": 1.5e-07, "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock", - "max_input_tokens": 1000000, + "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", @@ -14403,50 +15509,58 @@ "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html" }, "bedrock/us-west-2/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html", "supports_function_calling": true, "supports_reasoning": true }, "bedrock/us-west-2/moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_flex": 1.5e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, "supports_audio_input": false, "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html" }, "bedrock/us-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_flex": 2.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 262144, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html" }, "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": { "cache_creation_input_token_cost": 1e-06, @@ -14642,6 +15756,7 @@ "source": "https://developers.openai.com/api/docs/pricing" }, "claude-haiku-4-5-20251001": { + "supports_web_search": true, "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, "cache_creation_input_token_cost_batches": 6.25e-07, @@ -14699,18 +15814,14 @@ "claude-sonnet-4-5": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_creation_input_token_cost_batches": 1.875e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, "cache_read_input_token_cost_batches": 1.5e-07, + "deprecation_date": "2026-11-30", "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -14737,18 +15848,14 @@ "claude-sonnet-4-5-20250929": { "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_creation_input_token_cost_batches": 1.875e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, "cache_read_input_token_cost_batches": 1.5e-07, + "deprecation_date": "2026-11-30", "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -14774,6 +15881,7 @@ "source": "https://docs.anthropic.com/en/docs/about-claude/pricing" }, "claude-sonnet-5": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, @@ -14817,7 +15925,54 @@ "prompt_cache_min_tokens": 1024, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, + "claude-sonnet-5-5": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "provider_specific_entry": { + "us": 1.1 + }, + "supports_output_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_web_search": true + }, "claude-sonnet-4-6": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, @@ -14840,7 +15995,7 @@ }, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -14891,6 +16046,7 @@ "output_cost_per_token_batches": 7.5e-06 }, "claude-opus-4-5-20251101": { + "supports_web_search": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, "cache_creation_input_token_cost_batches": 3.125e-06, @@ -14960,6 +16116,7 @@ "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-6": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -15045,6 +16202,7 @@ "prompt_cache_min_tokens": 4096 }, "claude-opus-4-7": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -15132,6 +16290,7 @@ "prompt_cache_min_tokens": 2048 }, "claude-fable-5": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, @@ -15176,6 +16335,7 @@ "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-fable-5-1": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, @@ -15221,6 +16381,7 @@ "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-5-5": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, @@ -15258,9 +16419,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "provider_specific_entry": { - "fast": 2.0 - }, + "provider_specific_entry": {"us":1.1,"fast":2}, "supports_output_config": true, "supports_speed": true, "supports_fast_mode": true, @@ -15268,6 +16427,7 @@ "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-5": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -15315,6 +16475,7 @@ "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, "claude-opus-4-8": { + "supports_web_search": true, "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, @@ -15361,6 +16522,82 @@ "prompt_cache_min_tokens": 1024, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, + "cloudflare/clef-omni": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 64000, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/", + "supports_audio_input": true, + "supports_video_input": true, + "supports_vision": true + }, + "cloudflare/@cf/cloudflare/clef-omni": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 64000, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clef-omni/", + "supports_audio_input": true, + "supports_video_input": true, + "supports_vision": true + }, + "cloudflare/clef": { + "input_cost_per_token": 2.4e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true + }, + "cloudflare/clef-flash": { + "input_cost_per_token": 9e-08, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true + }, + "cloudflare/@cf/cloudflare/clef": { + "input_cost_per_token": 2.4e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true + }, + "cloudflare/@cf/cloudflare/clef-flash": { + "input_cost_per_token": 9e-08, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/", + "supports_vision": true + }, + "cloudflare/clairic": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "extraction", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clairic/", + "supports_vision": true + }, + "cloudflare/@cf/cloudflare/clairic": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cloudflare", + "max_input_tokens": 65536, + "mode": "extraction", + "output_cost_per_token": 0.0, + "source": "https://developers.cloudflare.com/workers-ai/models/clairic/", + "supports_vision": true + }, "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { "input_cost_per_token": 1.923e-06, "litellm_provider": "cloudflare", @@ -15796,7 +17033,31 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, - "supports_embedding_image_input": true + "supports_embedding_image_input": true, + "input_cost_per_image_token": 4.7e-07, + "source": "https://cohere.com/pricing" + }, + "cohere/embed-v5.0-pro": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "cohere", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048, + "supports_embedding_image_input": true, + "source": "https://cohere.com/pricing" + }, + "cohere/embed-v5.0-fast": { + "input_cost_per_token": 8e-08, + "litellm_provider": "cohere", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048, + "supports_embedding_image_input": true, + "source": "https://cohere.com/pricing" }, "cohere/parse-v5.0": { "litellm_provider": "cohere", @@ -15811,11 +17072,12 @@ "input_cost_per_query": 0.002, "input_cost_per_token": 0.0, "litellm_provider": "bedrock", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "rerank", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-cohere-rerank-3-5.md" }, "command-a-03-2025": { "input_cost_per_token": 2.5e-06, @@ -15896,6 +17158,144 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "coralbricks/glm-5.3-fast": { + "cache_creation_input_token_cost": 1.68e-06, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1.12e-06, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "coralbricks/glm-5.3-fp4": { + "cache_creation_input_token_cost": 1.68e-06, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1.12e-06, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "coralbricks/glm-5.3": { + "cache_creation_input_token_cost": 1.68e-06, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1.12e-06, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "coralbricks/deepseek-v4.1-flash-fast": { + "cache_creation_input_token_cost": 9e-08, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1e-08, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "coralbricks/deepseek-v4.1-flash-fast-fp4": { + "cache_creation_input_token_cost": 9e-08, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1e-08, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "coralbricks/deepseek-v4.1-flash": { + "cache_creation_input_token_cost": 9e-08, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 1e-08, + "litellm_provider": "coralbricks", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.coralbricks.ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, "computer-use-preview": { "deprecation_date": "2026-07-23", "input_cost_per_token": 3e-06, @@ -15926,8 +17326,39 @@ "supports_vision": true, "source": "https://platform.openai.com/docs/models/computer-use-preview" }, + "computer-use-preview-2025-03-11": { + "deprecation_date": "2026-07-23", + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://developers.openai.com/api/docs/models/computer-use-preview" + }, "deepseek-chat": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, @@ -15949,6 +17380,7 @@ }, "deepseek-reasoner": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, @@ -16810,7 +18242,9 @@ ] }, "dashscope/qwen3.7-max": { + "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "dashscope", "max_input_tokens": 991808, @@ -16961,6 +18395,281 @@ "/v1/images/generations" ] }, + "dashscope/wan3.0-video": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", + "output_cost_per_second": 0.165025, + "output_cost_per_second_480p": 0.041256, + "output_cost_per_second_720p": 0.082513, + "output_cost_per_second_1080p": 0.165025, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan3.0-video-prime": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", + "output_cost_per_second": 0.254399, + "output_cost_per_second_480p": 0.0636, + "output_cost_per_second_720p": 0.127199, + "output_cost_per_second_1080p": 0.254399, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.1-t2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.1-i2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.1-r2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.0-t2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.0-i2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/happyhorse-1.0-r2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan2.7-t2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan2.7-i2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "dashscope/wan2.7-r2v": { + "litellm_provider": "dashscope", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, "qwencloud/deepseek-v4-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, @@ -17802,7 +19511,9 @@ ] }, "qwencloud/qwen3.7-max": { + "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "qwencloud", "max_input_tokens": 991808, @@ -17913,6 +19624,281 @@ "/v1/images/generations" ] }, + "qwencloud/wan3.0-video": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", + "output_cost_per_second": 0.2, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.2, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan3.0-video-prime": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", + "output_cost_per_second": 0.28, + "output_cost_per_second_480p": 0.068, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.28, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.1-t2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", + "output_cost_per_second": 0.18, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.18, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 text-to-video. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.1-i2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", + "output_cost_per_second": 0.18, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.18, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 image-to-video from a first frame. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.1-r2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", + "output_cost_per_second": 0.18, + "output_cost_per_second_480p": 0.07, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.18, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.0-t2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", + "output_cost_per_second": 0.24, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.24, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.0-i2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", + "output_cost_per_second": 0.24, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.24, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/happyhorse-1.0-r2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", + "output_cost_per_second": 0.24, + "output_cost_per_second_720p": 0.14, + "output_cost_per_second_1080p": 0.24, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan2.7-t2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", + "output_cost_per_second": 0.15, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.15, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 text-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan2.7-i2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", + "output_cost_per_second": 0.15, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.15, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwencloud/wan2.7-r2v": { + "litellm_provider": "qwencloud", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", + "output_cost_per_second": 0.15, + "output_cost_per_second_720p": 0.1, + "output_cost_per_second_1080p": 0.15, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "Wan 2.7 reference-to-video. No 480P tier. Singapore list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, "qwen_ai_platform/deepseek-v4-flash": { "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 2e-07, @@ -18754,7 +20740,9 @@ ] }, "qwen_ai_platform/qwen3.7-max": { + "cache_creation_input_token_cost": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "explicit_cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, @@ -18905,6 +20893,281 @@ "/v1/images/generations" ] }, + "qwen_ai_platform/wan3.0-video": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video", + "output_cost_per_second": 0.165025, + "output_cost_per_second_480p": 0.041256, + "output_cost_per_second_720p": 0.082513, + "output_cost_per_second_1080p": 0.165025, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan3.0-video-prime": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video-prime", + "output_cost_per_second": 0.254399, + "output_cost_per_second_480p": 0.0636, + "output_cost_per_second_720p": 0.127199, + "output_cost_per_second_1080p": 0.254399, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 3.0 fast tier. Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.1-t2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-t2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 text-to-video. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.1-i2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-i2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.1 image-to-video from a first frame. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.1-r2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-1-r2v", + "output_cost_per_second": 0.165026, + "output_cost_per_second_480p": 0.0618845, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.165026, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.1 reference-to-video, 1 to 9 reference images. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.0-t2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-t2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.0-i2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-i2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "HappyHorse 1.0 image-to-video from a first frame. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/happyhorse-1.0-r2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/happyhorse-1-0-r2v", + "output_cost_per_second": 0.220034, + "output_cost_per_second_720p": 0.123769, + "output_cost_per_second_1080p": 0.220034, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "HappyHorse 1.0 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan2.7-t2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-t2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 text-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan2.7-i2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-i2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "first_frame" + }, + "metadata": { + "comment": "Wan 2.7 image-to-video (first frame, first and last frame, continuation). No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, + "qwen_ai_platform/wan2.7-r2v": { + "litellm_provider": "qwen_ai_platform", + "mode": "video_generation", + "source": "https://www.alibabacloud.com/help/en/model-studio/wan2-7-r2v", + "output_cost_per_second": 0.143353, + "output_cost_per_second_720p": 0.086012, + "output_cost_per_second_1080p": 0.143353, + "supported_modalities": [ + "text", + "image", + "video", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "provider_specific_entry": { + "dashscope_video_reference_input": "reference_image" + }, + "metadata": { + "comment": "Wan 2.7 reference-to-video. No 480P tier. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier." + } + }, "databricks/databricks-bge-large-en": { "cache_creation_input_token_cost": 1.0003e-07, "cache_read_input_token_cost": 1.0003e-07, @@ -19094,7 +21357,7 @@ "output_cost_per_token": 2.5000010000000002e-05, "output_dbu_cost_per_token": 0.000357143, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, "supports_legacy_thinking": true, "supports_prompt_caching": true, @@ -19186,6 +21449,41 @@ "supports_tool_choice": true, "supports_vision": true }, + "databricks/databricks-claude-opus-5-5": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_creation_input_token_cost_above_1hr": 8.00002e-06, + "cache_read_input_token_cost": 1.9999e-07, + "input_cost_per_token": 4.00001e-06, + "input_dbu_cost_per_token": 5.7143e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.999998e-05, + "output_dbu_cost_per_token": 0.000285714, + "prompt_cache_min_tokens": 512, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_anthropic_thinking_payload": true, + "supports_assistant_prefill": false, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_output_config": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true + }, "databricks/databricks-claude-sonnet-4": { "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, @@ -19274,7 +21572,7 @@ "output_cost_per_token": 1.5000020000000002e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, "supports_legacy_thinking": true, "supports_prompt_caching": true, @@ -19317,6 +21615,7 @@ "input_cost_per_token": 1.4e-07, "input_dbu_cost_per_token": 2e-06, "litellm_provider": "databricks", + "token_count_framing": 97, "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, @@ -19337,8 +21636,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": false, - "token_count_framing": 97 + "supports_vision": false }, "databricks/system.ai.deepseek-v4-flash-0731": { "litellm_provider": "databricks", @@ -19623,6 +21921,7 @@ ], "supports_function_calling": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, @@ -19647,6 +21946,7 @@ ], "supports_function_calling": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, @@ -19678,6 +21978,7 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, @@ -19741,6 +22042,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true }, @@ -20313,6 +22615,7 @@ "input_cost_per_token": 2.99999e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", + "token_count_framing": 100, "max_input_tokens": 1000000, "max_output_tokens": 1048576, "max_tokens": 1048576, @@ -20334,8 +22637,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true, - "token_count_framing": 100 + "supports_vision": true }, "databricks/system.ai.kimi-k3": { "litellm_provider": "databricks", @@ -20463,6 +22765,30 @@ "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, + "databricks/databricks-openjev-qwen35-4b": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 0.0, + "litellm_provider": "databricks", + "metadata": { + "notes": "Pay-per-token Foundation Model API decision endpoint (OpenJev, Qwen 3.5 4B) queried through the System One API. Databricks published no DBU rate for it as of 2026-10-07, so a deployment's model_info prices set the billed cost." + }, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models" + }, + "databricks/ai_decide": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 0.0, + "litellm_provider": "databricks", + "metadata": { + "notes": "The ai_decide AI Function (Beta), called through POST /api/2.0/ai-functions/ai-decide. Its response carries no token usage, so LiteLLM records no spend for it." + }, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.databricks.com/api/ai-functions/v1/ai-decide" + }, "dataforseo/search": { "input_cost_per_query": 0.003, "litellm_provider": "dataforseo", @@ -21844,6 +24170,7 @@ "deepseek/deepseek-chat": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", @@ -21898,6 +24225,7 @@ }, "deepseek/deepseek-reasoner": { "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-07-24", "input_cost_per_token": 2.8e-07, "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", @@ -21953,14 +24281,15 @@ "supports_tool_choice": true }, "deepseek.v3-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 5.8e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 163840, - "max_output_tokens": 81920, - "max_tokens": 81920, + "max_input_tokens": 128000, + "max_output_tokens": 8000, + "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -21968,17 +24297,23 @@ }, "deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, + "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 164000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, + "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -22198,6 +24533,265 @@ "litellm_provider": "perplexity", "mode": "search" }, + "sail/moonshotai/Kimi-K3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 1.25e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token_balanced": 2e-06, + "output_cost_per_token_balanced": 1e-05, + "cache_read_input_token_cost_balanced": 2e-07, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_flex": 6.25e-06, + "cache_read_input_token_cost_flex": 1.5e-07, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/zai-org/GLM-5.3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 9.8e-07, + "output_cost_per_token": 3.08e-06, + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token_balanced": 5e-07, + "output_cost_per_token_balanced": 2.5e-06, + "cache_read_input_token_cost_balanced": 1.2e-07, + "input_cost_per_token_flex": 4e-07, + "output_cost_per_token_flex": 1.8e-06, + "cache_read_input_token_cost_flex": 8e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/zai-org/GLM-5.3-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.1e-07, + "output_cost_per_token": 3.5e-07, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_balanced": 8e-08, + "output_cost_per_token_balanced": 2.8e-07, + "cache_read_input_token_cost_balanced": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1.8e-07, + "cache_read_input_token_cost_flex": 1e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/deepseek-ai/DeepSeek-V4-Pro-0813": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 9.2e-07, + "output_cost_per_token": 2.77e-06, + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token_balanced": 7.4e-07, + "output_cost_per_token_balanced": 2.22e-06, + "cache_read_input_token_cost_balanced": 3e-08, + "input_cost_per_token_flex": 4.6e-07, + "output_cost_per_token_flex": 1.39e-06, + "cache_read_input_token_cost_flex": 2e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_balanced": 7e-08, + "output_cost_per_token_balanced": 1.4e-07, + "cache_read_input_token_cost_balanced": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 9e-08, + "cache_read_input_token_cost_flex": 1e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/deepseek-ai/DeepSeek-V4.1-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token_balanced": 7e-08, + "output_cost_per_token_balanced": 2.2e-07, + "cache_read_input_token_cost_balanced": 5e-09, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1.5e-07, + "cache_read_input_token_cost_flex": 4e-09, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/moonshotai/Kimi-K2.6": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_balanced": 4.5e-07, + "output_cost_per_token_balanced": 3e-06, + "cache_read_input_token_cost_balanced": 2e-07, + "input_cost_per_token_flex": 3.5e-07, + "output_cost_per_token_flex": 2e-06, + "cache_read_input_token_cost_flex": 1e-07, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/google/gemma-4-31B-it": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_balanced": 1.2e-07, + "output_cost_per_token_balanced": 6e-07, + "cache_read_input_token_cost_balanced": 8e-08, + "input_cost_per_token_flex": 6e-08, + "output_cost_per_token_flex": 3e-07, + "cache_read_input_token_cost_flex": 2e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/nvidia/Gemma-4-31B-IT-NVFP4": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token_balanced": 1.1e-07, + "output_cost_per_token_balanced": 3.2e-07, + "cache_read_input_token_cost_balanced": 6e-08, + "input_cost_per_token_flex": 7e-08, + "output_cost_per_token_flex": 2e-07, + "cache_read_input_token_cost_flex": 4e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/google/gemma-4-12B-it": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token_balanced": 1e-07, + "output_cost_per_token_balanced": 2e-06, + "cache_read_input_token_cost_balanced": 7e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 1e-06, + "cache_read_input_token_cost_flex": 2e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/openai/gpt-oss-120b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 3e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "source": "https://docs.sailresearch.com/models" + }, + "sail/Qwen/Qwen3.6-35B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token_flex": 5e-08, + "output_cost_per_token_flex": 4e-07, + "cache_read_input_token_cost_flex": 2e-08, + "litellm_provider": "sail", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://docs.sailresearch.com/models" + }, "searxng/search": { "litellm_provider": "searxng", "mode": "search", @@ -22231,7 +24825,7 @@ } }, "agentcore/search": { - "input_cost_per_query": 0.0, + "input_cost_per_query": 0.007, "litellm_provider": "agentcore", "mode": "search", "metadata": { @@ -22246,6 +24840,11 @@ "notes": "Grounding with Bing Search (G1 SKU): $14 per 1,000 transactions. Tokens for the Foundry model deployment that runs the grounded search are billed separately on that deployment." } }, + "deepseek/search": { + "input_cost_per_query": 0.00075, + "litellm_provider": "deepseek", + "mode": "search" + }, "tinyfish/search": { "input_cost_per_query": 0.0, "litellm_provider": "tinyfish", @@ -22390,13 +24989,16 @@ }, "eu.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2.625e-07, + "cache_read_input_token_cost_flex": 1.3125e-07, "input_cost_per_token": 1.05e-06, + "input_cost_per_token_flex": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 4.2e-06, + "output_cost_per_token_flex": 2.1e-06, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_pdf_input": true, @@ -22450,7 +25052,11 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -22547,7 +25153,11 @@ "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, - "deprecation_date": "2027-01-08" + "deprecation_date": "2027-01-08", + "token_count_model": { + "model": "anthropic.claude-opus-4-1-20250805-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -22585,7 +25195,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -22606,7 +25216,11 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, @@ -22618,6 +25232,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -22644,9 +25259,14 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "eu.meta.llama3-2-1b-instruct-v1:0": { + "deprecation_date": "2026-07-07", "input_cost_per_token": 1.3e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -22654,10 +25274,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.3e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "eu.meta.llama3-2-3b-instruct-v1:0": { + "deprecation_date": "2026-07-07", "input_cost_per_token": 1.9e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -22665,6 +25287,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.9e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, @@ -22672,10 +25295,11 @@ "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md", "supports_function_calling": true, "supports_tool_choice": false }, @@ -24984,9 +27608,10 @@ "output_cost_per_token": 5e-07 }, "fireworks-ai-up-to-4b": { - "input_cost_per_token": 2e-07, + "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "output_cost_per_token": 2e-07 + "output_cost_per_token": 1e-07, + "source": "https://docs.fireworks.ai/serverless/pricing" }, "fireworks_ai/WhereIsAI/UAE-Large-V1": { "input_cost_per_token": 1.6e-08, @@ -25013,7 +27638,7 @@ "fireworks_ai/accounts/fireworks/models/deepseek-r1": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 163840, "max_output_tokens": 20480, "max_tokens": 20480, "mode": "chat", @@ -25025,7 +27650,7 @@ "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 160000, + "max_input_tokens": 163840, "max_output_tokens": 160000, "max_tokens": 160000, "mode": "chat", @@ -25037,7 +27662,7 @@ "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { "input_cost_per_token": 5.5e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 163840, "max_output_tokens": 20480, "max_tokens": 20480, "mode": "chat", @@ -25049,7 +27674,7 @@ "fireworks_ai/accounts/fireworks/models/deepseek-v3": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", @@ -25182,7 +27807,7 @@ "fireworks_ai/accounts/fireworks/models/glm-4p5": { "input_cost_per_token": 5.5e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 96000, "max_tokens": 96000, "mode": "chat", @@ -25196,7 +27821,7 @@ "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { "input_cost_per_token": 2.2e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 96000, "max_tokens": 96000, "mode": "chat", @@ -25211,7 +27836,7 @@ "input_cost_per_token": 5.5e-07, "output_cost_per_token": 2.19e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 202800, "max_tokens": 202800, "mode": "chat", @@ -25225,7 +27850,7 @@ "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 202800, "max_tokens": 202800, "mode": "chat", @@ -25240,7 +27865,7 @@ "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", @@ -25275,6 +27900,7 @@ "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-08, "cache_read_input_token_cost_priority": 1.8e-08, + "deprecation_date": "2026-11-07", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "fireworks_ai", @@ -25284,7 +27910,7 @@ "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -25404,7 +28030,7 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { "input_cost_per_token": 3e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -25417,7 +28043,7 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -25430,7 +28056,7 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -25444,7 +28070,7 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -25457,7 +28083,7 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { "input_cost_per_token": 1e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -25470,7 +28096,7 @@ "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 16384, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -25508,7 +28134,7 @@ "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 204800, + "max_input_tokens": 196608, "max_output_tokens": 204800, "max_tokens": 204800, "mode": "chat", @@ -25609,7 +28235,7 @@ "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 6e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 202800, "max_tokens": 202800, "mode": "chat", @@ -25624,7 +28250,7 @@ "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "fireworks_ai", - "max_input_tokens": 202800, + "max_input_tokens": 202752, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", @@ -25675,6 +28301,7 @@ "fireworks_ai/gpt-oss-120b": { "cache_read_input_token_cost": 1.5e-08, "cache_read_input_token_cost_priority": 1.8e-08, + "deprecation_date": "2026-11-07", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 1.8e-07, "litellm_provider": "fireworks_ai", @@ -25684,7 +28311,7 @@ "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -25799,7 +28426,7 @@ "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "fireworks_ai", - "max_input_tokens": 204800, + "max_input_tokens": 196608, "max_output_tokens": 204800, "max_tokens": 204800, "mode": "chat", @@ -26152,6 +28779,7 @@ "ft:gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.875e-06, "cache_read_input_token_cost_batches": 9e-07, + "deprecation_date": "2027-01-14", "input_cost_per_token": 3.75e-06, "input_cost_per_token_batches": 2.225e-06, "litellm_provider": "openai", @@ -26173,6 +28801,7 @@ }, "ft:gpt-4o-2024-11-20": { "cache_creation_input_token_cost": 1.875e-06, + "deprecation_date": "2027-01-14", "input_cost_per_token": 3.75e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -26191,6 +28820,7 @@ "ft:gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, + "deprecation_date": "2027-01-14", "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "litellm_provider": "openai", @@ -26212,6 +28842,7 @@ "ft:gpt-4.1-2025-04-14": { "cache_read_input_token_cost": 7.5e-07, "cache_read_input_token_cost_batches": 5e-07, + "deprecation_date": "2027-01-14", "input_cost_per_token": 3e-06, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "openai", @@ -26232,6 +28863,7 @@ "ft:gpt-4.1-mini-2025-04-14": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_batches": 1e-07, + "deprecation_date": "2027-01-14", "input_cost_per_token": 8e-07, "input_cost_per_token_batches": 4e-07, "litellm_provider": "openai", @@ -26338,6 +28970,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, "input_cost_per_token_batches": 1.5e-07, @@ -26370,7 +29003,8 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26428,7 +29062,8 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26450,6 +29085,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3-pro-image-preview": { @@ -26479,7 +29115,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26501,17 +29138,20 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, + "cache_read_input_token_cost_priority": 9e-08, "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -26522,10 +29162,12 @@ "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.4e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26547,6 +29189,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-image-preview": { @@ -26567,7 +29210,8 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26589,16 +29233,20 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2027-06-28", "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, @@ -26609,10 +29257,12 @@ "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.7e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -26679,6 +29329,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -26740,6 +29391,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -26787,6 +29439,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -26799,6 +29452,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -26812,7 +29466,7 @@ "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, - "mode": "image_generation", + "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, @@ -26885,6 +29539,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-08, "input_cost_per_token_batches": 5e-08, @@ -26939,6 +29594,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -26985,6 +29641,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false }, @@ -27032,7 +29689,8 @@ "search_context_size_high": 0.035 }, "gemini_native_audio": true, - "input_cost_per_image_token": 3e-06 + "input_cost_per_image_token": 3e-06, + "input_cost_per_video_token": 3e-06 }, "gemini-live-2.5-flash-preview-native-audio-09-2025": { "input_cost_per_audio_token": 3e-06, @@ -27171,6 +29829,7 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_above_200k_tokens_priority": 4.5e-06, "input_cost_per_token_batches": 6.25e-07, @@ -27182,22 +29841,33 @@ "output_cost_per_token_priority": 1.8e-05 }, "gemini-3.1-pro-preview": { - "prompt_cache_min_tokens": 4096, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", + "output_cost_per_image": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, - "output_cost_per_image": 0.00012, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27215,33 +29885,18 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "cache_read_input_token_cost_flex": 2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "web_search_billing_unit": "per_query" }, "gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, @@ -27293,6 +29948,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -27349,20 +30005,32 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_flex": 5e-08, - "input_cost_per_token": 5e-07, + "cache_read_input_token_cost_priority": 9e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, + "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.4e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27380,6 +30048,7 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -27389,23 +30058,7 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 9e-07, - "input_cost_per_audio_token_priority": 1.8e-06, - "output_cost_per_token_priority": 5.4e-06, - "cache_read_input_token_cost_priority": 9e-08, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 5e-07, - "input_cost_per_token_batches": 2.5e-07, - "input_cost_per_token_flex": 2.5e-07, - "output_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_flex": 1.5e-06 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.5-flash": { "prompt_cache_min_tokens": 4096, @@ -27460,6 +30113,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -27508,6 +30162,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -27518,11 +30173,13 @@ "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, + "deprecation_date": "2026-11-19", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -27567,6 +30224,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -27577,22 +30235,26 @@ "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, + "deprecation_date": "2027-01-28", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3.8-flash": { - "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, @@ -27602,7 +30264,11 @@ "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096.0, "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27620,29 +30286,21 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 1.35e-06, - "output_cost_per_token_priority": 6.75e-06, - "cache_read_input_token_cost_priority": 1.35e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, @@ -27685,6 +30343,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_url_context": false, @@ -27694,6 +30353,7 @@ "supports_native_streaming": true }, "vertex_ai/gemini-3.8-live": { + "gemini_audio_only_live": true, "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, @@ -27706,7 +30366,8 @@ "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "output_cost_per_video_token": 1e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/vertex_ai/live", "/v1/realtime" @@ -27726,26 +30387,36 @@ "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, - "supports_web_search": true, - "gemini_audio_only_live": true + "supports_web_search": true }, "vertex_ai/gemini-3.1-pro-preview": { - "prompt_cache_min_tokens": 4096, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 2e-06, "input_cost_per_token_above_200k_tokens": 4e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", + "output_cost_per_image": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_200k_tokens": 1.8e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, - "output_cost_per_image": 0.00012, + "output_cost_per_token_flex": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -27763,33 +30434,18 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_url_context": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 3.6e-06, - "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, - "output_cost_per_token_priority": 2.16e-05, - "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, - "cache_read_input_token_cost_priority": 3.6e-07, - "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, - "cache_read_input_token_cost_flex": 2e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, @@ -27847,6 +30503,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -27931,7 +30588,7 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_reasoning_token": 5e-06, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "search_context_cost_per_query": { @@ -28152,8 +30809,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28174,6 +30831,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "supports_reasoning": false }, @@ -28195,8 +30853,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28218,6 +30876,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite-preview": { @@ -28279,6 +30938,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -28309,7 +30969,7 @@ "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", @@ -28346,7 +31006,7 @@ "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", @@ -28428,8 +31088,10 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, "input_cost_per_token_priority": 5.4e-07, @@ -28441,7 +31103,7 @@ }, "gemini/gemini-2.5-flash-image": { "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-10-02", + "deprecation_date": "2027-03-15", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, @@ -28461,8 +31123,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28507,6 +31169,7 @@ "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, + "output_cost_per_image_token_batches": 6e-05, "output_cost_per_token": 1.2e-05, "rpm": 1000, "tpm": 4000000, @@ -28516,8 +31179,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28528,7 +31191,7 @@ "image" ], "supports_function_calling": false, - "supports_prompt_caching": true, + "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, @@ -28538,8 +31201,9 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", - "supports_reasoning": false + "supports_reasoning": true }, "gemini/nano-banana-pro-preview": { "input_cost_per_image": 0.0011, @@ -28563,8 +31227,7 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28598,15 +31261,17 @@ "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 6e-05, + "output_cost_per_image_token_batches": 3e-05, "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, - "rpm": 1000, - "tpm": 4000000, + "rpm": 1000.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28617,17 +31282,14 @@ "image" ], "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, + "tpm": 4000000.0, "web_search_billing_unit": "per_query" }, "gemini/gemini-3.1-flash-lite-image": { @@ -28647,8 +31309,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", - "/v1/batch" + "/v1/images/generations", + "/v1/images/edits" ], "supported_modalities": [ "text", @@ -28659,8 +31321,9 @@ "image" ], "supports_function_calling": false, + "supports_pdf_input": true, "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, @@ -28668,21 +31331,20 @@ "tpm": 4000000 }, "gemini/deep-research-pro-preview-12-2025": { + "deprecation_date": "2026-10-23", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.134, - "output_cost_per_image_token": 0.00012, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", "output_cost_per_token": 1.2e-05, - "rpm": 1000, - "tpm": 4000000, "output_cost_per_token_batches": 6e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "rpm": 1000.0, + "search_context_cost_per_query": {"search_context_size_low":0.035,"search_context_size_medium":0.035,"search_context_size_high":0.035}, + "source": "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -28690,23 +31352,21 @@ ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": false, + "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - } + "tpm": 4000000.0 }, "gemini/gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, @@ -28757,8 +31417,10 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 1500, "period": "day", "shared_group": "gemini-2-flash"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 1.5e-07, + "input_cost_per_audio_token_priority": 5.4e-07, "input_cost_per_token_batches": 5e-08, "input_cost_per_token_flex": 5e-08, "input_cost_per_token_priority": 1.8e-07, @@ -28886,6 +31548,7 @@ "web_search_billing_unit": "per_query" }, "gemini/gemini-2.5-flash-preview-tts": { + "deprecation_date": "2026-11-17", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", @@ -28960,13 +31623,16 @@ "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, + "search_free_requests": {"count": 10000, "period": "day", "shared_group": "gemini-2.5-pro"}, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_batches": 6.25e-07, "input_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 5e-06, - "output_cost_per_token_flex": 5e-06 + "output_cost_per_token_flex": 5e-06, + "supports_url_context": true }, "gemini/gemini-2.5-computer-use-preview-10-2025": { + "deprecation_date": "2026-07-28", "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, "litellm_provider": "gemini", @@ -29055,9 +31721,11 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "input_cost_per_audio_token_batches": 2.5e-07, + "input_cost_per_audio_token_priority": 9e-07 }, "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, @@ -29102,6 +31770,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29115,6 +31784,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29171,6 +31841,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 5e-07, @@ -29234,6 +31905,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -29283,6 +31955,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29299,6 +31972,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29344,6 +32018,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29360,6 +32035,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29405,6 +32081,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29421,6 +32098,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29456,7 +32134,7 @@ "supports_video_input": true, "supports_vision": true, "tpm": 800000, - "deprecation_date": "2026-09-30" + "deprecation_date": "2026-10-22" }, "gemini/gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, @@ -29516,6 +32194,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, @@ -29579,6 +32258,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, @@ -29587,9 +32267,15 @@ "gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 9e-08, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_audio_token_priority": 1.8e-06, "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, @@ -29597,6 +32283,11 @@ "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.4e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -29614,6 +32305,7 @@ ], "supports_audio_output": false, "supports_function_calling": true, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -29624,23 +32316,7 @@ "supports_url_context": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 9e-07, - "input_cost_per_audio_token_priority": 1.8e-06, - "output_cost_per_token_priority": 5.4e-06, - "cache_read_input_token_cost_priority": 9e-08, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 5e-07, - "input_cost_per_token_batches": 2.5e-07, - "input_cost_per_token_flex": 2.5e-07, - "output_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_flex": 1.5e-06 + "web_search_billing_unit": "per_query" }, "gemini-omni-flash-preview": { "input_cost_per_audio_token": 1.5e-06, @@ -29726,6 +32402,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-07, @@ -29774,6 +32451,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29784,11 +32462,13 @@ "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, + "deprecation_date": "2026-11-19", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -29833,6 +32513,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -29843,22 +32524,26 @@ "input_cost_per_token_priority": 1.35e-06, "output_cost_per_token_priority": 6.75e-06, "cache_read_input_token_cost_priority": 1.35e-07, + "deprecation_date": "2027-01-28", "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, "gemini-3.8-flash": { - "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token": 7.5e-07, "input_cost_per_token_batches": 3.75e-07, "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, @@ -29868,6 +32553,10 @@ "output_cost_per_token": 3.75e-06, "output_cost_per_token_batches": 1.875e-06, "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", @@ -29883,32 +32572,24 @@ "supported_output_modalities": [ "text" ], - "supports_audio_output": false, "supports_audio_input": true, + "supports_audio_output": false, "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true, - "input_cost_per_token_priority": 1.35e-06, - "output_cost_per_token_priority": 6.75e-06, - "cache_read_input_token_cost_priority": 1.35e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.014, - "search_context_size_medium": 0.014, - "search_context_size_high": 0.014 - }, - "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "web_search_billing_unit": "per_query" }, "gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, @@ -29951,6 +32632,7 @@ "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": false, "supports_url_context": false, @@ -29961,6 +32643,7 @@ }, "gemini/gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-07, + "deprecation_date": "2026-11-17", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, @@ -30221,6 +32904,7 @@ "output_cost_per_image": 0.08 }, "gemini/veo-3.1-fast-generate-preview": { + "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, @@ -30237,6 +32921,7 @@ ] }, "gemini/veo-3.1-generate-preview": { + "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, @@ -30252,6 +32937,7 @@ ] }, "gemini/veo-3.1-lite-generate-preview": { + "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, "max_tokens": 1024, @@ -30297,83 +32983,270 @@ "video" ] }, - "github_copilot/claude-haiku-4.5": { + "github_copilot/claude-fable-5": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ - "/v1/chat/completions" + "/v1/chat/completions", + "/v1/messages" ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true - }, - "github_copilot/claude-opus-4.5": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_output_config": true - }, - "github_copilot/claude-opus-4.6-fast": { "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "github_copilot/claude-fable-5.1": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-05, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "github_copilot/claude-haiku-4.5": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token": 5e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, "supports_vision": true }, - "github_copilot/claude-opus-41": { - "litellm_provider": "github_copilot", - "max_input_tokens": 80000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_vision": true - }, - "github_copilot/claude-sonnet-4": { + "github_copilot/claude-haiku-5.5": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_100k_tokens": 5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ - "/v1/chat/completions" + "/v1/chat/completions", + "/v1/messages" ], + "supports_adaptive_thinking": true, "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": false + }, + "github_copilot/claude-opus-4.8": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 5e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_vision": true }, - "github_copilot/claude-sonnet-4.5": { + "github_copilot/claude-opus-4.8-fast": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_read_input_token_cost": 1e-06, + "input_cost_per_token": 1e-05, "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 16000, - "max_tokens": 16000, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/claude-opus-5": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 5e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/claude-opus-5.5": { + "cache_creation_input_token_cost": 5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "github_copilot/claude-sonnet-5": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/claude-sonnet-5.5": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "thinking_always_on": true + }, + "github_copilot/gemini-3.7-flash": { + "cache_read_input_token_cost": 7.5e-08, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 7.5e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_vision": true + }, + "github_copilot/gemini-3.8-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_sampling_params": false, "supports_vision": true }, "github_copilot/gpt-3.5-turbo": { @@ -30418,22 +33291,26 @@ "supports_parallel_function_calling": true }, "github_copilot/gpt-4.1": { + "deprecation_date": "2026-06-01", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-4.1-2025-04-14": { + "deprecation_date": "2026-06-01", "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/model-deprecation-history.yml", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -30500,82 +33377,304 @@ "supports_function_calling": true, "supports_parallel_function_calling": true }, - "github_copilot/gpt-5": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true - }, "github_copilot/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 2.5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true - }, - "github_copilot/gpt-5.1": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true - }, - "github_copilot/gpt-5.1-codex-max": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "responses", - "supported_endpoints": [ - "/v1/responses" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true - }, - "github_copilot/gpt-5.2": { - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], + "output_cost_per_token": 2e-06, + "source": "https://github.blog/changelog/2026-10-19-github-copilot-models-deprecated-on-october-19-2026", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_vision": true }, "github_copilot/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 1.4e-05, + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.4": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.4-mini": { + "cache_read_input_token_cost": 7.5e-08, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 7.5e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 4.5e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.5": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_200k_tokens": 5e-07, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_200k_tokens": 4e-08, + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_200k_tokens": 4e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_200k_tokens": 1.8e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.6-sol": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.6-terra": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "deprecation_date": "2026-11-16", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-6-astra": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 917504, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/mai-code-1.1-flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.2e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/responses" ], @@ -30584,38 +33683,6 @@ "supports_response_schema": true, "supports_vision": true }, - "github_copilot/mai-code-1-flash": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 4.5e-06, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true - }, - "github_copilot/mai-code-1-flash-internal": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "github_copilot", - "max_input_tokens": 128000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 4.5e-06, - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true - }, "github_copilot/text-embedding-3-small": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, @@ -30634,6 +33701,90 @@ "max_tokens": 8191, "mode": "embedding" }, + "chatgpt/gpt-6-sol": { + "litellm_provider": "chatgpt", + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6-luna": { + "litellm_provider": "chatgpt", + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6-astra": { + "litellm_provider": "chatgpt", + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "chatgpt/gpt-6.1-sol": { + "litellm_provider": "chatgpt", + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, "chatgpt/gpt-5.5": { "litellm_provider": "chatgpt", "source": "https://platform.openai.com/docs/models/gpt-5.5", @@ -31099,24 +34250,28 @@ "output_cost_per_token": 1.2e-06 }, "baseten/MiniMaxAI/MiniMax-M2.5": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 1.2e-06 }, "baseten/nvidia/Nemotron-120B-A12B": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 7.5e-07 }, "baseten/zai-org/GLM-5": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 9.5e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 3.15e-06 }, "baseten/zai-org/GLM-4.7": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "baseten", @@ -31134,24 +34289,28 @@ "supports_vision": false }, "baseten/zai-org/GLM-4.6": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 2.2e-06 }, "baseten/moonshotai/Kimi-K2.5": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 3e-06 }, "baseten/moonshotai/Kimi-K2-Thinking": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 2.5e-06 }, "baseten/moonshotai/Kimi-K2-Instruct-0905": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 6e-07, "litellm_provider": "baseten", "mode": "chat", @@ -31175,12 +34334,14 @@ "supports_vision": false }, "baseten/deepseek-ai/DeepSeek-V3.1": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 5e-07, "litellm_provider": "baseten", "mode": "chat", "output_cost_per_token": 1.5e-06 }, "baseten/deepseek-ai/DeepSeek-V3-0324": { + "deprecation_date": "2026-10-16", "input_cost_per_token": 7.7e-07, "litellm_provider": "baseten", "mode": "chat", @@ -31206,14 +34367,21 @@ "output_cost_per_token": 2e-06 }, "google.gemma-3-12b-it": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 9e-08, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.9e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_flex": 1.5e-07, + "output_cost_per_token_priority": 5.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -31221,14 +34389,21 @@ "supports_vision": true }, "google.gemma-3-27b-it": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.3e-07, + "input_cost_per_token_batches": 1.2e-07, + "input_cost_per_token_flex": 1.2e-07, + "input_cost_per_token_priority": 4e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 3.8e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.9e-07, + "output_cost_per_token_flex": 1.9e-07, + "output_cost_per_token_priority": 6.7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -31236,14 +34411,21 @@ "supports_vision": true }, "google.gemma-3-4b-it": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4e-08, + "input_cost_per_token_batches": 2e-08, + "input_cost_per_token_flex": 2e-08, + "input_cost_per_token_priority": 7e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-08, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 4e-08, + "output_cost_per_token_flex": 4e-08, + "output_cost_per_token_priority": 1.4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -31264,6 +34446,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -31290,7 +34473,11 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.5e-06, "output_cost_per_token_batches": 7.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -31302,7 +34489,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -31323,7 +34510,11 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.25e-06, @@ -31351,17 +34542,27 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-07, - "output_cost_per_token_batches": 2.5e-06 + "output_cost_per_token_batches": 2.5e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "global.amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_priority": 1.3125e-07, "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -31584,6 +34785,7 @@ "gpt-4.1-2025-04-14": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_priority": 8.75e-07, + "deprecation_date": "2027-01-14", "input_cost_per_token": 2e-06, "input_cost_per_token_priority": 3.5e-06, "input_cost_per_token_batches": 1e-06, @@ -31670,6 +34872,7 @@ "gpt-4.1-mini-2025-04-14": { "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_priority": 1.75e-07, + "deprecation_date": "2027-01-14", "input_cost_per_token": 4e-07, "input_cost_per_token_priority": 7e-07, "input_cost_per_token_batches": 2e-07, @@ -31835,6 +35038,7 @@ "gpt-4o-2024-08-06": { "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, + "deprecation_date": "2027-01-14", "input_cost_per_token": 2.5e-06, "input_cost_per_token_priority": 4.25e-06, "input_cost_per_token_batches": 1.25e-06, @@ -31859,6 +35063,7 @@ "gpt-4o-2024-11-20": { "cache_read_input_token_cost": 1.25e-06, "cache_read_input_token_cost_priority": 2.125e-06, + "deprecation_date": "2027-01-14", "input_cost_per_token": 2.5e-06, "input_cost_per_token_priority": 4.25e-06, "input_cost_per_token_batches": 1.25e-06, @@ -32064,6 +35269,44 @@ "supports_tool_choice": true, "supports_vision": false }, + "gpt-audio-mini-2025-10-06": { + "deprecation_date": "2026-07-23", + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 6e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://developers.openai.com/api/docs/models/gpt-audio-mini", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/realtime", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "gpt-audio-mini-2025-12-15": { "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, @@ -32134,6 +35377,7 @@ "gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_priority": 1.25e-07, + "deprecation_date": "2027-01-14", "input_cost_per_token": 1.5e-07, "input_cost_per_token_priority": 2.5e-07, "input_cost_per_token_batches": 7.5e-08, @@ -32224,6 +35468,34 @@ "supports_vision": true, "supports_web_search": true }, + "gpt-4o-mini-search-preview-2025-03-11": { + "deprecation_date": "2026-07-23", + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.025, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.025 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-search-preview" + }, "gpt-4o-mini-transcribe": { "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, @@ -32258,6 +35530,26 @@ "audio" ] }, + "gpt-4o-mini-tts-2025-03-20": { + "deprecation_date": "2027-01-06", + "input_cost_per_token": 6e-07, + "litellm_provider": "openai", + "mode": "audio_speech", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_second": 0.00025, + "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "audio" + ] + }, "gpt-4o-search-preview": { "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, @@ -32284,6 +35576,34 @@ "supports_vision": true, "supports_web_search": true }, + "gpt-4o-search-preview-2025-03-11": { + "deprecation_date": "2026-07-23", + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.025, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.025 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "source": "https://developers.openai.com/api/docs/models/gpt-4o-search-preview" + }, "gpt-4o-transcribe": { "input_cost_per_audio_token": 2.5e-06, "input_cost_per_token": 2.5e-06, @@ -32379,10 +35699,13 @@ "gpt-image-2.5-flare": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_batches": 6.25e-07, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, + "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ "/v1/images/generations", @@ -32411,10 +35734,13 @@ "gpt-image-2.5-sunburst": { "cache_read_input_image_token_cost": 2e-06, "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_batches": 6.25e-07, "input_cost_per_token": 5e-06, "litellm_provider": "openai", "mode": "image_generation", "input_cost_per_image_token": 8e-06, + "input_cost_per_image_token_batches": 4e-06, + "input_cost_per_token_batches": 2.5e-06, "output_cost_per_image_token": 3e-05, "supported_endpoints": [ "/v1/images/generations", @@ -32933,7 +36259,8 @@ "output_cost_per_token_flex": 5e-06, "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": false + "supports_minimal_reasoning_effort": false, + "deprecation_date": "2027-04-01" }, "gpt-5.1-codex-mini": { "cache_read_input_token_cost": 2.5e-08, @@ -33155,6 +36482,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -33272,6 +36600,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -33383,16 +36712,22 @@ "cache_read_input_token_cost_above_272k_tokens_batches": 1e-06, "cache_creation_input_token_cost_batches": 6.25e-06, "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015, + "cache_creation_input_token_cost_ultrafast": 7.5e-05, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05, "cache_read_input_token_cost_flex": 5e-07, "cache_read_input_token_cost_priority": 2e-06, + "cache_read_input_token_cost_ultrafast": 6e-06, "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, "input_cost_per_token_above_272k_tokens_flex": 1e-05, "input_cost_per_token_above_272k_tokens_priority": 4e-05, "input_cost_per_token_batches": 5e-06, "input_cost_per_token_above_272k_tokens_batches": 1e-05, + "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012, "input_cost_per_token_flex": 5e-06, "input_cost_per_token_priority": 2e-05, + "input_cost_per_token_ultrafast": 6e-05, "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -33404,8 +36739,10 @@ "output_cost_per_token_above_272k_tokens_priority": 0.00015, "output_cost_per_token_batches": 2.5e-05, "output_cost_per_token_above_272k_tokens_batches": 3.75e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045, "output_cost_per_token_flex": 2.5e-05, "output_cost_per_token_priority": 0.0001, + "output_cost_per_token_ultrafast": 0.0003, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { @@ -33440,6 +36777,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true @@ -33516,19 +36854,24 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, "gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_decisions": 1e-07, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens_decisions": 2e-07, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-07, "cache_creation_input_token_cost_flex": 6.25e-08, "cache_creation_input_token_cost_priority": 2.5e-07, "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_decisions": 1e-07, "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "cache_read_input_token_cost_above_272k_tokens_decisions": 2e-07, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 4e-08, "cache_read_input_token_cost_batches": 5e-09, @@ -33538,7 +36881,9 @@ "cache_read_input_token_cost_flex": 5e-09, "cache_read_input_token_cost_priority": 2e-08, "input_cost_per_token": 1e-07, + "input_cost_per_token_decisions": 1e-07, "input_cost_per_token_above_272k_tokens": 2e-07, + "input_cost_per_token_above_272k_tokens_decisions": 2e-07, "input_cost_per_token_above_272k_tokens_flex": 1e-07, "input_cost_per_token_above_272k_tokens_priority": 4e-07, "input_cost_per_token_batches": 5e-08, @@ -33551,7 +36896,9 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, + "output_cost_per_token_decisions": 0.0, "output_cost_per_token_above_272k_tokens": 7.5e-07, + "output_cost_per_token_above_272k_tokens_decisions": 0.0, "output_cost_per_token_above_272k_tokens_flex": 3.75e-07, "output_cost_per_token_above_272k_tokens_priority": 1.5e-06, "output_cost_per_token_batches": 2.5e-07, @@ -33593,6 +36940,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true @@ -33666,6 +37014,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true @@ -33741,6 +37090,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true @@ -33815,6 +37165,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true @@ -33889,6 +37240,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true @@ -34174,6 +37526,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -34236,6 +37589,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -34290,6 +37644,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -34341,6 +37696,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -34395,6 +37751,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", @@ -34452,6 +37809,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", @@ -34505,6 +37863,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -34557,6 +37916,7 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": false, @@ -34612,6 +37972,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -34666,6 +38027,7 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, + "supports_tool_search": true, "supports_vision": true, "supports_web_search": true, "supports_none_reasoning_effort": true, @@ -34723,7 +38085,8 @@ "default_reasoning_effort": "none", "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": false + "supports_minimal_reasoning_effort": false, + "deprecation_date": "2027-04-01" }, "gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-08, @@ -36404,6 +39767,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -36430,7 +39794,11 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -36458,7 +39826,11 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "crusoe/deepseek-ai/DeepSeek-R1-0528": { "input_cost_per_token": 3e-06, @@ -36583,6 +39955,736 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "inferenceapis/deepseek-ai/DeepSeek-V3": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-ai/DeepSeek-V4-Flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-ai/DeepSeek-V4-Pro": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1.72e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1.72e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-chat": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-reasoner": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-v3": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-v4-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 1.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3.8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-v4-pro": { + "cache_read_input_token_cost": 1.7e-07, + "input_cost_per_token": 1.72e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/glm-5.3": { + "cache_read_input_token_cost": 3.4e-07, + "input_cost_per_token": 1.82e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 5.72e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/glm-5.3-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/gpt-oss-120b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 8.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.42e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/llama-3.1-8b-instant": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/llama-3.3-70b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/llama-3.3-70b-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/llama-3.3-70b-versatile": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/minimax-m3": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 3.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 1.56e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/MiniMaxAI/MiniMax-M3": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 3.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 1.56e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/moonshotai/Kimi-K2.7-Code": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 8.9e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4.42e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/openai/gpt-oss-120b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/openai/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "inferenceapis", + "max_input_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/Qwen/Qwen3-VL-235B-A22B-Instruct": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "inferenceapis/Qwen/Qwen3.8-Flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/qwen3-vl": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "inferenceapis/qwen3-vl-235b": { + "input_cost_per_token": 2.6e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "inferenceapis/qwen3.8-flash": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/zai-org/GLM-5.3": { + "cache_read_input_token_cost": 3.4e-07, + "input_cost_per_token": 1.82e-06, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 5.72e-06, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "inferenceapis/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "inferenceapis", + "max_input_tokens": 1048575, + "max_tokens": 1048575, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "source": "https://inferenceapis.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "text-completion-inception/mercury-edit-2": { "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 2.5e-07, @@ -37035,51 +41137,64 @@ "source": "https://aws.amazon.com/bedrock/pricing/" }, "meta.llama3-1-405b-instruct-v1:0": { - "input_cost_per_token": 5.32e-06, + "deprecation_date": "2026-07-07", + "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.6e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-1-70b-instruct-v1:0": { - "input_cost_per_token": 9.9e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 9.9e-07, - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-1-8b-instruct-v1:0": { - "input_cost_per_token": 2.2e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2.2e-07, - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-2-11b-instruct-v1:0": { - "input_cost_per_token": 3.5e-07, + "deprecation_date": "2027-03-30", + "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.5e-07, + "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-1-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "output_cost_per_token_batches": 1.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-2-11b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "input_cost_per_token": 1.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.6e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true }, "meta.llama3-2-1b-instruct-v1:0": { + "deprecation_date": "2026-07-07", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -37087,10 +41202,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-2-3b-instruct-v1:0": { + "deprecation_date": "2026-07-07", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -37098,60 +41215,73 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-2-90b-instruct-v1:0": { - "input_cost_per_token": 2e-06, + "deprecation_date": "2026-07-07", + "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 7.2e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true }, "meta.llama3-3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "meta.llama3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.65e-06, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.5e-06 + "output_cost_per_token": 3.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" }, "meta.llama3-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-07 + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" }, "meta.llama4-maverick-17b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9.7e-07, "output_cost_per_token_batches": 4.85e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", "supported_modalities": [ "text", "image" @@ -37164,15 +41294,17 @@ "supports_tool_choice": false }, "meta.llama4-scout-17b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.7e-07, "input_cost_per_token_batches": 8.5e-08, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 10000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_batches": 3.3e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", "supported_modalities": [ "text", "image" @@ -37405,6 +41537,49 @@ ], "supports_audio_input": true }, + "meta/muse-wonder-1.0": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "meta", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://dev.meta.ai/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "meta_llama/Llama-3.3-70B-Instruct": { "litellm_provider": "meta_llama", "max_input_tokens": 128000, @@ -37472,14 +41647,21 @@ "supports_tool_choice": true }, "minimax.minimax-m2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -37488,33 +41670,46 @@ "supports_vision": false }, "minimax.minimax-m2.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 196000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "minimax.minimax-m2.5": { "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.25e-07, "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 196000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -37644,31 +41839,96 @@ "max_input_tokens": 1000000, "max_output_tokens": 128000 }, + "minimax/MiniMax-H3": { + "litellm_provider": "minimax", + "mode": "video_generation", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", + "output_cost_per_second": 0.08, + "output_cost_per_second_768p": 0.08, + "output_cost_per_second_2k": 0.13, + "input_cost_per_image": 0.04, + "provider_specific_entry": { + "minimax_free_input_images": 5 + }, + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "metadata": { + "comment": "V2 async task API. Pay-as-you-go list price $0.08/s at 768P and $0.13/s at 2K, plus $0.04 per input image beyond the first 5. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." + } + }, + "minimax/MiniMax-H3-Max": { + "litellm_provider": "minimax", + "mode": "video_generation", + "source": "https://platform.minimax.io/docs/guides/pricing-paygo", + "output_cost_per_second": 0.08, + "output_cost_per_second_480p": 0.05, + "output_cost_per_second_768p": 0.08, + "input_cost_per_image": 0.074, + "provider_specific_entry": { + "minimax_free_input_images": 2 + }, + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "video" + ], + "supported_endpoints": [ + "/v1/videos" + ], + "metadata": { + "comment": "V2 async task API, fast tier. Pay-as-you-go list price $0.05/s at 480P and $0.08/s at 768P; no 2K. Plus $0.074 per input image beyond the first 2. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call." + } + }, "mistral.devstral-2-123b": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_flex": 2e-07, + "input_cost_per_token_priority": 7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "output_cost_per_token_flex": 1e-06, + "output_cost_per_token_priority": 3.5e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "mistral.magistral-small-2509": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 40000, "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.63e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, @@ -37678,13 +41938,19 @@ }, "mistral.ministral-3-14b-instruct": { "input_cost_per_token": 2e-07, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "input_cost_per_token_priority": 3.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1e-07, + "output_cost_per_token_flex": 1e-07, + "output_cost_per_token_priority": 3.5e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -37694,13 +41960,19 @@ }, "mistral.ministral-3-3b-instruct": { "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 5e-08, + "output_cost_per_token_flex": 5e-08, + "output_cost_per_token_priority": 1.7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -37710,13 +41982,19 @@ }, "mistral.ministral-3-8b-instruct": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 7e-08, + "output_cost_per_token_flex": 7e-08, + "output_cost_per_token_priority": 2.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -37725,47 +42003,55 @@ "supports_vision": true }, "mistral.mistral-7b-instruct-v0:2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-7b-instruct.md", "supports_tool_choice": true }, "mistral.mistral-large-2402-v1:0": { "input_cost_per_token": 4e-06, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", "supports_function_calling": true }, "mistral.mistral-large-2407-v1:0": { - "input_cost_per_token": 3e-06, + "input_cost_per_token": 2e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "mode": "chat", - "output_cost_per_token": 9e-06, + "output_cost_per_token": 6e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": true }, "mistral.mistral-large-3-675b-instruct": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.63e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -37778,47 +42064,62 @@ "input_cost_per_token_batches": 5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-small.md", "supports_function_calling": true }, "mistral.mixtral-8x7b-instruct-v0:1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mixtral-8x7b-instruct.md", "supports_tool_choice": true }, "mistral.voxtral-mini-3b-2507": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4e-08, + "input_cost_per_token_batches": 2e-08, + "input_cost_per_token_flex": 2e-08, + "input_cost_per_token_priority": 7e-08, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, + "max_input_tokens": 32768, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-08, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 2e-08, + "output_cost_per_token_flex": 2e-08, + "output_cost_per_token_priority": 7e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true }, "mistral.voxtral-small-24b-2507": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_flex": 5e-08, + "input_cost_per_token_priority": 1.7e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, + "max_input_tokens": 32768, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_flex": 1.5e-07, + "output_cost_per_token_priority": 5.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true @@ -38038,7 +42339,6 @@ }, "mistral/voxtral-small-2507": { "cache_read_input_token_cost": 1e-08, - "input_cost_per_second": 6.666666666666667e-05, "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 32768, @@ -38054,7 +42354,6 @@ }, "mistral/voxtral-small-latest": { "cache_read_input_token_cost": 1e-08, - "input_cost_per_second": 6.666666666666667e-05, "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 32768, @@ -38070,6 +42369,7 @@ }, "mistral/zai-glm-5-2": { "cache_read_input_token_cost": 1.4e-07, + "deprecation_date": "2026-10-31", "input_cost_per_token": 1.4e-06, "litellm_provider": "mistral", "max_input_tokens": 1048576, @@ -38200,6 +42500,7 @@ "source": "https://mistral.ai/pricing#api-pricing" }, "mistral/mistral-ocr-4-0": { + "deprecation_date": "2026-09-30", "litellm_provider": "mistral", "ocr_cost_per_page": 0.004, "ocr_cost_per_page_batches": 0.002, @@ -38295,6 +42596,48 @@ "max_tokens": 8192, "mode": "embedding" }, + "mistral/mistral-large-4": { + "cache_read_input_token_cost": 6.8e-08, + "input_cost_per_token": 6.8e-07, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.09e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/mistral-large-4", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-large-4-0": { + "cache_read_input_token_cost": 6.8e-08, + "input_cost_per_token": 6.8e-07, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 2.09e-06, + "reasoning_effort_levels": [ + "none", + "high" + ], + "source": "https://docs.mistral.ai/models/mistral-large-4", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "mistral/mistral-large-latest": { "cache_read_input_token_cost": 5e-08, "input_cost_per_token": 5e-07, @@ -38585,14 +42928,19 @@ "supports_vision": true }, "moonshot.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.38e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, @@ -38603,17 +42951,23 @@ }, "moonshotai.kimi-k2.5": { "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 3e-06, + "output_cost_per_token_batches": 1.5e-06, + "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.25e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true }, @@ -39346,6 +43700,7 @@ "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { "input_cost_per_token": 1.32e-06, "litellm_provider": "nebius", + "max_input_tokens": 979000, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813", @@ -39355,12 +43710,14 @@ "nebius/deepseek-ai/DeepSeek-V4.1-Flash": { "input_cost_per_token": 3e-07, "litellm_provider": "nebius", - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "max_tokens": 1048576, + "max_input_tokens": 1048000, + "max_output_tokens": 384000, + "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://tokenfactory.nebius.com/endpoints?modals=endpoint-details&model-id=deepseek-ai/DeepSeek-V4.1-Flash", + "supports_function_calling": true, + "supports_reasoning": true, "supports_vision": true }, "nebius/MiniMaxAI/MiniMax-M2.5": { @@ -39605,6 +43962,16 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.5-397B-A17B" }, + "nebius/Qwen/Qwen3.8-27B": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "nebius", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.8-27B", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/zai-org/GLM-5.1": { "max_tokens": 202752, "max_input_tokens": 202752, @@ -39632,8 +43999,8 @@ "nebius/zai-org/GLM-5.3": { "input_cost_per_token": 1.4e-06, "litellm_provider": "nebius", - "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_input_tokens": 1024000, + "max_tokens": 1024000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", @@ -39650,7 +44017,8 @@ "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, - "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash" + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash", + "supports_vision": true }, "nebius/BAAI/bge-en-icl": { "max_tokens": 32768, @@ -39689,14 +44057,21 @@ "source": "https://tokenfactory.nebius.com/models/catalog/embedding/Qwen%2FQwen3-Embedding-8B" }, "nvidia.nemotron-nano-12b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2e-07, + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "input_cost_per_token_priority": 3.5e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -39704,14 +44079,21 @@ "supports_vision": true }, "nvidia.nemotron-nano-9b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.3e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.2e-07, + "output_cost_per_token_flex": 1.2e-07, + "output_cost_per_token_priority": 4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_response_schema": true, @@ -39720,16 +44102,22 @@ }, "nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.4e-07, + "output_cost_per_token_batches": 1.2e-07, + "output_cost_per_token_flex": 1.2e-07, + "output_cost_per_token_priority": 4.2e-07, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_native_structured_output": true, "supports_response_schema": true, @@ -39737,13 +44125,19 @@ }, "nvidia.nemotron-super-3-120b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.5e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3.25e-07, + "output_cost_per_token_flex": 3.25e-07, + "output_cost_per_token_priority": 1.1375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_reasoning": true, @@ -39913,6 +44307,39 @@ "supports_web_search": true }, "o3-deep-research": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "source": "https://developers.openai.com/api/docs/models/o3-deep-research", + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_pdf_input": true, + "deprecation_date": "2026-07-23" + }, + "o3-deep-research-2025-06-26": { + "deprecation_date": "2026-07-23", "cache_read_input_token_cost": 2.5e-06, "input_cost_per_token": 1e-05, "litellm_provider": "openai", @@ -40142,6 +44569,39 @@ "supports_web_search": true }, "o4-mini-deep-research": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-06, + "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", + "supported_endpoints": [ + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": false, + "supports_vision": true, + "supports_pdf_input": true, + "deprecation_date": "2026-07-23" + }, + "o4-mini-deep-research-2025-06-26": { + "deprecation_date": "2026-07-23", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "openai", @@ -40616,6 +45076,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, + "reasoning_effort_levels": [], "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, "supports_response_schema": false @@ -40632,6 +45093,72 @@ "supports_function_calling": true, "supports_response_schema": false }, + "oci/xai.grok-4.20-0309-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true + }, + "oci/xai.grok-4.20-0309-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_reasoning": true + }, + "oci/xai.grok-4.20-non-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true + }, + "oci/xai.grok-4.20-reasoning": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "oci", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "output_cost_per_token_above_200k_tokens": 5e-06, + "reasoning_effort_levels": [], + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_reasoning": true + }, "oci/xai.grok-code-fast-1": { "input_cost_per_token": 5e-06, "litellm_provider": "oci", @@ -40689,6 +45216,32 @@ "supports_response_schema": true, "supports_vision": true }, + "oci/openai.gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true + }, + "oci/openai.gpt-oss-20b": { + "input_cost_per_token": 7e-08, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_reasoning": true + }, "oci/cohere.embed-english-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "oci", @@ -41070,28 +45623,50 @@ "output_cost_per_token": 0.0 }, "openai.gpt-oss-120b-1:0": { + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "openai.gpt-oss-20b-1:0": { + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3.5e-08, + "input_cost_per_token_flex": 3.5e-08, + "input_cost_per_token_priority": 1.225e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_flex": 1.5e-07, + "output_cost_per_token_priority": 5.25e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -41099,14 +45674,21 @@ }, "openai.gpt-oss-safeguard-120b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, @@ -41114,2303 +45696,26 @@ }, "openai.gpt-oss-safeguard-20b": { "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.2e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1e-07, + "output_cost_per_token_flex": 1e-07, + "output_cost_per_token_priority": 3.5e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_response_schema": true, "supports_system_messages": true, "supports_vision": false }, - "openrouter/anthropic/claude-3-haiku": { - "cache_creation_input_token_cost": 3e-07, - "cache_creation_input_token_cost_above_1hr": 5e-07, - "cache_read_input_token_cost": 3e-08, - "input_cost_per_image": 0.0004, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_web_search": true - }, - "openrouter/anthropic/claude-3.5-sonnet": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/anthropic/claude-3.7-sonnet": { - "input_cost_per_image": 0.0048, - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/anthropic/claude-opus-4.1": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 3e-05, - "cache_read_input_token_cost": 1.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": false, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-4": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost": 3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": false, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-4.6": { - "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost": 3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_max_reasoning_effort": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.5": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_output_config": true, - "prompt_cache_min_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.6": { - "supports_adaptive_thinking": true, - "supports_legacy_thinking": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_max_reasoning_effort": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 4096, - "supports_response_schema": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-4.5": { - "input_cost_per_image": 0.0048, - "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 6e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 1024, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-haiku-4.5": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_1hr": 2e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "prompt_cache_min_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.7": { - "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_max_reasoning_effort": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_xhigh_reasoning_effort": true, - "prompt_cache_min_tokens": 2048, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-5": { - "prompt_cache_min_tokens": 512, - "supports_adaptive_thinking": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": false, - "supports_audio_input": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_max_reasoning_effort": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true - }, - "openrouter/anthropic/claude-opus-5.5": { - "cache_creation_input_token_cost": 5e-06, - "cache_creation_input_token_cost_above_1hr": 8e-06, - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/bytedance/ui-tars-1.5-7b": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-chat": { - "input_cost_per_token": 3.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 8.9e-07, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-chat-v3-0324": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 147456, - "max_tokens": 147456, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-chat-v3.1": { - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_cache_hit": 2e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 9.5e-07, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "cache_read_input_token_cost": 1.3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v3.2": { - "cache_read_input_token_cost": 1.345e-07, - "deprecation_date": "2026-09-28", - "input_cost_per_token": 2.69e-07, - "input_cost_per_token_cache_hit": 1.345e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 4e-07, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v3.2-exp": { - "cache_read_input_token_cost": 2e-08, - "deprecation_date": "2026-09-28", - "input_cost_per_token": 2.7e-07, - "input_cost_per_token_cache_hit": 2e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 4.1e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": true, - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-r1": { - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 7e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 64000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": true, - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-r1-0528": { - "cache_read_input_token_cost": 3.5e-07, - "input_cost_per_token": 5e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 2.15e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_assistant_prefill": true, - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v4-pro": { - "input_cost_per_token": 8.44944e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 1.689888e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "cache_read_input_token_cost": 7.0412e-08, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v4.1-flash": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 6e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 393216, - "max_tokens": 393216, - "mode": "chat", - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9}, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v4-pro-0813": { - "input_cost_per_token": 4.62e-07, - "input_cost_per_token_cache_hit": 1.9272e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "output_cost_per_token": 1.386e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "cache_read_input_token_cost": 1.54e-08, - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":0.00000132,"output_cost_per_token":0.00000396,"cache_read_input_token_cost":4.4e-8}, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/fireworks/ember-1": { - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": false, - "supports_pdf_input": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/google/gemini-2.5-flash": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 1e-07, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_image_size": false, - "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-10-20", - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_pdf_input": true, - "supports_reasoning": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-2.5-pro": { - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 1.25e-07, - "input_cost_per_audio_token": 1.25e-06, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "deprecation_date": "2026-10-20", - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_pdf_input": true, - "supports_reasoning": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3-pro-preview": { - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "input_cost_per_token_batches": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "output_cost_per_token_batches": 6e-06, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/google/gemini-3-flash-preview": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 1e-07, - "cache_read_input_token_cost": 5e-08, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 3e-06, - "output_cost_per_token": 3e-06, - "rpm": 2000, - "source": "https://openrouter.ai/api/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000, - "supports_video_input": true - }, - "openrouter/google/gemini-3.1-flash-lite-preview": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 5e-08, - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 1.5e-06, - "output_cost_per_token": 1.5e-06, - "rpm": 2000, - "source": "https://openrouter.ai/api/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000 - }, - "openrouter/google/gemini-3.1-flash-lite": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 5e-08, - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_reasoning_token": 1.5e-06, - "output_cost_per_token": 1.5e-06, - "rpm": 2000, - "source": "https://openrouter.ai/api/v1/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 800000 - }, - "openrouter/google/gemini-3.1-pro-preview": { - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, - "cache_read_input_audio_token_cost": 2e-07, - "input_cost_per_audio_token": 2e-06, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/gryphe/mythomax-l2-13b": { - "input_cost_per_token": 8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 3686, - "max_tokens": 3686, - "mode": "chat", - "output_cost_per_token": 1.1e-07, - "supports_tool_choice": false, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mancer/weaver": { - "input_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_tokens": 6000, - "mode": "chat", - "output_cost_per_token": 7.5e-07, - "supports_tool_choice": false, - "max_input_tokens": 8000, - "max_output_tokens": 6000, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/meta-llama/llama-3-70b-instruct": { - "input_cost_per_token": 5.9e-07, - "litellm_provider": "openrouter", - "max_tokens": 8000, - "mode": "chat", - "output_cost_per_token": 7.9e-07, - "supports_tool_choice": true, - "max_input_tokens": 8192, - "max_output_tokens": 8000 - }, - "openrouter/minimax/minimax-m2": { - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mistralai/devstral-2512": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_image": 0, - "input_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mistralai/ministral-3b-2512": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_image": 0, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, - "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/ministral-8b-2512": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_image": 0, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/ministral-14b-2512": { - "cache_read_input_token_cost": 2e-08, - "input_cost_per_image": 0, - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-7b-instruct": { - "input_cost_per_token": 1.3e-07, - "litellm_provider": "openrouter", - "max_tokens": 8191, - "mode": "chat", - "output_cost_per_token": 1.3e-07, - "supports_tool_choice": true, - "max_input_tokens": 32768, - "max_output_tokens": 8191 - }, - "openrouter/mistralai/mistral-large": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_tokens": 102400, - "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_tool_choice": true, - "max_input_tokens": 128000, - "max_output_tokens": 102400, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-small-3.1-24b-instruct": { - "input_cost_per_token": 3.51e-07, - "litellm_provider": "openrouter", - "max_tokens": 102400, - "mode": "chat", - "output_cost_per_token": 5.55e-07, - "supports_tool_choice": true, - "max_input_tokens": 128000, - "max_output_tokens": 102400, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "input_cost_per_token": 9.375e-08, - "litellm_provider": "openrouter", - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "supports_tool_choice": true, - "max_input_tokens": 256000, - "max_output_tokens": 16384, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mixtral-8x22b-instruct": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_tokens": 52428, - "mode": "chat", - "output_cost_per_token": 6e-06, - "supports_tool_choice": true, - "max_input_tokens": 65536, - "max_output_tokens": 52428, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k2.5": { - "cache_read_input_token_cost": 7e-08, - "input_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 2.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3.5-lightning": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_token": 8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-3.5-turbo": { - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "supports_tool_choice": true, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-3.5-turbo-16k": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 4e-06, - "supports_tool_choice": true, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-4": { - "input_cost_per_token": 3e-05, - "litellm_provider": "openrouter", - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 6e-05, - "supports_tool_choice": true, - "max_input_tokens": 8191, - "max_output_tokens": 4096, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-4.1": { - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4.1-mini": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4.1-nano": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4o": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 1.25e-06, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4o-2024-05-13": { - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-chat": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_reasoning": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-5-codex": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_reasoning": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-5.2-codex": { - "cache_read_input_token_cost": 1.75e-07, - "input_cost_per_token": 1.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-mini": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-nano": { - "cache_read_input_token_cost": 5e-09, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.1-codex-max": { - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.2": { - "input_cost_per_image": 0, - "cache_read_input_token_cost": 1.75e-07, - "input_cost_per_token": 1.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.2-chat": { - "input_cost_per_image": 0, - "cache_read_input_token_cost": 1.75e-07, - "input_cost_per_token": 1.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 1.4e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.2-pro": { - "input_cost_per_image": 0, - "input_cost_per_token": 2.1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.000168, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "default_reasoning_effort": "medium", - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "reasoning_effort_levels": [ - "none", - "low", - "medium", - "high", - "xhigh", - "max" - ], - "source": "https://openrouter.ai/api/v1/models", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-sol-pro": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-oss-120b": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-oss-120b:batch": { - "input_cost_per_token": 2.96e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 1.36e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-oss-20b": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 1.8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 9e-08, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/o1": { - "cache_read_input_token_cost": 7.5e-06, - "input_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 6e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/o3-mini": { - "input_cost_per_token": 1.1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 4.4e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": false, - "cache_read_input_token_cost": 5.5e-07, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/openai/o3-mini-high": { - "input_cost_per_token": 1.1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 4.4e-06, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": false, - "cache_read_input_token_cost": 5.5e-07, - "supports_prompt_caching": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_web_search": true - }, - "openrouter/qwen/qwen-2.5-coder-32b-instruct": { - "input_cost_per_token": 6.6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen-vl-plus": { - "input_cost_per_token": 2.1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 6.3e-07, - "supports_tool_choice": true, - "supports_vision": true - }, - "openrouter/qwen/qwen3-coder": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_tool_choice": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-coder-plus": { - "cache_creation_input_token_cost": 8.125e-07, - "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06, - "cache_read_input_token_cost_above_128k_tokens": 3.9e-07, - "input_cost_per_token_above_32k_tokens": 1.17e-06, - "cache_creation_input_token_cost_above_32k_tokens": 1.4625e-06, - "cache_read_input_token_cost_above_32k_tokens": 2.34e-07, - "output_cost_per_token_above_32k_tokens": 5.85e-06, - "cache_read_input_token_cost": 1.3e-07, - "input_cost_per_token": 6.5e-07, - "input_cost_per_token_above_128k_tokens": 1.95e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 3.25e-06, - "output_cost_per_token_above_128k_tokens": 9.75e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-235b-a22b-2507": { - "cache_read_input_token_cost": 1.75e-08, - "input_cost_per_token": 8.75e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 3.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-235b-a22b-thinking-2507": { - "input_cost_per_token": 2.3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 2.3e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.6-plus": { - "cache_creation_input_token_cost": 4.0625e-07, - "input_cost_per_token_above_256k_tokens": 1.3e-06, - "cache_creation_input_token_cost_above_256k_tokens": 1.625e-06, - "output_cost_per_token_above_256k_tokens": 3.9e-06, - "input_cost_per_token": 3.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.95e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-35b-a3b": { - "input_cost_per_token": 3.125e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_vision": true, - "cache_read_input_token_cost": 1.5625e-07, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-27b": { - "input_cost_per_token": 1.95e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.56e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-122b-a10b": { - "input_cost_per_token": 2.6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 2.08e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-flash-02-23": { - "input_cost_per_token": 6.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 2.6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-plus-02-15": { - "input_cost_per_token": 2.6e-07, - "input_cost_per_token_above_256k_tokens": 3.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.56e-06, - "output_cost_per_token_above_256k_tokens": 1.95e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-397b-a17b": { - "cache_read_input_token_cost": 2.25e-07, - "input_cost_per_token": 5.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 3.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/switchpoint/router": { - "input_cost_per_token": 8.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3.4e-06, - "source": "https://openrouter.ai/switchpoint/router", - "supports_tool_choice": true - }, - "openrouter/undi95/remm-slerp-l2-13b": { - "input_cost_per_token": 3.5e-07, - "litellm_provider": "openrouter", - "max_tokens": 5529, - "mode": "chat", - "output_cost_per_token": 6.5e-07, - "supports_tool_choice": false, - "max_input_tokens": 6144, - "max_output_tokens": 5529, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/x-ai/grok-4": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "max_tokens": 256000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/x-ai/grok-4", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "openrouter/z-ai/glm-4.6": { - "input_cost_per_token": 4.3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.75e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "cache_read_input_token_cost": 8e-08, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.6:exacto": { - "input_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 202800, - "max_output_tokens": 131000, - "max_tokens": 131000, - "mode": "chat", - "output_cost_per_token": 1.9e-06, - "source": "https://openrouter.ai/z-ai/glm-4.6:exacto", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "openrouter/xiaomi/mimo-v2-flash": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 1e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true - }, - "openrouter/xiaomi/mimo-v2.5-pro": { - "input_cost_per_token": 4.35e-07, - "output_cost_per_token": 8.7e-07, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 3.6e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/xiaomi/mimo-v2.5": { - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 2.8e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_pdf_input": false, - "supports_video_input": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.7": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.75e-06, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_assistant_prefill": true, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_response_schema": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.7-flash": { - "input_cost_per_token": 6.05e-08, - "output_cost_per_token": 4e-07, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 1e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": false, - "supports_response_schema": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5": { - "cache_read_input_token_cost": 1.2e-07, - "input_cost_per_token": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.92e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.1": { - "input_cost_per_token": 9.66e-07, - "output_cost_per_token": 3.036e-06, - "cache_read_input_token_cost": 1.794e-07, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m2.1": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-10-08", - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_computer_use": false, - "supports_pdf_input": false, - "supports_response_schema": true, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m2.5": { - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 1.08e-06, - "cache_read_input_token_cost": 2.7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_computer_use": false, - "supports_pdf_input": false, - "supports_response_schema": true, - "supports_web_search": false - }, - "openrouter/openrouter/auto": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_tokens": 2000000, - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true - }, - "openrouter/openrouter/free": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_tokens": 200000, - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true - }, - "openrouter/openrouter/bodybuilder": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_tokens": 128000, - "mode": "chat" - }, "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { "input_cost_per_token": 6.7e-07, "litellm_provider": "ovhcloud", @@ -43613,66 +45918,6 @@ "supports_response_schema": true, "supports_tool_choice": false }, - "palm/chat-bison": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/chat-bison-001": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "completion", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-001": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "completion", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-safety-off": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "completion", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-safety-recitation-off": { - "input_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "max_tokens": 1024, - "mode": "completion", - "output_cost_per_token": 1.25e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, "parallel_ai/search": { "input_cost_per_query": 0.005, "litellm_provider": "parallel_ai", @@ -43794,6 +46039,54 @@ "mode": "chat", "output_cost_per_token": 2.8e-07 }, + "perplexity/pplx-decider-v1-27b": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/api-reference/decisions-post" + }, + "perplexity/pplx-decider-v1.1-27b": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/getting-started/pricing" + }, + "perplexity/pplx-decider-v1.2": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, + "perplexity/pplx-decider-latest": { + "input_cost_per_token": 2e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, + "perplexity/pplx-decider-flash-v1.2": { + "input_cost_per_token": 1e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, + "perplexity/pplx-decider-flash-latest": { + "input_cost_per_token": 1e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.perplexity.ai/docs/decisions/quickstart" + }, "perplexity/sonar": { "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", @@ -44160,6 +46453,14 @@ "supports_reasoning": true, "supports_function_calling": true }, + "perplexity/perplexity/deepseek-v4-pro-0813": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1.32e-06, + "output_cost_per_token": 3.96e-06, + "cache_read_input_token_cost": 4.4e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/perplexity/glm-5.2": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, @@ -44260,42 +46561,52 @@ "supports_reasoning": true }, "qwen.qwen3-coder-480b-a35b-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.5e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 262000, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.8e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-west-2/index.json" + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html" }, "qwen.qwen3-235b-a22b-2507-v1:0": { "input_cost_per_token": 2.2e-07, + "input_cost_per_token_flex": 1.1e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8.8e-07, + "output_cost_per_token_flex": 4.4e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "input_cost_per_token_batches": 1.1e-07, - "output_cost_per_token_batches": 4.4e-07 + "output_cost_per_token_batches": 4.4e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html" }, "qwen.qwen3-coder-30b-a3b-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -44303,12 +46614,19 @@ }, "qwen.qwen3-32b-v1:0": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_flex": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -44333,12 +46651,12 @@ "bedrock/ap-northeast-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44349,12 +46667,12 @@ "bedrock/ap-south-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44365,12 +46683,12 @@ "bedrock/ap-southeast-2/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.545e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.236e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44381,12 +46699,12 @@ "bedrock/eu-west-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44397,12 +46715,12 @@ "bedrock/eu-west-2/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 2.3e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.86e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44413,12 +46731,12 @@ "bedrock/sa-east-1/qwen.qwen3-next-80b-a3b": { "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "supports_function_calling": true, "supports_native_structured_output": true, "supports_system_messages": true, @@ -44428,13 +46746,17 @@ }, "qwen.qwen3-vl-235b-a22b": { "input_cost_per_token": 5.3e-07, + "input_cost_per_token_batches": 2.6e-07, + "input_cost_per_token_priority": 9.3e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.66e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_batches": 1.33e-06, + "output_cost_per_token_priority": 4.66e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_system_messages": true, @@ -44444,16 +46766,22 @@ }, "qwen.qwen3-coder-next": { "input_cost_per_token": 5e-07, + "input_cost_per_token_batches": 2.5e-07, + "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 8.75e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_flex": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -45157,6 +47485,53 @@ "supports_vision": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, + "scx-ai/DeepSeek-V4.1-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "scx-ai", + "max_input_tokens": 1000000, + "max_output_tokens": 375000, + "max_tokens": 375000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://scx.ai/models/deepseek-v4-1-flash", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "scx-ai/GLM-5.3": { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 9.8e-07, + "litellm_provider": "scx-ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.08e-06, + "source": "https://scx.ai/models/glm-5-3", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, + "scx-ai/Kimi-K3": { + "cache_read_input_token_cost": 2.8e-07, + "input_cost_per_token": 2.83e-06, + "litellm_provider": "scx-ai", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.413e-05, + "source": "https://scx.ai/models/kimi-k3", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": false + }, "scx-ai/GLM-5.2": { "cache_read_input_token_cost": 2.2e-07, "input_cost_per_token": 6.1e-07, @@ -45607,78 +47982,169 @@ "mode": "image_edit", "output_cost_per_image": 0.4 }, + "us.stability.stable-conservative-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.4, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-creative-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.6 }, + "us.stability.stable-creative-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.6, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-fast-upscale-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.03 }, + "us.stability.stable-fast-upscale-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.03, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-outpaint-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.06 }, + "us.stability.stable-outpaint-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.06, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-control-sketch-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-control-sketch-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-control-structure-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-control-structure-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-erase-object-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-erase-object-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-inpaint-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-inpaint-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-remove-background-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-remove-background-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-search-recolor-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-search-recolor-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-search-replace-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-search-replace-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-style-guide-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.07 }, + "us.stability.stable-image-style-guide-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.07, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-style-transfer-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, "mode": "image_edit", "output_cost_per_image": 0.08 }, + "us.stability.stable-style-transfer-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "mode": "image_edit", + "output_cost_per_image": 0.08, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "stability.stable-image-core-v1:1": { "litellm_provider": "bedrock", "max_input_tokens": 77, @@ -45909,14 +48375,6 @@ "mode": "embedding", "output_cost_per_token": 0.0 }, - "together_ai/baai/bge-base-en-v1.5": { - "input_cost_per_token": 8e-09, - "litellm_provider": "together_ai", - "max_input_tokens": 512, - "mode": "embedding", - "output_cost_per_token": 0.0, - "output_vector_size": 768 - }, "together_ai/BAAI/bge-base-en-v1.5": { "input_cost_per_token": 8e-09, "litellm_provider": "together_ai", @@ -45960,6 +48418,7 @@ "supports_tool_choice": true }, "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "deprecation_date": "2026-10-22", "input_cost_per_token": 1.04e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -46082,7 +48541,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 4.5e-06, - "source": "https://api.together.ai/v1/models", + "source": "https://www.together.ai/pricing", "supports_prompt_caching": true }, "together_ai/Qwen/Qwen3.7-Plus": { @@ -46116,7 +48575,7 @@ }, "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-09-29", + "deprecation_date": "2026-10-22", "input_cost_per_token": 1.4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -46146,7 +48605,6 @@ }, "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { "cache_read_input_token_cost": 1.3e-07, - "deprecation_date": "2026-09-29", "input_cost_per_token": 1.32e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -46171,6 +48629,19 @@ "source": "https://api.together.ai/v1/models", "supports_prompt_caching": true }, + "together_ai/meta-models/Muse-Spark-Open-816B-A42B": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "source": "https://docs.together.ai/docs/serverless-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, "together_ai/moonshotai/Kimi-K3": { "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, @@ -46261,6 +48732,7 @@ "supports_vision": true }, "tts-1": { + "deprecation_date": "2027-01-06", "input_cost_per_character": 1.5e-05, "litellm_provider": "openai", "mode": "audio_speech", @@ -46270,6 +48742,7 @@ ] }, "tts-1-hd": { + "deprecation_date": "2027-01-06", "input_cost_per_character": 3e-05, "litellm_provider": "openai", "mode": "audio_speech", @@ -46327,12 +48800,15 @@ "us.amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, + "input_cost_per_token_batches": 3e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, + "output_cost_per_token_batches": 1.2e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -46343,12 +48819,15 @@ "us.amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 8.75e-09, "input_cost_per_token": 3.5e-08, + "input_cost_per_token_batches": 1.75e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, + "output_cost_per_token_batches": 7e-08, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, @@ -46356,13 +48835,22 @@ }, "us.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 8e-07, + "input_cost_per_token_batches": 4e-07, + "input_cost_per_token_flex": 4e-07, + "input_cost_per_token_priority": 1.4e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_flex": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_pdf_input": true, "supports_prompt_caching": true, @@ -46414,7 +48902,11 @@ "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, - "output_cost_per_token_batches": 2.75e-06 + "output_cost_per_token_batches": 2.75e-06, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { "input_cost_per_token": 3e-06, @@ -46512,7 +49004,11 @@ "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-1-20250805-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.125e-06, @@ -46524,6 +49020,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.32e-05, "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, + "deprecation_date": "2027-04-08", "litellm_provider": "bedrock_converse", "supports_tool_search": true, "max_input_tokens": 200000, @@ -46550,7 +49047,11 @@ "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 1.65e-06, "output_cost_per_token_batches": 8.25e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 4.5e-06, @@ -46581,7 +49082,11 @@ "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "litellm_provider": "bedrock" + } }, "us-gov.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -46606,6 +49111,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -46615,7 +49121,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -46640,6 +49151,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -46649,7 +49161,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -46682,7 +49199,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -46717,7 +49239,12 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, - "supports_forced_tool_use": false + "supports_forced_tool_use": false, + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.5e-05, @@ -46751,7 +49278,12 @@ "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-fable-5-1", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us-gov.nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, @@ -46771,6 +49303,7 @@ "supports_vision": false }, "us-gov.nvidia.nemotron-nano-12b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.4e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -46778,6 +49311,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, @@ -46785,6 +49319,7 @@ "supports_response_schema": true }, "us-gov.nvidia.nemotron-nano-9b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -46792,6 +49327,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, @@ -46819,10 +49355,16 @@ "input_cost_per_token": 8.4e-08, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -46832,19 +49374,31 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "us-gov.xai.grok-4.6": { + "supports_regex_lookaround": false, "input_cost_per_token": 2.64e-06, "output_cost_per_token": 7.92e-06, "cache_read_input_token_cost": 6.6e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, @@ -46882,7 +49436,11 @@ "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-07, "output_cost_per_token_batches": 2.75e-06, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-opus-4-20250514-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -46941,7 +49499,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "global.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.25e-06, @@ -46974,7 +49536,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "eu.anthropic.claude-opus-4-5-20251101-v1:0": { "cache_creation_input_token_cost": 6.875e-06, @@ -47007,7 +49573,11 @@ "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "litellm_provider": "bedrock" + } }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -47019,7 +49589,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -47040,29 +49610,41 @@ "supports_vision": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "litellm_provider": "bedrock" + } }, "us.deepseek.r1-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.35e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", "supports_function_calling": false, "supports_reasoning": true, "supports_tool_choice": false }, "us.deepseek.v3.2": { "input_cost_per_token": 6.2e-07, + "input_cost_per_token_batches": 3.1e-07, + "input_cost_per_token_flex": 3.1e-07, + "input_cost_per_token_priority": 1.085e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, + "output_cost_per_token_batches": 9.25e-07, + "output_cost_per_token_flex": 9.25e-07, + "output_cost_per_token_priority": 3.2375e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -47073,12 +49655,14 @@ }, "eu.deepseek.v3.2": { "input_cost_per_token": 7.4e-07, + "input_cost_per_token_flex": 3.7e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 2.22e-06, + "output_cost_per_token_flex": 1.11e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, @@ -47088,51 +49672,64 @@ "supports_vision": false }, "us.meta.llama3-1-405b-instruct-v1:0": { - "input_cost_per_token": 5.32e-06, + "deprecation_date": "2026-07-07", + "input_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 1.6e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-1-70b-instruct-v1:0": { - "input_cost_per_token": 9.9e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 9.9e-07, - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-1-8b-instruct-v1:0": { - "input_cost_per_token": 2.2e-07, - "litellm_provider": "bedrock", - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "output_cost_per_token": 2.2e-07, - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-2-11b-instruct-v1:0": { - "input_cost_per_token": 3.5e-07, + "deprecation_date": "2027-03-30", + "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.5e-07, + "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-1-8b-instruct-v1:0": { + "deprecation_date": "2027-03-30", + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "output_cost_per_token_batches": 1.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-2-11b-instruct-v1:0": { + "deprecation_date": "2026-07-07", + "input_cost_per_token": 1.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.6e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true }, "us.meta.llama3-2-1b-instruct-v1:0": { + "deprecation_date": "2026-07-07", "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -47140,10 +49737,12 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-1b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-2-3b-instruct-v1:0": { + "deprecation_date": "2026-07-07", "input_cost_per_token": 1.5e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -47151,42 +49750,51 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-2-3b-instruct.md", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama3-2-90b-instruct-v1:0": { - "input_cost_per_token": 2e-06, + "deprecation_date": "2026-07-07", + "input_cost_per_token": 7.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 2e-06, + "output_cost_per_token": 7.2e-07, + "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", "supports_function_calling": true, "supports_tool_choice": false, "supports_vision": true }, "us.meta.llama3-3-70b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.2e-07, + "input_cost_per_token_batches": 3.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, + "output_cost_per_token_batches": 3.6e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_function_calling": true, "supports_tool_choice": false }, "us.meta.llama4-maverick-17b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.4e-07, "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9.7e-07, "output_cost_per_token_batches": 4.85e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.md", "supported_modalities": [ "text", "image" @@ -47199,15 +49807,17 @@ "supports_tool_choice": false }, "us.meta.llama4-scout-17b-instruct-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.7e-07, "input_cost_per_token_batches": 8.5e-08, "litellm_provider": "bedrock_converse", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_input_tokens": 10000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_batches": 3.3e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.md", "supported_modalities": [ "text", "image" @@ -47223,11 +49833,11 @@ "input_cost_per_token": 2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-pixtral-large.md", "supports_function_calling": true, "supports_tool_choice": false }, @@ -47617,7 +50227,7 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -49389,7 +51999,8 @@ "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_creation_input_token_cost_batches": 1.88e-06 }, "vertex_ai/claude-sonnet-5": { "deprecation_date": "2026-12-24", @@ -49446,7 +52057,7 @@ "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -49497,7 +52108,8 @@ "supports_vision": true, "supports_native_streaming": true, "prompt_cache_min_tokens": 1024, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_creation_input_token_cost_batches": 1.88e-06 }, "vertex_ai/mistralai/codestral-2@001": { "input_cost_per_token": 3e-07, @@ -49618,7 +52230,7 @@ "supported_regions": [ "global" ], - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -49639,7 +52251,7 @@ "supported_regions": [ "us-central1" ], - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -49666,7 +52278,8 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -49723,7 +52336,14 @@ "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "supports_reasoning": false, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ] + }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -49750,17 +52370,26 @@ "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, "output_cost_per_token_batches": 6e-06, "supports_reasoning": false, - "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" + "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ] + }, "vertex_ai/gemini-3.1-flash-image": { "cache_read_input_token_cost": 5e-08, "cache_read_input_token_cost_batches": 2.5e-08, "cache_read_input_token_cost_flex": 2.5e-08, + "cache_read_input_token_cost_priority": 9e-08, "deprecation_date": "2027-05-28", "input_cost_per_image": 0.00056, "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "input_cost_per_token_flex": 2.5e-07, + "input_cost_per_token_priority": 9e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, @@ -49771,8 +52400,17 @@ "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, + "output_cost_per_token_priority": 5.4e-06, + "regional_endpoint_uplift_multiplier": 1.1, "supports_reasoning": false, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ] + }, "vertex_ai/gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -49790,16 +52428,26 @@ "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, "supports_reasoning": false, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ] + }, "vertex_ai/gemini-3.1-flash-lite-image": { "cache_read_input_token_cost": 2.5e-08, "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2027-06-28", "input_cost_per_image": 0.00028, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, @@ -49810,10 +52458,12 @@ "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.7e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions", + "/v1/images/generations", + "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ @@ -49880,6 +52530,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -49942,6 +52593,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-07 @@ -49990,6 +52642,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, @@ -50002,6 +52655,7 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, + "search_free_requests": {"count": 5000, "period": "month", "shared_group": "gemini-3"}, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014 }, @@ -50015,7 +52669,7 @@ "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, - "mode": "image_generation", + "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, @@ -50900,6 +53554,26 @@ "mode": "rerank", "output_cost_per_token": 0.0 }, + "voyage/rerank-1": { + "input_cost_per_token": 5e-08, + "litellm_provider": "voyage", + "max_input_tokens": 8000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://docs.voyageai.com/docs/pricing" + }, + "voyage/rerank-lite-1": { + "input_cost_per_token": 2e-08, + "litellm_provider": "voyage", + "max_input_tokens": 4000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://docs.voyageai.com/docs/pricing" + }, "voyage/rerank-2.5": { "input_cost_per_token": 5e-08, "litellm_provider": "voyage", @@ -51036,6 +53710,16 @@ "mode": "embedding", "output_cost_per_token": 0.0 }, + "voyage/voyage-large-2-instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.voyageai.com/docs/pricing" + }, "voyage/voyage-law-2": { "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", @@ -51585,13 +54269,16 @@ }, "xai/grok-4.20-0309-reasoning": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, @@ -51599,8 +54286,11 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true @@ -51629,9 +54319,13 @@ "xai/grok-4.3": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_image_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, @@ -51639,6 +54333,8 @@ "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -51651,9 +54347,13 @@ "xai/grok-4.3-latest": { "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_image_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, @@ -51661,6 +54361,8 @@ "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -51781,53 +54483,71 @@ "supports_web_search": true }, "zai.glm-4.7": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_flex": 1.1e-06, + "output_cost_per_token_priority": 3.85e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "zai.glm-5": { "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "input_cost_per_token_priority": 1.75e-06, "output_cost_per_token": 3.2e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.6e-06, + "output_cost_per_token_priority": 5.6e-06, "supports_function_calling": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false }, "zai.glm-4.7-flash": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3.5e-08, + "input_cost_per_token_flex": 3.5e-08, + "input_cost_per_token_priority": 1.225e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, - "max_output_tokens": 4000, - "max_tokens": 4000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_flex": 2e-07, + "output_cost_per_token_priority": 7e-07, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_response_schema": true, "supports_vision": false @@ -52036,6 +54756,70 @@ "litellm_provider": "vertex_ai", "mode": "vector_store" }, + "vertex_ai/semantic-ranker-default": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-default-002": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-default-003": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-default-004": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-default@latest": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-fast": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-fast-004": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, + "vertex_ai/semantic-ranker-fast@latest": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai", + "mode": "rerank", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/generative-ai-app-builder/pricing" + }, "openai/container": { "code_interpreter_cost_per_session": 0.03, "litellm_provider": "openai", @@ -52084,7 +54868,7 @@ ] }, "azure/sora-2": { - "deprecation_date": "2026-10-15", + "deprecation_date": "2026-11-02", "litellm_provider": "azure", "mode": "video_generation", "output_cost_per_video_per_second": 0.1, @@ -52794,7 +55578,7 @@ }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt": { "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, @@ -52803,7 +55587,7 @@ }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt": { "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, @@ -53263,7 +56047,7 @@ }, "fireworks_ai/accounts/fireworks/models/minimax-m2": { "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 196608, "max_output_tokens": 4096, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, @@ -53434,7 +56218,7 @@ }, "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl": { "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, "output_cost_per_token": 1e-07, @@ -53497,7 +56281,7 @@ }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2": { "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -53506,7 +56290,7 @@ }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2": { "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -54102,7 +56886,7 @@ }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16": { "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, "output_cost_per_token": 9e-07, @@ -54127,15 +56911,6 @@ "litellm_provider": "fireworks_ai", "mode": "embedding" }, - "fireworks_ai/accounts/fireworks/models/": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai", - "mode": "embedding" - }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct": { "max_tokens": 4096, "max_input_tokens": 4096, @@ -54229,7 +57004,7 @@ }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct": { "max_tokens": 4096, - "max_input_tokens": 4096, + "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -56098,6 +58873,7 @@ ] }, "gpt-4o-mini-tts-2025-12-15": { + "deprecation_date": "2027-01-06", "input_cost_per_token": 6e-07, "litellm_provider": "openai", "mode": "audio_speech", @@ -56316,6 +59092,7 @@ ] }, "gemini-2.0-flash-exp-image-generation": { + "deprecation_date": "2025-11-14", "input_cost_per_token": 0.0, "litellm_provider": "gemini", "max_input_tokens": 32768, @@ -56336,6 +59113,7 @@ "supports_vision": true }, "gemini/gemini-2.0-flash-exp-image-generation": { + "deprecation_date": "2025-11-14", "input_cost_per_token": 0.0, "litellm_provider": "gemini", "max_input_tokens": 32768, @@ -56410,6 +59188,7 @@ "gemini_native_audio": true }, "gemini-2.5-flash-native-audio-preview-12-2025": { + "deprecation_date": "2026-11-17", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", @@ -56440,6 +59219,7 @@ "supports_web_search": true }, "gemini-3.1-flash-live-preview": { + "deprecation_date": "2026-11-17", "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, @@ -56601,6 +59381,7 @@ "gemini_native_audio": true }, "gemini/gemini-2.5-flash-native-audio-preview-12-2025": { + "deprecation_date": "2026-11-17", "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", @@ -56630,9 +59411,11 @@ "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_reasoning": true }, "gemini/gemini-3.1-flash-live-preview": { + "deprecation_date": "2026-11-17", "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, "input_cost_per_token": 7.5e-07, @@ -56668,9 +59451,11 @@ "rpm": 10, "gemini_audio_only_live": true, "input_cost_per_second": 8.33333333333e-05, - "supports_response_schema": false + "supports_response_schema": false, + "supports_reasoning": true }, "gemini/gemini-3.1-flash-tts-preview": { + "deprecation_date": "2026-11-17", "input_cost_per_token": 1e-06, "input_cost_per_token_batches": 5e-07, "litellm_provider": "gemini", @@ -56713,7 +59498,8 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" - ] + ], + "supports_prompt_caching": true }, "gemini/gemini-3.8-flash-lite-tts": { "cache_read_input_token_cost": 1.25e-07, @@ -56737,9 +59523,11 @@ "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/audio/speech" - ] + ], + "supports_prompt_caching": true }, "gemini-2.5-flash-preview-tts": { + "deprecation_date": "2026-11-17", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", @@ -57101,7 +59889,7 @@ "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -57130,12 +59918,19 @@ }, "bedrock_mantle/openai.gpt-oss-120b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, + "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -57148,12 +59943,19 @@ }, "bedrock_mantle/openai.gpt-oss-20b": { "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3.5e-08, + "input_cost_per_token_flex": 3.5e-08, + "input_cost_per_token_priority": 1.225e-07, "output_cost_per_token": 3e-07, + "output_cost_per_token_flex": 1.5e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 1.5e-07, + "output_cost_per_token_priority": 5.25e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -57166,12 +59968,19 @@ }, "bedrock_mantle/openai.gpt-oss-safeguard-120b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "output_cost_per_token": 6e-07, + "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], @@ -57182,12 +59991,19 @@ }, "bedrock_mantle/openai.gpt-oss-safeguard-20b": { "input_cost_per_token": 7e-08, + "input_cost_per_token_batches": 3e-08, + "input_cost_per_token_flex": 3e-08, + "input_cost_per_token_priority": 1.2e-07, "output_cost_per_token": 2e-07, + "output_cost_per_token_flex": 1e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 16000, + "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 1e-07, + "output_cost_per_token_priority": 3.5e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supported_endpoints": [ "/v1/chat/completions" ], @@ -57231,6 +60047,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57274,6 +60091,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57288,10 +60106,11 @@ "cache_read_input_token_cost": 1.375e-06, "output_cost_per_token": 8.25e-05, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 272000, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-cyber.html", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" @@ -57306,6 +60125,7 @@ "supports_function_calling": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57382,6 +60202,7 @@ "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57391,6 +60212,7 @@ "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html" }, "us.openai.gpt-5.6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 4.4e-06, "input_cost_per_token_above_272k_tokens": 8.8e-06, "cache_creation_input_token_cost": 5.5e-06, @@ -57400,11 +60222,12 @@ "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ "text", "image" @@ -57421,10 +60244,12 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "global.openai.gpt-5.6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "cache_creation_input_token_cost": 5e-06, @@ -57434,11 +60259,12 @@ "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ "text", "image" @@ -57455,10 +60281,12 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-5.6-terra": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "cache_creation_input_token_cost": 2.75e-06, @@ -57468,11 +60296,12 @@ "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ "text", "image" @@ -57489,10 +60318,12 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "global.openai.gpt-5.6-terra": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "cache_creation_input_token_cost": 2.5e-06, @@ -57502,11 +60333,12 @@ "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ "text", "image" @@ -57523,10 +60355,12 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-5.6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, "cache_creation_input_token_cost": 2.75e-07, @@ -57536,11 +60370,12 @@ "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ "text", "image" @@ -57557,6 +60392,7 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, @@ -57568,7 +60404,8 @@ "output_cost_per_token": 1.65e-05, "output_cost_per_token_above_272k_tokens": 2.475e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -57599,7 +60436,8 @@ "output_cost_per_token": 1.5e-05, "output_cost_per_token_above_272k_tokens": 2.25e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -57630,7 +60468,8 @@ "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -57661,7 +60500,8 @@ "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -57685,6 +60525,7 @@ ] }, "global.openai.gpt-5.6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, "cache_creation_input_token_cost": 2.5e-07, @@ -57694,11 +60535,12 @@ "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ "text", "image" @@ -57715,6 +60557,7 @@ "supports_vision": true, "supports_sampling_params": false, "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, @@ -57723,8 +60566,14 @@ "input_cost_per_token_above_272k_tokens": 2.2e-05, "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.000165, + "cache_creation_input_token_cost_ultrafast": 8.25e-05, "cache_read_input_token_cost": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-05, + "cache_read_input_token_cost_ultrafast": 6.6e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 0.000132, + "input_cost_per_token_ultrafast": 6.6e-05, "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, "litellm_provider": "bedrock_mantle", @@ -57732,6 +60581,8 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", + "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495, + "output_cost_per_token_ultrafast": 0.00033, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -57749,6 +60600,7 @@ "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57785,8 +60637,9 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57823,8 +60676,9 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -57833,19 +60687,29 @@ "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html" }, "us.openai.gpt-6-astra": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1.1e-05, "input_cost_per_token_above_272k_tokens": 2.2e-05, "cache_creation_input_token_cost": 1.375e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.000165, + "cache_creation_input_token_cost_ultrafast": 8.25e-05, "cache_read_input_token_cost": 1.1e-06, "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-05, + "cache_read_input_token_cost_ultrafast": 6.6e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 0.000132, + "input_cost_per_token_ultrafast": 6.6e-05, "output_cost_per_token": 5.5e-05, "output_cost_per_token_above_272k_tokens": 8.25e-05, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495, + "output_cost_per_token_ultrafast": 0.00033, "supported_modalities": [ "text", "image" @@ -57862,12 +60726,15 @@ "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_sampling_params": false, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, "cache_creation_input_token_cost": 2.75e-06, @@ -57877,6 +60744,7 @@ "output_cost_per_token": 1.1e-05, "output_cost_per_token_above_272k_tokens": 1.65e-05, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -57891,18 +60759,21 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "us.openai.gpt-6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1.1e-07, "input_cost_per_token_above_272k_tokens": 2.2e-07, "cache_creation_input_token_cost": 1.375e-07, @@ -57912,6 +60783,7 @@ "output_cost_per_token": 5.5e-07, "output_cost_per_token_above_272k_tokens": 8.25e-07, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -57926,31 +60798,43 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, "global.openai.gpt-6-astra": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015, + "cache_creation_input_token_cost_ultrafast": 7.5e-05, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-05, + "cache_read_input_token_cost_ultrafast": 6e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012, + "input_cost_per_token_ultrafast": 6e-05, "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045, + "output_cost_per_token_ultrafast": 0.0003, "supported_modalities": [ "text", "image" @@ -57967,8 +60851,10 @@ "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_sampling_params": false, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, @@ -57982,6 +60868,7 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -57996,15 +60883,17 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.openai.gpt-6-sol": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, "cache_creation_input_token_cost": 2.5e-06, @@ -58014,6 +60903,7 @@ "output_cost_per_token": 1e-05, "output_cost_per_token_above_272k_tokens": 1.5e-05, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -58028,14 +60918,16 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, @@ -58049,6 +60941,7 @@ "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -58063,15 +60956,17 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/" }, "global.openai.gpt-6-luna": { + "supports_bedrock_runtime_chat_completions_response_format": true, "input_cost_per_token": 1e-07, "input_cost_per_token_above_272k_tokens": 2e-07, "cache_creation_input_token_cost": 1.25e-07, @@ -58081,6 +60976,7 @@ "output_cost_per_token": 5e-07, "output_cost_per_token_above_272k_tokens": 7.5e-07, "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, @@ -58095,14 +60991,16 @@ "supports_function_calling": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "supports_none_reasoning_effort": false, + "supports_none_reasoning_effort": true, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, + "supports_sampling_params": false, "source": "https://aws.amazon.com/bedrock/pricing/", "supported_endpoints": [ + "/v1/chat/completions", "/v1/responses" ] }, @@ -58188,12 +61086,19 @@ }, "bedrock_mantle/google.gemma-4-31b": { "input_cost_per_token": 1.4e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.45e-07, "output_cost_per_token": 4e-07, + "output_cost_per_token_flex": 2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_priority": 7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58207,12 +61112,19 @@ }, "bedrock_mantle/google.gemma-4-26b-a4b": { "input_cost_per_token": 1.3e-07, + "input_cost_per_token_batches": 6.5e-08, + "input_cost_per_token_flex": 6.5e-08, + "input_cost_per_token_priority": 2.275e-07, "output_cost_per_token": 4e-07, + "output_cost_per_token_flex": 2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "mode": "chat", + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_priority": 7e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58226,12 +61138,19 @@ }, "bedrock_mantle/google.gemma-4-e2b": { "input_cost_per_token": 4e-08, + "input_cost_per_token_batches": 2e-08, + "input_cost_per_token_flex": 2e-08, + "input_cost_per_token_priority": 7e-08, "output_cost_per_token": 8e-08, + "output_cost_per_token_flex": 4e-08, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 4e-08, + "output_cost_per_token_priority": 1.4e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", @@ -58248,11 +61167,20 @@ "input_cost_per_token": 1.25e-06, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_flex": 6.25e-07, + "input_cost_per_token_priority": 2.1875e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 1048576, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.375e-06, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -58262,18 +61190,24 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/xai.grok-4.6": { "use_openai_responses_path": true, "input_cost_per_token": 2.2e-06, "output_cost_per_token": 6.6e-06, "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, "max_tokens": 500000, "mode": "chat", + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -58314,15 +61248,108 @@ "input_cost_per_token_batches": 5e-07, "output_cost_per_token_batches": 2.5e-06 }, + "bedrock_mantle/anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_1hr": 8.8e-06, + "cache_read_input_token_cost": 2.2e-07, + "input_cost_per_token": 4.4e-06, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "prompt_cache_min_tokens": 512, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html", + "thinking_always_on": true, + "supports_forced_tool_use": false + }, + "bedrock_mantle/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, "us.xai.grok-4.6": { + "supports_regex_lookaround": false, "input_cost_per_token": 2.2e-06, "output_cost_per_token": 6.6e-06, "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, "max_tokens": 500000, "mode": "chat", + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_prompt_caching": false, @@ -58331,14 +61358,26 @@ "supports_vision": true }, "global.xai.grok-4.6": { + "supports_regex_lookaround": false, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, "max_tokens": 500000, "mode": "chat", + "output_cost_per_token_flex": 3e-06, + "output_cost_per_token_priority": 1.05e-05, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_function_calling": true, "supports_prompt_caching": false, @@ -58400,6 +61439,41 @@ "supports_tool_choice": false, "supports_vision": true }, + "volcengine/doubao-seed-2-1-pro-260915": { + "cache_read_input_token_cost": 1.725e-07, + "input_cost_per_token": 8.625e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 1024000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4.3125e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "volcengine/doubao-seed-2-1-lite-260915": { + "cache_read_input_audio_token_cost": 3.45e-07, + "cache_read_input_token_cost": 2.3e-08, + "input_cost_per_audio_token": 1.725e-06, + "input_cost_per_token": 1.15e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 1024000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 3.88126e-07, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, "volcengine/doubao-seed-2-1-turbo-260628": { "cache_read_input_token_cost": 8.625e-08, "input_cost_per_token": 4.3125e-07, @@ -58530,6 +61604,61 @@ } ] }, + "volcengine/doubao-seedance-2-5-260628": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.216, + "output_cost_per_second_480p": 0.096075, + "output_cost_per_second_720p": 0.216, + "output_cost_per_second_1080p": 0.5346, + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "854x480", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "480x854", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s). List 70 CNY per million tokens at 480p and 720p and 77 at 1080p without a video input, matching Ark's per-resolution table and its 1080p 16:9 example of 3.74 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Accepts up to 50 reference assets (30 images, 10 videos, 10 audios) and clips of 4-30s; per-asset billing beyond the free allowance is not encoded. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, + "volcengine/doubao-seedance-2-0-260128": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.141942857, + "output_cost_per_second_480p": 0.066003429, + "output_cost_per_second_720p": 0.141942857, + "output_cost_per_second_1080p": 0.354085714, + "output_cost_per_second_4k": 0.722057143, + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 46 CNY per million tokens at 480p and 720p, 51 at 1080p, and 26 at 4k without a video input, matching Ark's per-resolution table and its 1080p and 4k 16:9 examples of 2.48 and 5.05 CNY/s, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s; 4k is exclusive to this tier. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, + "volcengine/doubao-seedance-2-0-fast-260128": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.114171429, + "output_cost_per_second_480p": 0.053089714, + "output_cost_per_second_720p": 0.114171429, + "supported_modalities": ["text", "image", "video", "audio"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 37 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, + "volcengine/doubao-seedance-2-0-mini-260615": { + "litellm_provider": "volcengine", + "mode": "video_generation", + "source": "https://www.volcengine.com/docs/82379/1544106", + "output_cost_per_second": 0.070971429, + "output_cost_per_second_480p": 0.033001714, + "output_cost_per_second_720p": 0.070971429, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["video"], + "supported_endpoints": ["/v1/videos"], + "provider_specific_entry": {"volcengine_video_frames": {"480p": {"16:9": "864x496", "4:3": "752x560", "1:1": "640x640", "3:4": "560x752", "9:16": "496x864", "21:9": "992x432"}, "720p": {"16:9": "1280x720", "4:3": "1112x834", "1:1": "960x960", "3:4": "834x1112", "9:16": "720x1280", "21:9": "1470x630"}}}, + "metadata": {"comment": "Ark bills per output token, not per second: tokens = width * height * 24 * seconds / 1024, so a per-second rate per resolution tier is exact for the 16:9 geometry Ark publishes (1280x720 is 21600 tokens/s; the 480p frame is 864x496, 10044 tokens/s, not the tier's nominal 854x480). List 23 CNY per million tokens without a video input, converted at 7.0 CNY/USD like the other volcengine entries. Clips of 4-15s at 480p or 720p. Only text and image inputs are declared; the mini tier's reference video and audio caps were not verified. Requests with a video input bill at a lower rate per token and are rejected, since their cost is not known at create time. provider_specific_entry.volcengine_video_frames is the frame Ark renders per resolution tier and ratio, verified with ffprobe at 480p for every ratio and at 720p for 16:9 and 4:3; the other 720p ratios are from the Seedance 2.0 model card."} + }, "bedrock/us-east-1/zai.glm-5": { "input_cost_per_token": 1e-06, "output_cost_per_token": 3.2e-06, @@ -58590,7 +61719,11 @@ "supports_native_structured_output": true, "supports_pdf_input": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.5e-06, @@ -58616,7 +61749,11 @@ "supports_native_structured_output": true, "supports_pdf_input": true, "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "token_count_model": { + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "litellm_provider": "bedrock" + } }, "snowflake/claude-sonnet-4-5": { "max_tokens": 16384, @@ -59418,16 +62555,16 @@ }, "tencent/deepseek-v4-pro": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 3.625e-09, - "input_cost_per_token": 4.35e-07, - "input_cost_per_token_cache_hit": 3.625e-09, + "cache_read_input_token_cost": 1.45e-07, + "input_cost_per_token": 1.74e-06, + "input_cost_per_token_cache_hit": 1.45e-07, "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 8.7e-07, - "source": "https://www.tencentcloud.com/products/tokenhub", + "output_cost_per_token": 3.48e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], @@ -59453,7 +62590,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, - "source": "https://www.tencentcloud.com/products/tokenhub", + "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], @@ -59468,6 +62605,310 @@ "supports_reasoning": true, "supports_vision": false }, + "tencent/deepseek-v4-pro-0813": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 1.32e-06, + "input_cost_per_token_cache_hit": 4.4e-08, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 6.6e-07, + "output_cost_per_token": 1.98e-06, + "weekday_timezone": "Asia/Shanghai", + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 3.96e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false + }, + "tencent/deepseek-v4.1-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_cache_hit": 6e-09, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "off_peak_pricing": { + "cache_read_input_token_cost": 3e-09, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "weekday_timezone": "Asia/Shanghai", + "windows": [ + { + "hours_utc": [ + "00:00-01:00", + "04:00-06:00", + "10:00-00:00" + ], + "weekdays": [ + 1, + 2, + 3, + 4, + 5 + ] + }, + { + "hours_utc": "00:00-00:00", + "weekdays": [ + 6, + 7 + ] + } + ] + }, + "output_cost_per_token": 1.2e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": true + }, + "tencent/glm-5.3-flashx": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 3.7e-07, + "input_cost_per_token_cache_hit": 7.5e-08, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "tencent/glm-5.3-flash": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_cache_hit": 3e-08, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "tencent/glm-5.3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "input_cost_per_token_cache_hit": 2.6e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/glm-5.2": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "input_cost_per_token_cache_hit": 2.6e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_cache_hit": 3e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k2.8-preview": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1e-06, + "input_cost_per_token_cache_hit": 2.5e-07, + "litellm_provider": "tencent", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k2.7-code-highspeed": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 3.8e-07, + "input_cost_per_token": 1.9e-06, + "input_cost_per_token_cache_hit": 3.8e-07, + "litellm_provider": "tencent", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "tencent/kimi-k2.7-code": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.5e-07, + "input_cost_per_token_cache_hit": 1.9e-07, + "litellm_provider": "tencent", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.tencentcloud.com/document/product/1300/78937", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "tencent/minimax-m3": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 6e-08, @@ -59477,7 +62918,7 @@ "max_input_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://www.tencentcloud.com/products/tokenhub", + "source": "https://www.tencentcloud.com/document/product/1300/78937", "supported_endpoints": [ "/v1/chat/completions" ], @@ -59632,13 +63073,16 @@ }, "xai/grok-4.20-0309-non-reasoning": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -59646,20 +63090,26 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-multi-agent-0309": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": false, "supports_prompt_caching": true, @@ -59668,8 +63118,11 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true, "supported_endpoints": [ @@ -59901,6 +63354,9 @@ "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 1e-06, "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 5e-06, "search_context_cost_per_query": { @@ -59923,6 +63379,7 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, @@ -59950,6 +63407,7 @@ "supports_vision": true }, "mistral/labs-leanstral-1-5": { + "deprecation_date": "2026-09-30", "input_cost_per_token": 0.0, "litellm_provider": "mistral", "max_input_tokens": 262144, @@ -60095,8 +63553,8 @@ { "name": "claude-tool-search", "pattern": "claude-[a-z]+-(?:4[-._](?:[5-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)", - "fill_missing_for_providers": ["anthropic", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], - "description": "Claude at version 4.5 or higher, in any id shape that contains claude--: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is left out on purpose: Anthropic documents tool search as unavailable on Azure-hosted Foundry deployments, and the azure_ai/ key cannot tell those from Anthropic-hosted ones.", + "fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"], + "description": "Claude at version 4.5 or higher, in any id shape that contains claude--: minors 4.5 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic's tool search docs list every Claude 4.5 and newer model as supported and Opus 4.1 and earlier as unsupported, so the flag follows the version instead of a per-model list. azure_ai is included because Microsoft Foundry runs tool search for Claude on both Anthropic-hosted and Azure-hosted deployments.", "model_info": { "supports_tool_search": true } @@ -60170,6 +63628,9 @@ "input_cost_per_audio_token": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "gemini", + "max_input_tokens": 98304, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "audio_transcription", "output_cost_per_token": 1.2e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -60192,6 +63653,9 @@ "input_cost_per_audio_token": 3.5e-06, "input_cost_per_token": 3.5e-06, "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "audio_transcription", "output_cost_per_token": 2.1e-05, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -60248,7 +63712,7 @@ }, "vertex_ai/gemini-3.5-live-translate-preview": { "input_cost_per_audio_token": 3.5e-06, - "input_cost_per_second": 8.83333333333e-05, + "input_cost_per_second": 8.75e-05, "input_cost_per_token": 3.5e-06, "litellm_provider": "vertex_ai", "mode": "realtime", @@ -60370,18 +63834,18 @@ "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": { - "cache_read_input_token_cost": 7e-09, - "cache_read_input_token_cost_priority": 8.75e-09, - "input_cost_per_token": 2.2e-07, - "input_cost_per_token_priority": 2.75e-07, + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 6.6e-07, - "output_cost_per_token_priority": 8.25e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -60391,13 +63855,16 @@ }, "fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-us": { "cache_read_input_token_cost": 9e-09, + "cache_read_input_token_cost_priority": 1.125e-08, "input_cost_per_token": 4.5e-07, + "input_cost_per_token_priority": 5.625e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.8e-06, + "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -60408,13 +63875,16 @@ }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp": { "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, "deprecation_date": "2026-09-25", "input_cost_per_token": 2.2e-07, + "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, + "output_cost_per_token_priority": 8.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, @@ -60466,18 +63936,18 @@ "supports_vision": false }, "fireworks_ai/deepseek-v4p1-flash": { - "cache_read_input_token_cost": 7e-09, - "cache_read_input_token_cost_priority": 8.75e-09, - "input_cost_per_token": 2.2e-07, - "input_cost_per_token_priority": 2.75e-07, + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 6.6e-07, - "output_cost_per_token_priority": 8.25e-07, - "source": "https://api.fireworks.ai/v1/serverless/models", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -60487,13 +63957,16 @@ }, "fireworks_ai/deepseek-v4p1-flash-us": { "cache_read_input_token_cost": 9e-09, + "cache_read_input_token_cost_priority": 1.125e-08, "input_cost_per_token": 4.5e-07, + "input_cost_per_token_priority": 5.625e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.8e-06, + "output_cost_per_token_priority": 2.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_prompt_caching": true, @@ -60504,13 +63977,16 @@ }, "fireworks_ai/deepseek-v4-flash-vision-exp": { "cache_read_input_token_cost": 7e-09, + "cache_read_input_token_cost_priority": 8.75e-09, "deprecation_date": "2026-09-25", "input_cost_per_token": 2.2e-07, + "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, + "output_cost_per_token_priority": 8.25e-07, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, @@ -60639,14 +64115,17 @@ }, "fireworks_ai/muse-glimmer-30b": { "cache_read_input_token_cost": 4e-08, + "cache_read_input_token_cost_priority": 6e-08, "deprecation_date": "2026-09-25", "input_cost_per_token": 3.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, + "output_cost_per_token_priority": 2.25e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, @@ -60656,14 +64135,18 @@ }, "fireworks_ai/nemotron-lightning-3p5-30b-a3b": { "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_priority": 1.25e-08, + "deprecation_date": "2026-11-07", "input_cost_per_token": 5e-08, + "input_cost_per_token_priority": 6.25e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 2.5e-07, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60672,14 +64155,18 @@ }, "fireworks_ai/nemotron-3-ultra-nvfp4": { "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_priority": 1.5e-07, + "deprecation_date": "2026-11-07", "input_cost_per_token": 6e-07, + "input_cost_per_token_priority": 7.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "output_cost_per_token_priority": 3e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60688,14 +64175,17 @@ }, "fireworks_ai/accounts/fireworks/models/muse-glimmer-30b": { "cache_read_input_token_cost": 4e-08, + "cache_read_input_token_cost_priority": 6e-08, "deprecation_date": "2026-09-25", "input_cost_per_token": 3.5e-07, + "input_cost_per_token_priority": 5.25e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, + "output_cost_per_token_priority": 2.25e-06, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, @@ -60703,16 +64193,31 @@ "supports_tool_choice": true, "supports_vision": true }, + "fireworks_ai/accounts/fireworks/models/muse-spark-open": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.25e-06, + "source": "https://fireworks.ai/models/fireworks/muse-spark-open", + "supports_function_calling": true, + "supports_vision": true + }, "fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b": { "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_priority": 1.25e-08, + "deprecation_date": "2026-11-07", "input_cost_per_token": 5e-08, + "input_cost_per_token_priority": 6.25e-08, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token_priority": 2.5e-07, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -60721,14 +64226,18 @@ }, "fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4": { "cache_read_input_token_cost": 1.2e-07, + "cache_read_input_token_cost_priority": 1.5e-07, + "deprecation_date": "2026-11-07", "input_cost_per_token": 6e-07, + "input_cost_per_token_priority": 7.5e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, - "source": "https://api.fireworks.ai/v1/serverless/models", + "output_cost_per_token_priority": 3e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -62352,6 +65861,7 @@ "supports_tool_choice": true, "supports_response_schema": true, "supports_reasoning": true, + "supports_sampling_params": false, "supports_vision": true, "source": "https://deepinfra.com/pricing", "supports_audio_input": true @@ -62836,6 +66346,40 @@ "supports_vision": false, "source": "https://deepinfra.com/pricing" }, + "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash": { + "max_tokens": 131072, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4.2e-07, + "cache_read_input_token_cost": 4.2e-09, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash" + }, + "deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "max_tokens": 131072, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 4.2e-07, + "cache_read_input_token_cost": 4.2e-09, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash-1017" + }, "deepinfra/openai/gpt-oss-120b-Ultra": { "max_tokens": 131072, "max_input_tokens": 131072, @@ -62944,13 +66488,16 @@ }, "xai/grok-4.20": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, @@ -62958,21 +66505,27 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-reasoning": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, @@ -62980,21 +66533,27 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true }, "xai/grok-4.20-reasoning-latest": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, @@ -63002,8 +66561,11 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true @@ -63158,6 +66720,23 @@ "video" ] }, + "xai/grok-imagine-video-1.5-lite": { + "input_cost_per_image": 0.01, + "litellm_provider": "xai", + "mode": "video_generation", + "output_cost_per_second": 0.02, + "output_cost_per_second_1080p": 0.14, + "output_cost_per_second_480p": 0.02, + "output_cost_per_second_720p": 0.03, + "source": "https://docs.x.ai/developers/pricing", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "video" + ] + }, "xai/grok-imagine-video-1.5-2026-05-30": { "input_cost_per_image": 0.01, "litellm_provider": "xai", @@ -63195,6 +66774,7 @@ ] }, "xai/grok-voice-transcribe-1.0": { + "deprecation_date": "2026-10-02", "input_cost_per_second": 2.778e-05, "litellm_provider": "xai", "metadata": { @@ -63240,13 +66820,16 @@ }, "xai/grok-4.20-non-reasoning": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -63254,20 +66837,26 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-non-reasoning-latest": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_prompt_caching": true, @@ -63275,20 +66864,26 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-multi-agent": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supported_endpoints": [ "/v1/responses" @@ -63300,20 +66895,26 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "xai/grok-4.20-multi-agent-latest": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supported_endpoints": [ "/v1/responses" @@ -63325,15 +66926,18 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_response_schema": true }, "groq/qwen/qwen3.8-27b": { "input_cost_per_token": 8e-07, "litellm_provider": "groq", - "max_input_tokens": 131042, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -63595,13 +67199,16 @@ }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-us": { "cache_read_input_token_cost": 3.9e-07, + "cache_read_input_token_cost_priority": 4.875e-07, "input_cost_per_token": 2.1e-06, + "input_cost_per_token_priority": 2.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.6e-06, + "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_reasoning": true, @@ -63630,13 +67237,16 @@ }, "fireworks_ai/glm-5p3-us": { "cache_read_input_token_cost": 3.9e-07, + "cache_read_input_token_cost_priority": 4.875e-07, "input_cost_per_token": 2.1e-06, + "input_cost_per_token_priority": 2.625e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.6e-06, + "output_cost_per_token_priority": 8.25e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_reasoning": true, @@ -63659,6 +67269,33 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/auto": { + "litellm_provider": "fireworks_ai", + "mode": "chat", + "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/routers/auto-instant": { + "litellm_provider": "fireworks_ai", + "mode": "chat", + "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/routers/firerouter": { + "litellm_provider": "fireworks_ai", + "mode": "chat", + "source": "https://docs.fireworks.ai/nexus/firerouter#example-router-ids", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "fireworks_ai/glm-5p3-fast": { "cache_read_input_token_cost": 3.9e-07, "input_cost_per_token": 2.1e-06, @@ -63693,12 +67330,16 @@ }, "fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us": { "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_priority": 5.625e-08, + "deprecation_date": "2026-11-07", "input_cost_per_token": 2.25e-07, + "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, + "output_cost_per_token_priority": 9.375e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_response_schema": true, @@ -63724,12 +67365,16 @@ }, "fireworks_ai/glm-5p3-flash-us": { "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_priority": 5.625e-08, + "deprecation_date": "2026-11-07", "input_cost_per_token": 2.25e-07, + "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, + "output_cost_per_token_priority": 9.375e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_response_schema": true, @@ -63738,13 +67383,17 @@ }, "fireworks_ai/accounts/fireworks/models/inkling": { "cache_read_input_token_cost": 1.7e-07, + "cache_read_input_token_cost_priority": 1.7e-07, + "deprecation_date": "2026-11-07", "input_cost_per_token": 1e-06, + "input_cost_per_token_priority": 1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.05e-06, - "source": "https://fireworks.ai/models/fireworks/inkling", + "output_cost_per_token_priority": 4.05e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -63776,12 +67425,12 @@ "supports_tool_choice": true }, "together_ai/Qwen/Qwen3.8-Flash": { - "input_cost_per_token": 9e-08, + "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", - "output_cost_per_token": 2.82e-07, + "output_cost_per_token": 4.7e-07, "source": "https://api.together.ai/v1/models" }, "together_ai/moonshotai/Kimi-K2.5-fp4": { @@ -63818,6 +67467,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { + "deprecation_date": "2026-02-25", "input_cost_per_token": 6e-08, "output_cost_per_token": 2.5e-07, "litellm_provider": "together_ai", @@ -63889,7 +67539,7 @@ }, "azure_ai/kimi-k2.7-code": { "cache_read_input_token_cost": 1.9e-07, - "deprecation_date": "2026-10-03", + "deprecation_date": "2027-04-16", "input_cost_per_token": 9.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, @@ -63912,52 +67562,26 @@ "supports_vision": true }, "azure_ai/deepseek-v4.1-flash": { - "cache_read_input_token_cost": 8e-09, - "input_cost_per_token": 3.75e-07, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 1.5e-06, + "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "deprecation_date": "2026-12-15", - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" - }, - "azure_ai/muse-spark-1.3": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 4.25e-06, - "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/deepseek-v4-1-flash-is-coming-to-microsoft-foundry/4556431" }, "azure_ai/MAI-Image-2.6": { "input_cost_per_image_token": 8e-06, "input_cost_per_token": 5e-06, "litellm_provider": "azure_ai", + "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image_token": 3.8e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -63970,6 +67594,7 @@ "input_cost_per_image_token": 2.5e-06, "input_cost_per_token": 1.75e-06, "litellm_provider": "azure_ai", + "max_input_tokens": 32000, "mode": "image_generation", "output_cost_per_image_token": 1.9e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -64090,6 +67715,7 @@ "supports_vision": true }, "azure_ai/deepseek-r1": { + "deprecation_date": "2026-08-13", "input_cost_per_token": 1.35e-06, "output_cost_per_token": 5.4e-06, "litellm_provider": "azure_ai", @@ -64097,6 +67723,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure_ai/deepseek-v3-0324": { + "deprecation_date": "2026-07-13", "input_cost_per_token": 1.14e-06, "output_cost_per_token": 4.56e-06, "litellm_provider": "azure_ai", @@ -64104,6 +67731,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure_ai/deepseek-v3.1": { + "deprecation_date": "2026-07-13", "input_cost_per_token": 1.23e-06, "output_cost_per_token": 4.94e-06, "litellm_provider": "azure_ai", @@ -64111,6 +67739,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure_ai/grok-3": { + "deprecation_date": "2026-05-01", "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "litellm_provider": "azure_ai", @@ -64118,6 +67747,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure_ai/grok-3-mini": { + "deprecation_date": "2026-05-01", "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.27e-06, "litellm_provider": "azure_ai", @@ -64125,6 +67755,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure_ai/grok-4-fast-non-reasoning": { + "deprecation_date": "2026-05-01", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", @@ -64132,6 +67763,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure_ai/grok-4-fast-reasoning": { + "deprecation_date": "2026-05-01", "input_cost_per_token": 2e-07, "output_cost_per_token": 5e-07, "litellm_provider": "azure_ai", @@ -64156,6 +67788,7 @@ "supports_vision": false }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.4e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -64163,6 +67796,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, @@ -64170,6 +67804,7 @@ "supports_response_schema": true }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-9b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -64177,6 +67812,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, @@ -64204,10 +67840,16 @@ "input_cost_per_token": 8.4e-08, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64217,10 +67859,16 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64248,6 +67896,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64257,7 +67906,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -64281,6 +67935,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64290,7 +67945,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -64322,7 +67982,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -64357,7 +68022,12 @@ "supports_xhigh_reasoning_effort": true, "thinking_always_on": true, "supports_forced_tool_use": false, - "source": "https://aws.amazon.com/bedrock/pricing/" + "source": "https://aws.amazon.com/bedrock/pricing/", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-west-1/anthropic.claude-fable-5-1": { "cache_creation_input_token_cost": 1.5e-05, @@ -64390,7 +68060,12 @@ "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "token_count_model": { + "model": "anthropic.claude-fable-5-1", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, @@ -64410,6 +68085,7 @@ "supports_vision": false }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 2.4e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -64417,6 +68093,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-12b-v2-vl-bf16.html", "supports_system_messages": true, "supports_vision": true, "supports_audio_input": false, @@ -64424,6 +68101,7 @@ "supports_response_schema": true }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-9b-v2": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock", "max_input_tokens": 128000, @@ -64431,6 +68109,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.76e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nvidia-nemotron-nano-9b-v2.html", "supports_system_messages": true, "supports_audio_input": false, "supports_function_calling": true, @@ -64458,10 +68137,16 @@ "input_cost_per_token": 8.4e-08, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64471,10 +68156,16 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.2e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_inline_reasoning": true, "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -64502,6 +68193,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64535,6 +68227,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -64672,14 +68365,15 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "input_cost_per_token": 2.64e-06, - "input_cost_per_token_above_272k_tokens": 5.28e-06, - "cache_creation_input_token_cost": 3.3e-06, - "cache_creation_input_token_cost_above_272k_tokens": 6.6e-06, - "cache_read_input_token_cost": 2.64e-07, - "cache_read_input_token_cost_above_272k_tokens": 5.28e-07, - "output_cost_per_token": 1.584e-05, - "output_cost_per_token_above_272k_tokens": 2.376e-05 + "input_cost_per_token": 2.7e-06, + "input_cost_per_token_above_272k_tokens": 5.4e-06, + "cache_creation_input_token_cost": 3.375e-06, + "cache_creation_input_token_cost_above_272k_tokens": 6.75e-06, + "cache_read_input_token_cost": 2.7e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.4e-07, + "output_cost_per_token": 1.62e-05, + "output_cost_per_token_above_272k_tokens": 2.43e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html" }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna": { "litellm_provider": "bedrock_mantle", @@ -64707,14 +68401,15 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "input_cost_per_token": 2.64e-07, - "input_cost_per_token_above_272k_tokens": 5.28e-07, - "cache_creation_input_token_cost": 3.3e-07, - "cache_creation_input_token_cost_above_272k_tokens": 6.6e-07, - "cache_read_input_token_cost": 2.64e-08, - "cache_read_input_token_cost_above_272k_tokens": 5.28e-08, - "output_cost_per_token": 1.584e-06, - "output_cost_per_token_above_272k_tokens": 2.376e-06 + "input_cost_per_token": 2.7e-07, + "input_cost_per_token_above_272k_tokens": 5.4e-07, + "cache_creation_input_token_cost": 3.375e-07, + "cache_creation_input_token_cost_above_272k_tokens": 6.75e-07, + "cache_read_input_token_cost": 2.7e-08, + "cache_read_input_token_cost_above_272k_tokens": 5.4e-08, + "output_cost_per_token": 1.62e-06, + "output_cost_per_token_above_272k_tokens": 2.43e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html" }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.4": { "litellm_provider": "bedrock_mantle", @@ -64741,9 +68436,10 @@ "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_vision": true, - "input_cost_per_token": 3.3e-06, - "cache_read_input_token_cost": 3.3e-07, - "output_cost_per_token": 1.98e-05 + "input_cost_per_token": 3.375e-06, + "cache_read_input_token_cost": 3.375e-07, + "output_cost_per_token": 2.025e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html" }, "bedrock_mantle/us-gov-west-1/xai.grok-4.3": { "use_openai_responses_path": true, @@ -64849,9 +68545,10 @@ "output_cost_per_token": 3.6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -64867,9 +68564,10 @@ "output_cost_per_token": 7.2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -64880,6 +68578,77 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "bedrock_mantle/us-gov-west-1/anthropic.claude-opus-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 6e-06, + "cache_creation_input_token_cost_above_1hr": 9.6e-06, + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 4.8e-06, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true, + "supports_forced_tool_use": false, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html" + }, + "bedrock_mantle/us-gov-west-1/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock_mantle", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, "bedrock_mantle/us-gov-east-1/openai.gpt-5.4": { "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, @@ -64935,9 +68704,10 @@ "output_cost_per_token": 3.6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -64953,9 +68723,10 @@ "output_cost_per_token": 7.2e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -64967,91 +68738,131 @@ "supports_tool_choice": true }, "bedrock_mantle/deepseek.v3.1": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 5.8e-07, + "input_cost_per_token_batches": 2.9e-07, + "input_cost_per_token_flex": 2.9e-07, + "input_cost_per_token_priority": 1.015e-06, "output_cost_per_token": 1.68e-06, + "output_cost_per_token_flex": 8.4e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 8.4e-07, + "output_cost_per_token_priority": 2.94e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/moonshotai.kimi-k2-thinking": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, + "input_cost_per_token_flex": 3e-07, + "input_cost_per_token_priority": 1.05e-06, "output_cost_per_token": 2.5e-06, + "output_cost_per_token_flex": 1.25e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_priority": 4.38e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-235b-a22b-2507": { "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "input_cost_per_token_flex": 1.1e-07, + "input_cost_per_token_priority": 3.85e-07, "output_cost_per_token": 8.8e-07, + "output_cost_per_token_flex": 4.4e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 4.4e-07, + "output_cost_per_token_priority": 1.54e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-32b": { "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, + "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 32000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-32b.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_flex": 7.5e-08, + "input_cost_per_token_priority": 2.625e-07, "output_cost_per_token": 6e-07, + "output_cost_per_token_flex": 3e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1.05e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-30b-a3b-instruct.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 4.5e-07, + "input_cost_per_token_batches": 2.25e-07, + "input_cost_per_token_flex": 2.25e-07, + "input_cost_per_token_priority": 7.875e-07, "output_cost_per_token": 1.8e-06, + "output_cost_per_token_flex": 9e-07, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 128000, + "max_input_tokens": 262144, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token_batches": 9e-07, + "output_cost_per_token_priority": 3.15e-06, "supported_endpoints": [ "/v1/chat/completions" ], @@ -65061,35 +68872,47 @@ }, "bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct": { "input_cost_per_token": 1.4e-07, + "input_cost_per_token_batches": 7e-08, + "input_cost_per_token_flex": 7e-08, + "input_cost_per_token_priority": 2.6e-07, "output_cost_per_token": 1.2e-06, + "output_cost_per_token_flex": 6e-07, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 6e-07, + "output_cost_per_token_priority": 2.1e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct": { "input_cost_per_token": 5.3e-07, + "input_cost_per_token_batches": 2.6e-07, + "input_cost_per_token_flex": 2.6e-07, + "input_cost_per_token_priority": 9.3e-07, "output_cost_per_token": 2.66e-06, + "output_cost_per_token_flex": 1.33e-06, "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "mode": "chat", + "output_cost_per_token_batches": 1.33e-06, + "output_cost_per_token_priority": 4.66e-06, "supported_endpoints": [ "/v1/chat/completions" ], "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-vl-235b-a22b.html" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json" }, "azure/us-gov/gpt-5.1": { "cache_read_input_token_cost": 1.71875e-07, @@ -65232,7 +69055,7 @@ "gemini/lyria-3.5": { "input_cost_per_token": 0, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", @@ -65340,12 +69163,12 @@ "mode": "responses", "supports_web_search": true, "supports_function_calling": true, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 3e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token_above_272k_tokens": 1e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token_above_272k_tokens": 8e-06, + "output_cost_per_token_above_272k_tokens": 3e-05, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-5.6-terra": { @@ -65428,6 +69251,22 @@ "cache_read_input_token_cost": 1.25e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, + "perplexity/openai/gpt-5-nano": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 5e-09, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-5.3-codex": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 3.5e-06, + "output_cost_per_token": 2.8e-05, + "cache_read_input_token_cost": 3.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/google/gemini-3.1-pro-preview": { "litellm_provider": "perplexity", "mode": "responses", @@ -65464,6 +69303,7 @@ "perplexity/google/gemini-3.5-flash-lite": { "litellm_provider": "perplexity", "mode": "responses", + "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 3e-07, @@ -65474,6 +69314,7 @@ "perplexity/google/gemini-3.6-flash": { "litellm_provider": "perplexity", "mode": "responses", + "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 1.5e-06, @@ -65484,6 +69325,7 @@ "perplexity/google/gemini-3.7-flash": { "litellm_provider": "perplexity", "mode": "responses", + "supports_sampling_params": false, "supports_web_search": true, "supports_function_calling": true, "input_cost_per_token": 7.5e-07, @@ -65607,675 +69449,6 @@ "cache_read_input_token_cost": 2.5e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, - "openrouter/anthropic/claude-fable-5": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 1e-06, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_1hr": 2e-05, - "prompt_cache_min_tokens": 512, - "supports_web_search": true - }, - "openrouter/anthropic/claude-fable-5.1": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "thinking_always_on": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2.5e-07, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_1hr": 2e-05, - "prompt_cache_min_tokens": 512, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.8": { - "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-07, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-5": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "supports_sampling_params": false, - "supports_adaptive_thinking": true, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "supports_web_search": true - }, - "openrouter/google/gemini-2.5-flash-lite": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 3e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 1e-08, - "deprecation_date": "2026-10-20", - "input_cost_per_audio_token": 3e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.5-flash": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 3e-07, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 9e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_audio_token": 3e-06, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.5-flash-lite": { - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 3e-08, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 3e-08, - "input_cost_per_audio_token": 3e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.6-flash": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 3.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 7.5e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.7-flash": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 3.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 7.5e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.8-flash": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 3.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 7.5e-07, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/openai/gpt-4o-mini": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.1": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 1.25e-07, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.3-codex": { - "input_cost_per_token": 1.75e-06, - "output_cost_per_token": 1.4e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 1.75e-07, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4": { - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 5e-07, - "input_cost_per_token_above_272k_tokens": 5e-06, - "output_cost_per_token_above_272k_tokens": 2.25e-05, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4-mini": { - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 4.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4-nano": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-08, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.5": { - "input_cost_per_token": 5e-06, - "output_cost_per_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-luna": { - "cache_creation_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost_above_272k_tokens": 5e-07, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-08, - "cache_read_input_token_cost_above_272k_tokens": 4e-08, - "input_cost_per_token_above_272k_tokens": 4e-07, - "output_cost_per_token_above_272k_tokens": 1.8e-06, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-luna-pro": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 2e-08, - "cache_creation_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost_above_272k_tokens": 5e-07, - "input_cost_per_token_above_272k_tokens": 4e-07, - "output_cost_per_token_above_272k_tokens": 1.8e-06, - "cache_read_input_token_cost_above_272k_tokens": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-terra": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token_above_272k_tokens": 4e-06, - "output_cost_per_token_above_272k_tokens": 1.8e-05, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-terra-pro": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "output_cost_per_token_above_272k_tokens": 1.8e-05, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/o3": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-07, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/o4-mini": { - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2.75e-07, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/x-ai/grok-4.20": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_output_tokens": 1800000, - "max_tokens": 1800000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/x-ai/grok-4.20-multi-agent": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 2000000, - "max_output_tokens": 1800000, - "max_tokens": 1800000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/x-ai/grok-4.3": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 900000, - "max_tokens": 900000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 5e-06, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/x-ai/grok-4.5": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "input_cost_per_token_above_200k_tokens": 4e-06, - "output_cost_per_token_above_200k_tokens": 1.2e-05, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/x-ai/grok-4.6": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "output_cost_per_token_above_200k_tokens": 1.2e-05, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/x-ai/grok-build-0.1": { - "input_cost_per_token": 1e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 230400, - "max_tokens": 230400, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": false, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_token_above_200k_tokens": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "supports_prompt_caching": true, - "supports_web_search": true - }, "baseten/zai-org/GLM-5.3": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, @@ -66324,2794 +69497,21 @@ "supports_tool_choice": true, "supports_vision": true }, - "openrouter/minimax/minimax-m3": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 512000, - "max_tokens": 512000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "cache_read_input_token_cost": 6e-08, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.7-plus": { - "input_cost_per_token": 3.2e-07, - "input_cost_per_token_above_256k_tokens": 9.6e-07, - "cache_creation_input_token_cost_above_256k_tokens": 1.2e-06, - "cache_read_input_token_cost_above_256k_tokens": 1.92e-07, - "output_cost_per_token_above_256k_tokens": 3.84e-06, - "output_cost_per_token": 1.28e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "cache_read_input_token_cost": 6.4e-08, - "supports_prompt_caching": true, - "cache_creation_input_token_cost": 4e-07, - "supports_audio_input": false, - "supports_pdf_input": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-6-astra": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "cache_read_input_token_cost": 1e-06, - "cache_creation_input_token_cost": 1.25e-05, - "input_cost_per_token_above_272k_tokens": 2e-05, - "output_cost_per_token_above_272k_tokens": 7.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 2e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-astra-pro": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, - "cache_read_input_token_cost": 1e-06, - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, - "input_cost_per_token_above_272k_tokens": 2e-05, - "output_cost_per_token_above_272k_tokens": 7.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/qwen/qwen3.8-flash": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 4.7e-07, - "cache_read_input_token_cost": 1.6e-08, - "cache_creation_input_token_cost": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.3-flash": { - "input_cost_per_token": 4.5e-08, - "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 2.85e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v4-flash-vision-exp": { - "input_cost_per_token": 2.2e-07, - "output_cost_per_token": 6.6e-07, - "cache_read_input_token_cost": 7e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.3": { - "input_cost_per_token": 1.4e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943717, - "max_tokens": 943717, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.8-27b": { - "input_cost_per_token": 4.2e-07, - "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 8.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.8-2.4t-a95b": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3.5-lightning:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.8-max": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/qwen/qwen3.8-max", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true - }, - "openrouter/qwen/qwen3.8-max-0902": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.8-max-prime": { - "input_cost_per_token": 4e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_video_input": true, - "supports_prompt_caching": true - }, - "openrouter/deepseek/deepseek-v4-flash-0731": { - "input_cost_per_token": 3e-08, - "output_cost_per_token": 3.2e-07, - "cache_read_input_token_cost": 1.6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.7-flash": { - "input_cost_per_token": 3e-08, - "input_cost_per_token_above_32k_tokens": 1e-07, - "cache_creation_input_token_cost_above_32k_tokens": 1.25e-07, - "cache_read_input_token_cost_above_32k_tokens": 2e-08, - "output_cost_per_token_above_32k_tokens": 4e-07, - "output_cost_per_token": 1.3e-07, - "cache_read_input_token_cost": 6e-09, - "cache_creation_input_token_cost": 3.8e-08, - "input_cost_per_token_above_256k_tokens": 2e-07, - "output_cost_per_token_above_256k_tokens": 8e-07, - "cache_read_input_token_cost_above_256k_tokens": 4e-08, - "cache_creation_input_token_cost_above_256k_tokens": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/poolside/laguna-s-2.1": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 1.8e-07, - "cache_read_input_token_cost": 9e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_web_search": false - }, - "openrouter/poolside/laguna-s-2.1:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k3": { - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/poolside/laguna-xs-2.1": { - "input_cost_per_token": 6e-08, - "output_cost_per_token": 1.2e-07, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_web_search": false - }, - "openrouter/poolside/laguna-xs-2.1:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/google/gemini-3.1-flash-lite-image": { - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.5e-06, - "output_cost_per_image_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 58982, - "max_tokens": 58982, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/google/gemini-3.1-flash-image": { - "input_cost_per_token": 5e-07, - "output_cost_per_token": 3e-06, - "output_cost_per_image_token": 6e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/google/gemini-3-pro-image": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 2e-07, - "input_cost_per_audio_token": 2e-06, - "output_cost_per_image_token": 0.00012, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/z-ai/glm-5.2": { - "input_cost_per_token": 6.496e-07, - "output_cost_per_token": 2.0416e-06, - "cache_read_input_token_cost": 1.2064e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.2:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k2.7-code": { - "input_cost_per_token": 6.562e-07, - "output_cost_per_token": 3.3e-06, - "cache_read_input_token_cost": 1.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3.5-content-safety": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3.5-content-safety:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3-ultra-550b-a55b": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.4e-06, - "cache_read_input_token_cost": 1.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 182520, - "max_tokens": 182520, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m3:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m3:free", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true - }, - "openrouter/qwen/qwen3.7-max": { - "input_cost_per_token": 1.475e-06, - "output_cost_per_token": 4.425e-06, - "cache_read_input_token_cost": 2.95e-07, - "cache_creation_input_token_cost": 1.84375e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-medium-3-5": { - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 7.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_response_schema": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-plus-20260420": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.8e-06, - "cache_creation_input_token_cost": 3.75e-07, - "input_cost_per_token_above_256k_tokens": 3.75e-07, - "output_cost_per_token_above_256k_tokens": 2.25e-06, - "cache_creation_input_token_cost_above_256k_tokens": 4.6875e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.6-flash": { - "input_cost_per_token": 1.875e-07, - "output_cost_per_token": 1.125e-06, - "cache_creation_input_token_cost": 2.34375e-07, - "input_cost_per_token_above_256k_tokens": 7.5e-07, - "output_cost_per_token_above_256k_tokens": 3e-06, - "cache_creation_input_token_cost_above_256k_tokens": 9.375e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.6-35b-a3b": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1e-06, - "cache_read_input_token_cost": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.6-max-preview": { - "input_cost_per_token": 1.027e-06, - "output_cost_per_token": 6.162e-06, - "cache_creation_input_token_cost": 1.28375e-06, - "input_cost_per_token_above_128k_tokens": 1.58e-06, - "output_cost_per_token_above_128k_tokens": 9.48e-06, - "cache_creation_input_token_cost_above_128k_tokens": 1.975e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.6-27b": { - "input_cost_per_token": 3.2e-07, - "output_cost_per_token": 2.7e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 262140, - "max_tokens": 262140, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/openai/gpt-5.5-pro": { - "input_cost_per_token": 3e-05, - "output_cost_per_token": 0.00018, - "input_cost_per_token_above_272k_tokens": 6e-05, - "output_cost_per_token_above_272k_tokens": 0.00027, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": true - }, - "openrouter/openai/gpt-chat-latest": { - "input_cost_per_token": 5e-06, - "output_cost_per_token": 3e-05, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/deepseek/deepseek-v4-flash": { - "input_cost_per_token": 4.9e-08, - "output_cost_per_token": 9.8e-08, - "cache_read_input_token_cost": 9.8e-09, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k2.6": { - "input_cost_per_token": 9.5e-07, - "output_cost_per_token": 4e-06, - "cache_read_input_token_cost": 1.6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/google/gemma-4-26b-a4b-it": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 9e-08, - "output_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/google/gemma-4-26b-a4b-it:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/google/gemma-4-31b-it": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 3.4e-07, - "cache_read_input_token_cost": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/google/gemma-4-31b-it:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5v-turbo": { - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 4e-06, - "cache_read_input_token_cost": 2.4e-07, - "deprecation_date": "2098-12-31", - "litellm_provider": "openrouter", - "max_input_tokens": 202752, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m2.7": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m2.7:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 196608, - "max_output_tokens": 176947, - "max_tokens": 176947, - "mode": "chat", - "source": "https://openrouter.ai/minimax/minimax-m2.7:free", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false - }, - "openrouter/mistralai/mistral-small-2603": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 1.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5-turbo": { - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 4e-06, - "cache_read_input_token_cost": 2.4e-07, - "deprecation_date": "2098-12-31", - "litellm_provider": "openrouter", - "max_input_tokens": 202752, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3-super-120b-a12b": { - "input_cost_per_token": 8e-08, - "output_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3-super-120b-a12b:free": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.5-9b": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/openai/gpt-5.4-pro": { - "input_cost_per_token": 3e-05, - "output_cost_per_token": 0.00018, - "input_cost_per_token_above_272k_tokens": 6e-05, - "output_cost_per_token_above_272k_tokens": 0.00027, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": true - }, - "openrouter/google/gemini-3.1-flash-image-preview": { - "input_cost_per_token": 5e-07, - "output_cost_per_token": 3e-06, - "output_cost_per_image_token": 6e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 58982, - "max_tokens": 58982, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/google/gemini-3.1-pro-preview-customtools": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 2e-07, - "input_cost_per_audio_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/qwen/qwen3-max-thinking": { - "input_cost_per_token": 7.8e-07, - "input_cost_per_token_above_32k_tokens": 1.56e-06, - "output_cost_per_token_above_32k_tokens": 7.8e-06, - "output_cost_per_token": 3.9e-06, - "input_cost_per_token_above_128k_tokens": 1.95e-06, - "output_cost_per_token_above_128k_tokens": 9.75e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-coder-next": { - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 8e-07, - "cache_read_input_token_cost": 7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m2-her": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-audio": { - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "input_cost_per_audio_token": 3.2e-05, - "output_cost_per_audio_token": 6.4e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_audio_input": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-audio-mini": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.4e-06, - "input_cost_per_audio_token": 6e-07, - "output_cost_per_audio_token": 2.4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_audio_input": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/nvidia/nemotron-3-nano-30b-a3b": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2e-07, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.6v": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 9e-07, - "cache_read_input_token_cost": 5.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/google/gemini-3-pro-image-preview": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 2e-07, - "input_cost_per_audio_token": 2e-06, - "output_cost_per_image_token": 0.00012, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.1-codex": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.1-codex-mini": { - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/moonshotai/kimi-k2-thinking": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.5e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/mistralai/voxtral-small-24b-2507": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 0.0001, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 26214, - "max_tokens": 26214, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-oss-safeguard-20b": { - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, - "cache_read_input_token_cost": 3.75e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-vl-32b-instruct": { - "input_cost_per_token": 1.04e-07, - "output_cost_per_token": 4.16e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-vl-8b-thinking": { - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 2.1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-vl-8b-instruct": { - "input_cost_per_token": 1.17e-07, - "output_cost_per_token": 4.55e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/google/gemini-2.5-flash-image": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 8.33333333333333e-08, - "cache_read_input_audio_token_cost": 1e-07, - "deprecation_date": "2027-03-15", - "input_cost_per_audio_token": 1e-06, - "output_cost_per_image_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": true - }, - "openrouter/qwen/qwen3-vl-30b-a3b-thinking": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-vl-30b-a3b-instruct": { - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 5.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/openai/gpt-5-pro": { - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 0.00012, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": true - }, - "openrouter/qwen/qwen3-vl-235b-a22b-thinking": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-vl-235b-a22b-instruct": { - "input_cost_per_token": 2.1e-07, - "output_cost_per_token": 1.9e-06, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-max": { - "input_cost_per_token": 7.8e-07, - "input_cost_per_token_above_32k_tokens": 1.56e-06, - "cache_creation_input_token_cost_above_32k_tokens": 1.95e-06, - "cache_read_input_token_cost_above_32k_tokens": 3.12e-07, - "output_cost_per_token_above_32k_tokens": 7.8e-06, - "output_cost_per_token": 3.9e-06, - "cache_read_input_token_cost": 1.56e-07, - "cache_creation_input_token_cost": 9.75e-07, - "input_cost_per_token_above_128k_tokens": 1.95e-06, - "output_cost_per_token_above_128k_tokens": 9.75e-06, - "cache_read_input_token_cost_above_128k_tokens": 3.9e-07, - "cache_creation_input_token_cost_above_128k_tokens": 2.4375e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v3.1-terminus": { - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 1e-06, - "cache_read_input_token_cost": 1.35e-07, - "deprecation_date": "2026-09-28", - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-coder-flash": { - "input_cost_per_token": 1.95e-07, - "input_cost_per_token_above_32k_tokens": 3.25e-07, - "cache_creation_input_token_cost_above_32k_tokens": 4.0625e-07, - "cache_read_input_token_cost_above_32k_tokens": 6.5e-08, - "output_cost_per_token_above_32k_tokens": 1.625e-06, - "output_cost_per_token": 9.75e-07, - "cache_read_input_token_cost": 3.9e-08, - "cache_creation_input_token_cost": 2.4375e-07, - "input_cost_per_token_above_128k_tokens": 5.2e-07, - "output_cost_per_token_above_128k_tokens": 2.6e-06, - "cache_read_input_token_cost_above_128k_tokens": 1.04e-07, - "cache_creation_input_token_cost_above_128k_tokens": 6.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-next-80b-a3b-thinking": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-next-80b-a3b-instruct": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1.1e-06, - "cache_read_input_token_cost": 7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen-plus-2025-07-28": { - "cache_creation_input_token_cost": 3.25e-07, - "cache_read_input_token_cost": 5.2e-08, - "input_cost_per_token": 2.6e-07, - "output_cost_per_token": 7.8e-07, - "input_cost_per_token_above_256k_tokens": 7.8e-07, - "output_cost_per_token_above_256k_tokens": 2.34e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k2-0905": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-30b-a3b-thinking-2507": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 81920, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-medium-3.1": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.5v": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 1.8e-06, - "cache_read_input_token_cost": 1.1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/mistralai/codestral-2508": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 9e-07, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 204800, - "max_tokens": 204800, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-coder-30b-a3b-instruct": { - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-30b-a3b-instruct-2507": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.5": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.2e-06, - "cache_read_input_token_cost": 1.1e-07, - "deprecation_date": "2026-12-31", - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-4.5-air": { - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 8.5e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_response_schema": false, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k2": { - "input_cost_per_token": 5.7e-07, - "output_cost_per_token": 2.3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 98304, - "max_tokens": 98304, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/minimax/minimax-m1": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 40000, - "max_tokens": 40000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/o3-pro": { - "input_cost_per_token": 2e-05, - "output_cost_per_token": 8e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": true - }, - "openrouter/google/gemini-2.5-pro-preview": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 1.25e-07, - "input_cost_per_audio_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/mistralai/mistral-medium-3": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/google/gemini-2.5-pro-preview-05-06": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost": 3.75e-07, - "input_cost_per_audio_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "source": "https://openrouter.ai/google/gemini-2.5-pro-preview-05-06", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_audio_input": true, - "supports_prompt_caching": true - }, - "openrouter/meta-llama/llama-guard-4-12b": { - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 1.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 163840, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-30b-a3b": { - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-8b": { - "input_cost_per_token": 1.17e-07, - "output_cost_per_token": 4.55e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-14b": { - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-32b": { - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3-235b-a22b": { - "input_cost_per_token": 4.55e-07, - "output_cost_per_token": 1.82e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/o4-mini-high": { - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true - }, - "openrouter/meta-llama/llama-4-maverick": { - "input_cost_per_token": 1.875e-07, - "output_cost_per_token": 6.525e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/meta-llama/llama-4-scout": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/openai/o1-pro": { - "input_cost_per_token": 0.00015, - "output_cost_per_token": 0.0006, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_web_search": true - }, - "openrouter/google/gemma-3-4b-it": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/google/gemma-3-12b-it": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/google/gemma-3-27b-it": { - "input_cost_per_token": 8e-08, - "output_cost_per_token": 4.5e-07, - "cache_read_input_token_cost": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-saba": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 2e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 26214, - "max_tokens": 26214, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen2.5-vl-72b-instruct": { - "input_cost_per_token": 8e-07, - "output_cost_per_token": 1e-06, - "cache_read_input_token_cost": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 115200, - "max_tokens": 115200, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen-plus": { - "input_cost_per_token": 2.6e-07, - "output_cost_per_token": 7.8e-07, - "cache_read_input_token_cost": 5.2e-08, - "cache_creation_input_token_cost": 3.25e-07, - "input_cost_per_token_above_256k_tokens": 7.8e-07, - "output_cost_per_token_above_256k_tokens": 2.34e-06, - "cache_read_input_token_cost_above_256k_tokens": 1.56e-07, - "cache_creation_input_token_cost_above_256k_tokens": 9.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-small-24b-instruct-2501": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-r1-distill-llama-70b": { - "deprecation_date": "2026-09-28", - "input_cost_per_token": 8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 7372, - "max_tokens": 7372, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_tool_choice": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/minimax/minimax-01": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000192, - "max_output_tokens": 900172, - "max_tokens": 900172, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/meta-llama/llama-3.3-70b-instruct": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-4o-2024-11-20": { - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_web_search": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false - }, - "openrouter/mistralai/mistral-large-2407": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen-2.5-7b-instruct": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/meta-llama/llama-3.2-1b-instruct": { - "input_cost_per_token": 2.7e-08, - "output_cost_per_token": 2.01e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 60000, - "max_output_tokens": 54000, - "max_tokens": 54000, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/meta-llama/llama-3.2-3b-instruct": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 3.3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen-2.5-72b-instruct": { - "input_cost_per_token": 3.6e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-4o-2024-08-06": { - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_web_search": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false - }, - "openrouter/meta-llama/llama-3.1-70b-instruct": { - "input_cost_per_token": 4e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/meta-llama/llama-3.1-8b-instruct": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-nemo": { - "input_cost_per_token": 1.9e-08, - "output_cost_per_token": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-4o-mini-2024-07-18": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_web_search": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false - }, - "openrouter/google/gemma-2-27b-it": { - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 6.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "max_tokens": 2048, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-4-turbo": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/openai/gpt-4-turbo-preview": { - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "source": "https://openrouter.ai/openai/gpt-4-turbo-preview", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": false - }, - "openrouter/openai/gpt-3.5-turbo-instruct": { - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 4095, - "max_output_tokens": 3685, - "max_tokens": 3685, - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_tool_choice": false, - "supports_response_schema": true, - "supports_vision": false, - "supports_web_search": false - }, "together_ai/arcee-ai/trinity-mini": { "input_cost_per_token": 4.5e-08, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 1.5e-07, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 128000, + "max_tokens": 128000 }, "vertex_ai/gemini-2.5-flash-native-audio": { "deprecation_date": "2026-12-13", "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 3e-06, "input_cost_per_token": 5e-07, + "input_cost_per_video_token": 3e-06, "litellm_provider": "vertex_ai", "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, @@ -69146,7 +69546,7 @@ }, "vertex_ai/gemini-3.5-transcribe-live": { "input_cost_per_audio_token": 3.5e-06, - "input_cost_per_second": 8.33333333333e-05, + "input_cost_per_second": 8.75e-05, "litellm_provider": "vertex_ai", "mode": "audio_transcription", "output_cost_per_token": 2.1e-05, @@ -69204,6 +69604,15 @@ "source": "https://developers.openai.com/api/docs/pricing", "supports_reasoning": true }, + "gpt-5.5-cyber-preview": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 1.25e-05, + "litellm_provider": "openai", + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "source": "https://developers.openai.com/api/docs/pricing", + "supports_reasoning": true + }, "gpt-rosalind-research": { "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 5e-06, @@ -69217,45 +69626,75 @@ "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 3.5e-06, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 4096, + "max_tokens": 4096 }, "together_ai/meta-llama/Llama-3.2-1B-Instruct": { "input_cost_per_token": 6e-08, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 6e-08, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 131072, + "max_tokens": 131072 }, "together_ai/meta-llama/Llama-3.2-3B-Instruct": { "input_cost_per_token": 6e-08, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 6e-08, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 131072, + "max_tokens": 131072 }, "together_ai/Qwen/Qwen2-1.5B-Instruct": { "input_cost_per_token": 2e-08, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 2e-08, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 32768, + "max_tokens": 32768 }, "together_ai/Qwen/Qwen2.5-14B-Instruct": { "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 8e-07, - "source": "https://api.together.ai/v1/models" + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 32768, + "max_tokens": 32768 }, "together_ai/Qwen/Qwen2.5-72B-Instruct": { "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "mode": "chat", "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models", + "max_input_tokens": 32768, + "max_tokens": 32768 + }, + "together_ai/Salesforce/Llama-Rank-V1": { + "deprecation_date": "2026-02-06", + "input_cost_per_token": 1e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "rerank", + "output_cost_per_token": 0.0, "source": "https://api.together.ai/v1/models" }, + "together_ai/meta-llama/Meta-Llama-3.1-8B": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 16384, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 2e-07, + "source": "https://api.together.xyz/v1/models" + }, "together_ai/together/Tev1-4B-experimental": { - "cache_read_input_token_cost": 4.2e-08, "input_cost_per_token": 4.2e-08, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -69465,7 +69904,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/google/gemma-4-31B-it": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -69598,6 +70037,7 @@ }, "together_ai/nvidia/nemotron-3-ultra-550b-a55b": { "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 512288, @@ -69607,7 +70047,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/openai/gpt-oss-20b": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69662,7 +70102,7 @@ "cache_read_input_token_cost": 4.13e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 6.6e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -69717,6 +70157,9 @@ "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, @@ -69742,7 +70185,7 @@ "cache_read_input_token_cost": 1.38e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -69778,7 +70221,7 @@ "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" @@ -69788,7 +70231,7 @@ "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -69812,7 +70255,7 @@ "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -69820,7 +70263,7 @@ "input_cost_per_token": 2.31e-05, "input_cost_per_token_batches": 1.155e-05, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" @@ -69832,7 +70275,7 @@ "input_cost_per_token": 1.925e-06, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" @@ -69871,7 +70314,7 @@ "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, "input_cost_per_token_batches": 1.65e-05, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 0.000198, "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, @@ -70030,12 +70473,29 @@ "output_cost_per_token_batches": 2.42e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, + "azure/eu/o3": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "azure/eu/o3-2025-04-16": { "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, @@ -70050,12 +70510,29 @@ "output_cost_per_token": 4.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, + "azure/eu/o4-mini": { + "deprecation_date": "2026-11-19", + "cache_read_input_token_cost": 3.03e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "azure/eu/o4-mini-2025-04-16": { "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 3.03e-07, "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -70101,7 +70578,8 @@ "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_reasoning": true }, "gemini/gemini-3.8-live-extended-thinking": { "input_cost_per_audio_token": 3e-06, @@ -70122,14 +70600,15 @@ "supports_function_calling": true, "supports_response_schema": false, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_reasoning": true }, "azure/us/codex-mini": { "deprecation_date": "2026-11-15", "cache_read_input_token_cost": 4.13e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 6.6e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -70184,6 +70663,9 @@ "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.65e-05, "output_cost_per_token_batches": 8.25e-06, @@ -70209,7 +70691,7 @@ "cache_read_input_token_cost": 1.38e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -70245,7 +70727,7 @@ "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 0.000132, "output_cost_per_token_batches": 6.6e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" @@ -70255,7 +70737,7 @@ "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -70279,7 +70761,7 @@ "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, @@ -70287,7 +70769,7 @@ "input_cost_per_token": 2.31e-05, "input_cost_per_token_batches": 1.155e-05, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 0.0001848, "output_cost_per_token_batches": 9.24e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" @@ -70299,7 +70781,7 @@ "input_cost_per_token": 1.925e-06, "input_cost_per_token_priority": 3.85e-06, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 1.54e-05, "output_cost_per_token_priority": 3.08e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" @@ -70338,7 +70820,7 @@ "input_cost_per_token_above_272k_tokens_batches": 3.3e-05, "input_cost_per_token_batches": 1.65e-05, "litellm_provider": "azure", - "mode": "chat", + "mode": "responses", "output_cost_per_token": 0.000198, "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, @@ -70480,7 +70962,7 @@ "supports_audio_input": true }, "azure/gpt-realtime-translate": { - "deprecation_date": "2027-05-06", + "deprecation_date": "2027-11-09", "input_cost_per_second": 0.000566666666667, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -70935,6 +71417,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_vision": true, "supports_web_search": true }, @@ -70952,6 +71435,7 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_sampling_params": false, "supports_vision": true, "supports_web_search": true }, @@ -71623,26 +72107,150 @@ "supports_reasoning": true, "supports_vision": true }, - "openrouter/typesafe/jev-1.13": { - "input_cost_per_token": 4.2e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 32000, - "max_output_tokens": 28800, - "max_tokens": 28800, + "bespoke/nimble-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "bespoke", + "max_input_tokens": 8192, "mode": "evaluation", "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/typesafe/jev-1.13" + "source": "https://github.com/bespokelabsai/nimble", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "bespoke/nimble": { + "input_cost_per_token": 0.0, + "litellm_provider": "bespoke", + "max_input_tokens": 8192, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://ollama.com/library/nimble", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model under the name Ollama serves it as; infrastructure costs are paid separately" + } + }, + "bespoke/bespokelabs/Bespoke-Nimble-9B": { + "input_cost_per_token": 0.0, + "litellm_provider": "bespoke", + "max_input_tokens": 8192, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/bespokelabsai/nimble", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "laya/english": { + "input_cost_per_token": 0.0, + "litellm_provider": "laya", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/NandhaKishorM/laya", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "laya/multilingual": { + "input_cost_per_token": 0.0, + "litellm_provider": "laya", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/NandhaKishorM/laya", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "laya/typed-decisions": { + "input_cost_per_token": 0.0, + "litellm_provider": "laya", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://github.com/NandhaKishorM/laya", + "supported_endpoints": [ + "/v1/systemone" + ], + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "strands_decider/strands-decider-2B-hobson-v19": { + "input_cost_per_token": 0.0, + "litellm_provider": "strands_decider", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v19", + "metadata": { + "notes": "Self-hosted decision model; infrastructure costs are paid separately" + } + }, + "nace/drex-v1.0": { + "input_cost_per_token": 4e-08, + "litellm_provider": "nace", + "max_input_tokens": 32768, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" + }, + "nace/drex-v1.5": { + "input_cost_per_token": 5e-08, + "litellm_provider": "nace", + "max_input_tokens": 131072, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" + }, + "nace/drex-v2.0": { + "input_cost_per_token": 6e-08, + "litellm_provider": "nace", + "max_input_tokens": 131072, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" + }, + "nace/drex-latest": { + "input_cost_per_token": 6e-08, + "litellm_provider": "nace", + "max_input_tokens": 131072, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://console.nace.ai/docs/drex/reference/models" }, "typesafe/jev-1.13.0": { "input_cost_per_token": 4.2e-08, "litellm_provider": "typesafe", + "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.typesafe.ai/models" }, + "typesafe/jev-1.14.0": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "typesafe", + "max_input_tokens": 65536, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.typesafe.ai/models", + "supports_box_questions": true + }, "typesafe/jev-latest": { "input_cost_per_token": 4.2e-08, "litellm_provider": "typesafe", + "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, "source": "https://docs.typesafe.ai/models" @@ -71650,9 +72258,11 @@ "typesafe/jev-preview": { "input_cost_per_token": 4.2e-08, "litellm_provider": "typesafe", + "max_input_tokens": 65536, "mode": "evaluation", "output_cost_per_token": 0.0, - "source": "https://docs.typesafe.ai/models" + "source": "https://docs.typesafe.ai/models", + "supports_box_questions": true }, "wandb/deepseek-ai/DeepSeek-V4.1-Flash": { "cache_read_input_token_cost": 3e-08, @@ -71689,4109 +72299,109 @@ "max_input_tokens": 1049000, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://wandb.ai/site/pricing/tokens/", + "source": "https://docs.wandb.ai/inference/models.md", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": true - }, - "openrouter/~anthropic/claude-fable-latest": { - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_1hr": 2e-05, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~anthropic/claude-haiku-latest": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_1hr": 2e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~anthropic/claude-opus-latest": { - "cache_creation_input_token_cost": 5e-06, - "cache_creation_input_token_cost_above_1hr": 8e-06, - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~anthropic/claude-sonnet-latest": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~deepseek/deepseek-flash-latest": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/~deepseek/deepseek-pro-latest": { - "cache_read_input_token_cost": 4.4e-08, - "input_cost_per_token": 1.32e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, - "mode": "chat", - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":6.6e-7,"output_cost_per_token":0.00000198,"cache_read_input_token_cost":2.2e-8}, - "output_cost_per_token": 3.96e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/~deepseek/deepseek-v4-flash-latest": { - "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 6.4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/~google/gemini-flash-latest": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 7.5e-08, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 7.5e-07, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 3.75e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~google/gemini-pro-latest": { - "cache_creation_input_token_cost": 3.75e-07, - "cache_read_input_audio_token_cost": 2e-07, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_200k_tokens": 4e-07, - "input_cost_per_audio_token": 2e-06, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_200k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_200k_tokens": 1.8e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~moonshotai/kimi-latest": { - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/~openai/gpt-astra-latest": { - "cache_creation_input_token_cost": 1.25e-05, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, - "cache_read_input_token_cost": 1e-06, - "cache_read_input_token_cost_above_272k_tokens": 2e-06, - "input_cost_per_token": 1e-05, - "input_cost_per_token_above_272k_tokens": 2e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-05, - "output_cost_per_token_above_272k_tokens": 7.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~openai/gpt-luna-latest": { - "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_272k_tokens": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~openai/gpt-mini-latest": { - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 4.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~openai/gpt-sol-latest": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~openai/gpt-terra-latest": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.2e-05, - "output_cost_per_token_above_272k_tokens": 1.8e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~x-ai/grok-latest": { - "cache_read_input_token_cost": 4e-07, - "cache_read_input_token_cost_above_200k_tokens": 8e-07, - "input_cost_per_token": 1.6e-06, - "input_cost_per_token_above_200k_tokens": 3.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, - "mode": "chat", - "output_cost_per_token": 4.8e-06, - "output_cost_per_token_above_200k_tokens": 9.6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/~z-ai/glm-flash-latest": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/~z-ai/glm-latest": { - "cache_read_input_token_cost": 1.2142e-07, - "input_cost_per_token": 6.538e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1310720, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2.0548e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/aion-labs/aion-2.0": { - "cache_read_input_token_cost": 2e-07, - "input_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/aion-labs/aion-3.0": { - "cache_read_input_token_cost": 7.5e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/aion-labs/aion-3.0-mini": { - "cache_read_input_token_cost": 1.8e-07, - "input_cost_per_token": 7e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/aion-labs/aion-3.5": { - "cache_read_input_token_cost": 7.5e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/aion-labs/aion-3.5-mini": { - "cache_read_input_token_cost": 1.8e-07, - "input_cost_per_token": 7e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/aion-labs/aion-rp-llama-3.1-8b": { - "input_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, - "mode": "chat", - "output_cost_per_token": 1.6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/amazon/nova-2-lite-v1": { - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/amazon/nova-lite-v1": { - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 300000, - "max_output_tokens": 5120, - "max_tokens": 5120, - "mode": "chat", - "output_cost_per_token": 2.4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/amazon/nova-micro-v1": { - "input_cost_per_token": 3.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 5120, - "max_tokens": 5120, - "mode": "chat", - "output_cost_per_token": 1.4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/amazon/nova-premier-v1": { - "cache_read_input_token_cost": 6.25e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/amazon/nova-pro-v1": { - "input_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 300000, - "max_output_tokens": 5120, - "max_tokens": 5120, - "mode": "chat", - "output_cost_per_token": 3.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/anthracite-org/magnum-v4-72b": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/anthropic/claude-fable-5:batch": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-fable-5.1:batch": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-haiku-4.5:batch": { - "cache_creation_input_token_cost": 6.25e-07, - "cache_creation_input_token_cost_above_1hr": 1e-06, - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.1:batch": { - "cache_creation_input_token_cost": 9.375e-06, - "cache_creation_input_token_cost_above_1hr": 1.5e-05, - "cache_read_input_token_cost": 7.5e-07, - "input_cost_per_token": 7.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 3.75e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.5:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.6:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.7:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-4.8:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-opus-5:batch": { - "cache_creation_input_token_cost": 3.125e-06, - "cache_creation_input_token_cost_above_1hr": 5e-06, - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-4.5:batch": { - "cache_creation_input_token_cost": 1.875e-06, - "cache_creation_input_token_cost_above_1hr": 3e-06, - "cache_creation_input_token_cost_above_200k_tokens": 3.75e-06, - "cache_read_input_token_cost": 1.5e-07, - "cache_read_input_token_cost_above_200k_tokens": 3e-07, - "input_cost_per_token": 1.5e-06, - "input_cost_per_token_above_200k_tokens": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 7.5e-06, - "output_cost_per_token_above_200k_tokens": 1.125e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-4.6:batch": { - "cache_creation_input_token_cost": 1.875e-06, - "cache_creation_input_token_cost_above_1hr": 3e-06, - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/anthropic/claude-sonnet-5:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_1hr": 2e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/arcee-ai/trinity-large-thinking": { - "cache_read_input_token_cost": 6e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 80000, - "max_tokens": 80000, - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/baidu/ernie-4.5-vl-424b-a47b": { - "deprecation_date": "2026-10-08", - "input_cost_per_token": 4.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 123000, - "max_output_tokens": 16000, - "max_tokens": 16000, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/bytedance-seed/seed-1.6": { - "deprecation_date": "2026-11-11", - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_above_128k_tokens": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 2e-06, - "output_cost_per_token_above_128k_tokens": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/bytedance-seed/seed-1.6-flash": { - "deprecation_date": "2026-11-11", - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 3e-07, - "output_cost_per_token_above_128k_tokens": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/bytedance-seed/seed-2-1-turbo": { - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 2.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/bytedance-seed/seed-2.0-code": { - "deprecation_date": "2026-11-11", - "input_cost_per_token": 5e-07, - "input_cost_per_token_above_128k_tokens": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3e-06, - "output_cost_per_token_above_128k_tokens": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/bytedance-seed/seed-2.0-lite": { - "input_cost_per_token": 2.5e-07, - "input_cost_per_token_above_128k_tokens": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-06, - "output_cost_per_token_above_128k_tokens": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/bytedance-seed/seed-2.0-mini": { - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_128k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 4e-07, - "output_cost_per_token_above_128k_tokens": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition": { - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 9e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/cohere/command-a": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/cohere/command-r-08-2024": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/cohere/command-r-plus-08-2024": { - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/cohere/command-r7b-12-2024": { - "input_cost_per_token": 3.75e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "max_tokens": 4000, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/cohere/north-mini-code:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/dots-studio/dots-3-note-preview:free": { - "deprecation_date": "2026-12-31", - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 512000, - "max_output_tokens": 460800, - "max_tokens": 460800, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/google/gemini-2.5-flash-lite:batch": { - "cache_read_input_audio_token_cost": 3e-08, - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 1.5e-07, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-2.5-flash:batch": { - "cache_read_input_audio_token_cost": 1e-07, - "cache_read_input_token_cost": 3e-08, - "deprecation_date": "2026-10-20", - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-2.5-pro:batch": { - "cache_read_input_audio_token_cost": 1.25e-07, - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "deprecation_date": "2026-10-20", - "input_cost_per_audio_token": 6.25e-07, - "input_cost_per_token": 6.25e-07, - "input_cost_per_token_above_200k_tokens": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_200k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3-flash-preview:batch": { - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.1-flash-lite:batch": { - "cache_read_input_audio_token_cost": 2.5e-08, - "cache_read_input_token_cost": 1.25e-08, - "input_cost_per_audio_token": 2.5e-07, - "input_cost_per_token": 1.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.1-pro-preview:batch": { - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_200k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_200k_tokens": 9e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.5-flash-lite:batch": { - "cache_read_input_audio_token_cost": 1.5e-08, - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_audio_token": 1.5e-07, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.5-flash:batch": { - "cache_read_input_audio_token_cost": 1.5e-07, - "cache_read_input_token_cost": 7.5e-08, - "input_cost_per_audio_token": 1.5e-06, - "input_cost_per_token": 7.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 4.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.6-flash:batch": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 3.75e-08, - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_audio_token": 3.75e-07, - "input_cost_per_token": 3.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.875e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.7-flash:batch": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 3.75e-08, - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_audio_token": 3.75e-07, - "input_cost_per_token": 3.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.875e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/google/gemini-3.8-flash:batch": { - "cache_creation_input_token_cost": 4.16666666666667e-08, - "cache_read_input_audio_token_cost": 3.75e-08, - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_audio_token": 3.75e-07, - "input_cost_per_token": 3.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.875e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_video_input": true - }, - "openrouter/ibm-granite/granite-4.0-h-micro": { - "input_cost_per_token": 1.7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131000, - "max_output_tokens": 117900, - "max_tokens": 117900, - "mode": "chat", - "output_cost_per_token": 1.12e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/ibm-granite/granite-4.2-8b": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inception/mercury-2": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 50000, - "max_tokens": 50000, - "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inception/mercury-2.5": { - "cache_read_input_token_cost": 4e-09, - "input_cost_per_token": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 260000, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inclusionai/ling-3.0-flash": { - "cache_read_input_token_cost": 4.2e-09, - "input_cost_per_token": 2.1e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 6.3e-08, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inclusionai/ling-3.0-flash-fin": { - "cache_read_input_token_cost": 1.2e-08, - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inclusionai/ling-3.0-flash-fin:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inclusionai/ling-3.0-flash-sante:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inclusionai/ling-3.0-flash-vl": { - "cache_read_input_token_cost": 1.2e-08, - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/inclusionai/ling-3.0-flash-vl:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/inference-net/schematron-v2-small": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 2.3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/inference-net/schematron-v2-turbo": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_token": 3e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/kwaipilot/kat-coder-pro-v2.5": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 7.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 2.96e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/liquid/lfm-2.5-2.6b:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/meituan/longcat-2.0": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048756, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/meta/muse-glimmer-30b": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/meta/muse-spark-1.1": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 4.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/meta/muse-spark-1.2": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 4.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/meta/muse-spark-1.2-contributor": { - "cache_read_input_token_cost": 2e-09, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/meta/muse-spark-1.3": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 4.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/meta/muse-spark-1.3-contributor": { - "cache_read_input_token_cost": 2e-09, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/microsoft/phi-4": { - "input_cost_per_token": 7e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 16384, - "max_output_tokens": 14745, - "max_tokens": 14745, - "mode": "chat", - "output_cost_per_token": 1.4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/microsoft/wizardlm-2-8x22b": { - "input_cost_per_token": 6.2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 65535, - "max_output_tokens": 8000, - "max_tokens": 8000, - "mode": "chat", - "output_cost_per_token": 6.2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mistralai/codestral-2508:batch": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 204800, - "max_tokens": 204800, - "mode": "chat", - "output_cost_per_token": 4.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/mistralai/ministral-8b-2512:batch": { - "cache_read_input_token_cost": 7.5e-09, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 7.5e-08, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-large-2512": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-large-2512:batch": { - "cache_read_input_token_cost": 2.5e-08, - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-medium-3-5:batch": { - "input_cost_per_token": 7.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 3.75e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-medium-3.1:batch": { - "cache_read_input_token_cost": 2e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 104857, - "max_tokens": 104857, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/mistralai/mistral-small-2603:batch": { - "cache_read_input_token_cost": 7.5e-09, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 209715, - "max_tokens": 209715, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/moonshotai/kimi-k3:batch": { - "cache_read_input_token_cost": 2.28e-07, - "input_cost_per_token": 2.28e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1.14e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/morph/morph-v3-fast": { - "input_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 81920, - "max_output_tokens": 38000, - "max_tokens": 38000, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/morph/morph-v3-large": { - "input_cost_per_token": 9e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.9e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/nex-agi/nex-n2.5-mini:free": { - "deprecation_date": "2026-09-25", - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nex-agi/nex-n2.5-pro:free": { - "deprecation_date": "2026-09-25", - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nousresearch/hermes-3-llama-3.1-405b": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/nousresearch/hermes-3-llama-3.1-70b": { - "input_cost_per_token": 7e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 7e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/nousresearch/hermes-4-405b": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-3.5-turbo-0613": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 4095, - "max_output_tokens": 3685, - "max_tokens": 3685, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/openai/gpt-3.5-turbo:batch": { - "input_cost_per_token": 2.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": true - }, - "openrouter/openai/gpt-4-turbo:batch": { - "input_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4.1-mini:batch": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4.1-nano:batch": { - "cache_read_input_token_cost": 1.25e-08, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4.1:batch": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4o-mini:batch": { - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-4o:batch": { - "cache_read_input_token_cost": 6.25e-07, - "input_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-image": { - "cache_read_input_token_cost": 1.25e-06, - "input_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-image-mini": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-mini:batch": { - "cache_read_input_token_cost": 1.25e-08, - "input_cost_per_token": 1.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-nano:batch": { - "cache_read_input_token_cost": 2.5e-09, - "input_cost_per_token": 2.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5-pro:batch": { - "input_cost_per_token": 7.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5:batch": { - "cache_read_input_token_cost": 6.25e-08, - "input_cost_per_token": 6.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.1:batch": { - "cache_read_input_token_cost": 6.25e-08, - "input_cost_per_token": 6.25e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.2-pro:batch": { - "input_cost_per_token": 1.05e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 8.4e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.2:batch": { - "cache_read_input_token_cost": 8.75e-08, - "input_cost_per_token": 8.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 7e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4-image-2": { - "cache_read_input_token_cost": 2e-06, - "input_cost_per_token": 8e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4-mini:batch": { - "cache_read_input_token_cost": 3.75e-08, - "input_cost_per_token": 3.75e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4-nano:batch": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6.25e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4-pro:batch": { - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_above_272k_tokens": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 9e-05, - "output_cost_per_token_above_272k_tokens": 0.000135, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.4:batch": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_272k_tokens": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_272k_tokens": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 7.5e-06, - "output_cost_per_token_above_272k_tokens": 1.125e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.5-pro:batch": { - "input_cost_per_token": 1.5e-05, - "input_cost_per_token_above_272k_tokens": 3e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 9e-05, - "output_cost_per_token_above_272k_tokens": 0.000135, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.5:batch": { - "cache_read_input_token_cost": 2.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 5e-07, - "input_cost_per_token": 2.5e-06, - "input_cost_per_token_above_272k_tokens": 5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_above_272k_tokens": 2.25e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-luna-pro:batch": { - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-07, - "output_cost_per_token_above_272k_tokens": 9e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-luna:batch": { - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-07, - "output_cost_per_token_above_272k_tokens": 9e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-sol-pro:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-sol:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-terra-pro:batch": { - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_272k_tokens": 9e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-5.6-terra:batch": { - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "output_cost_per_token_above_272k_tokens": 9e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-astra-pro:batch": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "output_cost_per_token_above_272k_tokens": 3.75e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-astra:batch": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-05, - "output_cost_per_token_above_272k_tokens": 3.75e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-luna": { - "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_272k_tokens": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-luna-pro": { - "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, - "cache_read_input_token_cost": 1e-08, - "cache_read_input_token_cost_above_272k_tokens": 2e-08, - "input_cost_per_token": 1e-07, - "input_cost_per_token_above_272k_tokens": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-07, - "output_cost_per_token_above_272k_tokens": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-sol-pro": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 2e-07, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/o3-mini:batch": { - "cache_read_input_token_cost": 2.75e-07, - "input_cost_per_token": 5.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 2.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": true - }, - "openrouter/openai/o3:batch": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/o4-mini:batch": { - "cache_read_input_token_cost": 1.375e-07, - "input_cost_per_token": 5.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "max_tokens": 100000, - "mode": "chat", - "output_cost_per_token": 2.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/perceptron/perceptron-mk1": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/perplexity/sonar": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 127072, - "max_output_tokens": 114364, - "max_tokens": 114364, - "mode": "chat", - "output_cost_per_token": 1e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/perplexity/sonar-deep-research": { - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 115200, - "max_tokens": 115200, - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": true - }, - "openrouter/perplexity/sonar-pro": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 8000, - "max_tokens": 8000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/perplexity/sonar-pro-search": { - "input_cost_per_token": 3e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 200000, - "max_output_tokens": 8000, - "max_tokens": 8000, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/perplexity/sonar-reasoning-pro": { - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 128000, - "max_output_tokens": 115200, - "max_tokens": 115200, - "mode": "chat", - "output_cost_per_token": 8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/qwen/qwen3.8-27b:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/rekaai/reka-edge": { - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 16384, - "max_output_tokens": 14745, - "max_tokens": 14745, - "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/rekaai/reka-flash-3": { - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 65536, - "max_output_tokens": 58982, - "max_tokens": 58982, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/relace/relace-apply-3": { - "input_cost_per_token": 8.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/relace/relace-search": { - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 256000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/sakana/fugu-max": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/sakana/fugu-ultra": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/sakana/fugu-ultra-v2": { - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/sakana/sakana-namazu": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 9.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/sao10k/l3-lunaris-8b": { - "input_cost_per_token": 4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 7372, - "max_tokens": 7372, - "mode": "chat", - "output_cost_per_token": 5e-08, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/sao10k/l3.1-euryale-70b": { - "input_cost_per_token": 8.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 8.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/sao10k/l3.3-euryale-70b": { - "input_cost_per_token": 6.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 16384, - "mode": "chat", - "output_cost_per_token": 7.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/stealth/space-bunny-alpha": { - "deprecation_date": "2098-12-31", - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_reasoning": true, "supports_tool_choice": true, - "supports_video_input": true, "supports_vision": true }, - "openrouter/stepfun/step-3.5-flash": { - "input_cost_per_token": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "chat", - "output_cost_per_token": 3e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/stepfun/step-3.7-flash": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 230400, - "max_tokens": 230400, - "mode": "chat", - "output_cost_per_token": 1.15e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/tencent/hunyuan-a13b-instruct": { - "input_cost_per_token": 1.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 5.7e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/tencent/hy-mt2-1.8b": { - "input_cost_per_token": 4.4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 1.77e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/tencent/hy-mt2-30b-a3b": { - "input_cost_per_token": 7.4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 2.95e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/tencent/hy-mt2-7b": { - "input_cost_per_token": 7.4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 2.95e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/tencent/hy3": { - "cache_read_input_token_cost": 3.3e-08, - "input_cost_per_token": 1.32e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "off_peak_pricing": {"hours_utc":"16:00-00:00","input_cost_per_token":8.25e-8,"output_cost_per_token":3.3e-7,"cache_read_input_token_cost":2.0625e-8}, - "output_cost_per_token": 5.28e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/tencent/hy3-preview": { - "cache_read_input_token_cost": 6e-08, - "input_cost_per_token": 1.8e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/tencent/hy4-preview": { - "cache_read_input_token_cost": 4.2e-08, - "input_cost_per_token": 8.34e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 2.501e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/thedrummer/cydonia-24b-v4.1": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/thedrummer/skyfall-36b-v2": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 5.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 32768, - "max_output_tokens": 29491, - "max_tokens": 29491, - "mode": "chat", - "output_cost_per_token": 8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/thedrummer/unslopnemo-12b": { - "input_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1024000, - "max_output_tokens": 819200, - "max_tokens": 819200, - "mode": "chat", - "output_cost_per_token": 4e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/thinkingmachines/inkling": { - "cache_read_input_token_cost": 1.7e-07, - "input_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 471859, - "max_tokens": 471859, - "mode": "chat", - "output_cost_per_token": 4.05e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/thinkingmachines/inkling-small": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/thinkingmachines/inkling-small:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/thinkingmachines/inkling:free": { - "input_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 262144, - "max_tokens": 262144, - "mode": "chat", - "output_cost_per_token": 0.0, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/unbiased/pareto": { - "cache_read_input_token_cost": 2.5e-07, - "input_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/upstage/solar-pro-3": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/upstage/solar-pro4": { - "cache_read_input_token_cost": 1.8e-08, - "input_cost_per_token": 9e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 524288, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3.6e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/upstage/solar-mini4": { - "cache_read_input_token_cost": 5e-09, - "input_cost_per_token": 5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 524288, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/writer/palmyra-x5": { - "input_cost_per_token": 6e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1040000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/x-ai/grok-4.3:batch": { - "cache_read_input_token_cost": 1.6e-07, - "cache_read_input_token_cost_above_200k_tokens": 3.2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_200k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 900000, - "max_tokens": 900000, - "mode": "chat", - "output_cost_per_token": 2e-06, - "output_cost_per_token_above_200k_tokens": 4e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/z-ai/glm-5.3-flash:batch": { - "cache_read_input_token_cost": 1.2e-08, - "input_cost_per_token": 6e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.3:batch": { - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 4.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 2e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/prism-ml/ternary-bonsai-2-27b": { - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.3-prime": { - "cache_read_input_token_cost": 5.6e-07, - "input_cost_per_token": 2.8e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 8.8e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/z-ai/glm-5.3-flashx": { - "cache_read_input_token_cost": 9e-08, - "deprecation_date": "2098-12-31", - "input_cost_per_token": 3.7e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.25e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/x-ai/grok-4.7": { - "cache_read_input_token_cost": 4e-07, - "cache_read_input_token_cost_above_200k_tokens": 8e-07, - "input_cost_per_token": 1.6e-06, - "input_cost_per_token_above_200k_tokens": 3.2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 500000, - "max_output_tokens": 450000, - "max_tokens": 450000, - "mode": "chat", - "output_cost_per_token": 4.8e-06, - "output_cost_per_token_above_200k_tokens": 9.6e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, "moonshotai.kimi-k3": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "token_count_framing": 64, - "token_count_tokenizer": "kimi_k3" - }, - "global.moonshotai.kimi-k3": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "litellm_provider": "bedrock_converse", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "token_count_framing": 64, - "token_count_tokenizer": "kimi_k3" - }, - "us.moonshotai.kimi-k3": { + "supports_regex_lookaround": false, "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_flex": 2.0625e-06, + "cache_creation_input_token_cost_priority": 7.21875e-06, "cache_read_input_token_cost": 3.3e-07, + "cache_read_input_token_cost_flex": 1.65e-07, + "cache_read_input_token_cost_priority": 5.775e-07, "input_cost_per_token": 3.3e-06, + "input_cost_per_token_flex": 1.65e-06, + "input_cost_per_token_priority": 5.775e-06, "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.65e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token_flex": 8.25e-06, + "output_cost_per_token_priority": 2.8875e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, + "supports_vision": true + }, + "global.moonshotai.kimi-k3": { + "supports_regex_lookaround": false, + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_flex": 1.875e-06, + "cache_creation_input_token_cost_priority": 6.5625e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_flex": 1.5e-07, + "cache_read_input_token_cost_priority": 5.25e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_flex": 1.5e-06, + "input_cost_per_token_priority": 5.25e-06, + "litellm_provider": "bedrock_converse", "token_count_framing": 64, - "token_count_tokenizer": "kimi_k3" - }, - "openrouter/xiaomi/mimo-v2.6-flash": { - "cache_read_input_token_cost": 2.8e-09, - "input_cost_per_token": 1.4e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "token_count_tokenizer": "kimi_k3", + "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.8e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_flex": 7.5e-06, + "output_cost_per_token_priority": 2.625e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, - "openrouter/xiaomi/mimo-v2.6-pro": { - "cache_read_input_token_cost": 3.6e-09, - "input_cost_per_token": 4.35e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "us.moonshotai.kimi-k3": { + "supports_regex_lookaround": false, + "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_flex": 2.0625e-06, + "cache_creation_input_token_cost_priority": 7.21875e-06, + "cache_read_input_token_cost": 3.3e-07, + "cache_read_input_token_cost_flex": 1.65e-07, + "cache_read_input_token_cost_priority": 5.775e-07, + "input_cost_per_token": 3.3e-06, + "input_cost_per_token_flex": 1.65e-06, + "input_cost_per_token_priority": 5.775e-06, + "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", + "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 8.7e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_flex": 8.25e-06, + "output_cost_per_token_priority": 2.8875e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, "supports_function_calling": true, - "supports_pdf_input": false, + "supports_prompt_cache_breakpoint": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/xiaomi/mimo-v2.6-pro-ultraspeed": { - "cache_read_input_token_cost": 3.6e-08, - "input_cost_per_token": 4.35e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 8.7e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false + "supports_vision": true }, "xiaomi_mimo/mimo-v2.6-pro": { "cache_read_input_token_cost": 3.6e-09, @@ -75841,13 +72451,16 @@ }, "xai/grok-4.20-0309": { "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1.6e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, + "output_cost_per_token_batches": 2e-06, "source": "https://api.x.ai/v1/language-models", "supports_function_calling": true, "supports_reasoning": true, @@ -75855,8 +72468,11 @@ "supports_vision": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, "output_cost_per_token_above_200k_tokens": 5e-06, + "output_cost_per_token_above_200k_tokens_batches": 4e-06, "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-07, "input_cost_per_image_token": 1.25e-06, "supports_prompt_caching": true, "supports_response_schema": true @@ -76261,53 +72877,13 @@ "supports_prompt_caching": true, "supports_response_schema": true }, - "openrouter/nex-agi/nex-n2.5-mini": { - "cache_read_input_token_cost": 2.5e-09, - "input_cost_per_token": 2.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 1e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": false, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/nex-agi/nex-n2.5-pro": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 7.5e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, "baseten/deepseek-ai/DeepSeek-V4.1-Flash": { "cache_read_input_token_cost": 7e-09, "input_cost_per_token": 3e-07, "litellm_provider": "baseten", "max_input_tokens": 1048576, - "max_output_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://inference.baseten.co/v1/models", @@ -76319,6 +72895,7 @@ "supports_vision": true }, "baseten/moonshotai/Kimi-K2.6": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "baseten", @@ -76336,6 +72913,7 @@ "supports_vision": true }, "baseten/moonshotai/Kimi-K2.7-Code": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.6e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "baseten", @@ -76387,6 +72965,7 @@ "supports_vision": false }, "baseten/thinkingmachines/inkling": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1e-06, "litellm_provider": "baseten", @@ -76404,6 +72983,7 @@ "supports_vision": true }, "baseten/thinkingmachines/inkling-small": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "baseten", @@ -76472,6 +73052,7 @@ "supports_vision": false }, "baseten/deepseek-ai/DeepSeek-V4-Pro": { + "deprecation_date": "2026-10-16", "cache_read_input_token_cost": 1.45e-07, "input_cost_per_token": 1.74e-06, "litellm_provider": "baseten", @@ -76620,13 +73201,25 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "fireworks_ai/accounts/fireworks/routers/rune": { + "cache_read_input_token_cost": 8.4e-09, + "input_cost_per_token": 4.2e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 262144, + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://docs.fireworks.ai" + }, "fireworks_ai/accounts/fireworks/models/ember-1": { "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_priority": 3.75e-07, "input_cost_per_token": 3e-06, + "input_cost_per_token_priority": 3.75e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_priority": 1.875e-05, "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, @@ -76634,224 +73227,6 @@ "supports_tool_choice": true, "supports_vision": true }, - "openrouter/anthropic/claude-opus-5.5:batch": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_1hr": 4e-06, - "cache_read_input_token_cost": 1e-07, - "input_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/cohere/command-a-plus": { - "cache_read_input_token_cost": 1.5e-07, - "input_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 192000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/deepseek/deepseek-v4.1-flash:batch": { - "cache_read_input_token_cost": 3.36e-09, - "input_cost_per_token": 1.12e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1048576, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3.36e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/openai/gpt-6-luna-pro:batch": { - "cache_creation_input_token_cost": 6.25e-08, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-07, - "cache_read_input_token_cost": 5e-09, - "cache_read_input_token_cost_above_272k_tokens": 1e-08, - "input_cost_per_token": 5e-08, - "input_cost_per_token_above_272k_tokens": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "output_cost_per_token_above_272k_tokens": 3.75e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-luna:batch": { - "cache_creation_input_token_cost": 6.25e-08, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-07, - "cache_read_input_token_cost": 5e-09, - "cache_read_input_token_cost_above_272k_tokens": 1e-08, - "input_cost_per_token": 5e-08, - "input_cost_per_token_above_272k_tokens": 1e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.5e-07, - "output_cost_per_token_above_272k_tokens": 3.75e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-sol-pro:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6-sol:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-oss-20b:batch": { - "input_cost_per_token": 2.4e-08, - "litellm_provider": "openrouter", - "max_input_tokens": 131072, - "max_output_tokens": 117964, - "max_tokens": 117964, - "mode": "chat", - "output_cost_per_token": 1.12e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": false, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": false, - "supports_web_search": false - }, - "openrouter/qwen/qwen3.8-omni-flash": { - "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 1000000, - "max_output_tokens": 131072, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 4.7e-07, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_pdf_input": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": false - }, - "openrouter/perceptron/perceptron-mk1.5": { - "input_cost_per_token": 1.5e-07, - "litellm_provider": "openrouter", - "max_input_tokens": 36864, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_video_input": true, - "supports_vision": true - }, "vertex_ai/gemini-2.0-flash": { "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 1e-06, @@ -77126,7 +73501,12 @@ "cache_read_input_token_cost": 1.1e-06, "output_cost_per_token": 5.5e-05, "cache_creation_input_token_cost_above_1hr": 2.2e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-mythos-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + } }, "apac.anthropic.claude-fable-5": { "litellm_provider": "bedrock_converse", @@ -77148,7 +73528,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77181,7 +73561,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": true, + "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77225,7 +73605,12 @@ "input_cost_per_token": 5.5e-06, "cache_creation_input_token_cost_above_1hr": 1.1e-05, "cache_read_input_token_cost": 5.5e-07, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-7", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "apac.anthropic.claude-opus-4-8": { "bedrock_converse_supports_strict_tools": false, @@ -77249,6 +73634,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77259,7 +73645,12 @@ "output_cost_per_token": 2.75e-05, "cache_read_input_token_cost": 5.5e-07, "cache_creation_input_token_cost": 6.875e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-4-8", + "litellm_provider": "bedrock_mantle", + "region": "ap-northeast-1" + } }, "apac.anthropic.claude-opus-5": { "bedrock_converse_supports_strict_tools": false, @@ -77292,7 +73683,12 @@ "input_cost_per_token": 5.5e-06, "cache_read_input_token_cost": 5.5e-07, "output_cost_per_token": 2.75e-05, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "apac.anthropic.claude-opus-5-5": { "bedrock_converse_supports_strict_tools": false, @@ -77327,7 +73723,12 @@ "input_cost_per_token": 4.4e-06, "output_cost_per_token": 2.2e-05, "cache_read_input_token_cost": 2.2e-07, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "apac.anthropic.claude-sonnet-4-6": { "supports_adaptive_thinking": true, @@ -77338,7 +73739,7 @@ "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", - "supports_assistant_prefill": true, + "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -77357,7 +73758,11 @@ "cache_read_input_token_cost": 3.3e-07, "cache_creation_input_token_cost": 4.125e-06, "input_cost_per_token": 3.3e-06, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-4-6", + "litellm_provider": "bedrock" + } }, "apac.anthropic.claude-sonnet-5": { "bedrock_converse_supports_strict_tools": false, @@ -77381,6 +73786,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77391,7 +73797,12 @@ "input_cost_per_token": 2.2e-06, "output_cost_per_token": 1.1e-05, "cache_read_input_token_cost": 2.2e-07, - "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "token_count_model": { + "model": "anthropic.claude-sonnet-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + } }, "us.anthropic.claude-mythos-preview": { "litellm_provider": "bedrock_converse", @@ -77454,6 +73865,7 @@ "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "deepseek.r1-v1:0": { + "deprecation_date": "2027-03-30", "input_cost_per_token": 1.35e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, @@ -77461,7 +73873,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://aws.amazon.com/bedrock/pricing/", + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", "supports_function_calling": false, "supports_reasoning": true, "supports_tool_choice": false @@ -77478,64 +73890,1369 @@ "supports_function_calling": true, "supports_tool_choice": false }, - "cloudflare/clef": { - "input_cost_per_token": 2.4e-07, - "litellm_provider": "cloudflare", - "max_input_tokens": 65536, - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + "azure_ai/MAI-Cyber-1-Flash": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 256000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true }, - "cloudflare/clef-flash": { - "input_cost_per_token": 9e-08, - "litellm_provider": "cloudflare", - "max_input_tokens": 65536, - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + "azure_ai/mistral-ocr-2505": { + "litellm_provider": "azure_ai", + "mode": "ocr", + "ocr_cost_per_page": 0.001, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/" }, - "cloudflare/@cf/cloudflare/clef": { - "input_cost_per_token": 2.4e-07, - "litellm_provider": "cloudflare", - "max_input_tokens": 65536, - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + "azure_ai/mistral-ocr-2512": { + "litellm_provider": "azure_ai", + "mode": "ocr", + "ocr_cost_per_page": 0.002, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/" }, - "cloudflare/@cf/cloudflare/clef-flash": { - "input_cost_per_token": 9e-08, - "litellm_provider": "cloudflare", - "max_input_tokens": 65536, - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://developers.cloudflare.com/workers-ai/platform/pricing/" + "anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "perplexity/pplx-decider-v1-27b": { - "input_cost_per_token": 4e-08, - "litellm_provider": "perplexity", - "max_input_tokens": 262144, - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://docs.perplexity.ai/api-reference/decisions-post" + "apac.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_creation_input_token_cost": 2.75e-06, + "input_cost_per_token": 2.2e-06, + "output_cost_per_token": 1.1e-05, + "cache_read_input_token_cost": 1.1e-07, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "strands_decider/strands-decider-2B-hobson-v19": { - "input_cost_per_token": 0.0, - "litellm_provider": "strands_decider", - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://huggingface.co/StrandsAgents/strands-decider-2B-hobson-v19", - "metadata": { - "notes": "Self-hosted decision model; infrastructure costs are paid separately" + "au.anthropic.claude-sonnet-5-5": { + "token_count_model": { + "model": "au.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + }, + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "azure_ai/claude-sonnet-5-5": { + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2027-09-29", + "input_cost_per_token": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01" + }, + "bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true + }, + "bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" } }, - "azure_ai/Microsoft-Decision-1": { - "input_cost_per_token": 4.2e-08, - "litellm_provider": "azure_ai", - "mode": "evaluation", - "output_cost_per_token": 0.0, - "source": "https://prices.azure.com/api/retail/prices?$filter=productName eq 'Microsoft Decision Models'" + "eu.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, - "claude-haiku-5-5": { + "global.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "global.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "jp.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "perplexity/anthropic/claude-sonnet-5-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_adaptive_thinking": true, + "supports_web_search": true, + "supports_function_calling": true, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-fable-5-1": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 2.5e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/anthropic/claude-opus-5-5": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, + "cache_read_input_token_cost": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6.1-sol": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6-sol": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6-astra": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_creation_input_token_cost": 1.25e-05, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/openai/gpt-6-luna": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token_above_272k_tokens": 2e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/google/gemini-3.8-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_sampling_params": false, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "cache_read_input_token_cost": 7.5e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "perplexity/xai/grok-4.7": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token_above_200k_tokens": 4e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, + "us-gov.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "bedrock_output_config_effort_ceiling": "xhigh", + "cache_creation_input_token_cost": 3e-06, + "cache_creation_input_token_cost_above_1hr": 4.8e-06, + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 2.4e-06, + "litellm_provider": "bedrock_converse", + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, + "supports_output_config": true, + "supports_parallel_tool_use_config": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-sonnet-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } + }, + "us.anthropic.claude-sonnet-5-5": { + "bedrock_converse_supports_strict_tools": false, + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_1hr": 4.4e-06, + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 2.2e-06, + "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "us.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, + "supports_tool_search": true, + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, + "supports_max_reasoning_effort": true, + "supports_output_config": true, + "bedrock_output_config_effort_ceiling": "xhigh", + "supports_parallel_tool_use_config": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" + }, + "vertex_ai/claude-sonnet-5-5": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/claude-sonnet-5-5@default": { + "regional_endpoint_uplift_multiplier": 1.1, + "supports_mid_conversation_system": true, + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "supports_max_reasoning_effort": true, + "supports_forced_tool_use": false, + "thinking_always_on": true, + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "prism/deepseek-v4.1-flash": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 1.7e-07, + "litellm_provider": "prism", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 6.3e-07, + "source": "https://prisminference.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "prism/deepseek-v4-flash": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 1.7e-07, + "litellm_provider": "prism", + "max_input_tokens": 1000000, + "max_output_tokens": 384000, + "max_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 2.1e-07, + "source": "https://prisminference.com/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "global.xai.grok-4.7": { + "supports_regex_lookaround": false, + "supported_endpoints": ["/v1/chat/completions"], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_flex": 3e-06, + "output_cost_per_token_priority": 1.05e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html", + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.xai.grok-4.7": { + "supports_regex_lookaround": false, + "supported_endpoints": ["/v1/chat/completions"], + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": true, + "supports_bedrock_runtime_chat_completions_response_format": true, + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_flex": 2.75e-07, + "cache_read_input_token_cost_priority": 9.625e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_flex": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "output_cost_per_token_flex": 3.3e-06, + "output_cost_per_token_priority": 1.155e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html", + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05, + "cache_creation_input_token_cost_batches": 1.25e-06, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_creation_input_token_cost_ultrafast": 1.5e-05, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 2e-07, + "cache_read_input_token_cost_ultrafast": 6e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_batches": 2e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 4e-06, + "input_cost_per_token_ultrafast": 1.2e-05, + "litellm_provider": "openai", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, + "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, + "output_cost_per_token_above_272k_tokens_priority": 3e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 2e-05, + "output_cost_per_token_ultrafast": 6e-05, + "regional_processing_uplift_multiplier_eu": 1.1, + "regional_processing_uplift_multiplier_us": 1.1, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_cache_breakpoint": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_tool_search": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, + "global.openai.gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05, + "cache_creation_input_token_cost_ultrafast": 1.5e-05, + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06, + "cache_read_input_token_cost_ultrafast": 6e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05, + "input_cost_per_token_ultrafast": 1.2e-05, + "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05, + "output_cost_per_token_ultrafast": 6e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_bedrock_runtime_chat_completions_response_format": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_sampling_params": false, + "supports_xhigh_reasoning_effort": true + }, + "bedrock_mantle/openai.gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05, + "cache_creation_input_token_cost_ultrafast": 1.65e-05, + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06, + "cache_read_input_token_cost_ultrafast": 6.6e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05, + "input_cost_per_token_ultrafast": 1.32e-05, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "responses", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05, + "output_cost_per_token_ultrafast": 6.6e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_prompt_cache_breakpoint": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "use_openai_responses_path": true + }, + "us.openai.gpt-6.1-sol": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05, + "cache_creation_input_token_cost_ultrafast": 1.65e-05, + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-07, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06, + "cache_read_input_token_cost_ultrafast": 6.6e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_above_272k_tokens": 4.4e-06, + "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05, + "input_cost_per_token_ultrafast": 1.32e-05, + "litellm_provider": "bedrock_converse", + "supports_bedrock_converse_tool_result_images": false, + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_above_272k_tokens": 1.65e-05, + "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05, + "output_cost_per_token_ultrafast": 6.6e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_bedrock_runtime_chat_completions_response_format": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_sampling_params": false, + "supports_xhigh_reasoning_effort": true + }, + "vertex_ai/gemini-3.8-flash-tts": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "audio_speech", + "output_cost_per_audio_token": 9e-06, + "output_cost_per_token": 9e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "vertex_ai/gemini-3.8-flash-lite-tts": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "audio_speech", + "output_cost_per_audio_token": 6e-06, + "output_cost_per_token": 6e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "vertex_ai/xai/grok-4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 524288, + "max_output_tokens": 524288, + "max_tokens": 524288, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/kimi-k2-thinking": { + "deprecation_date": "2026-03-29", + "input_cost_per_token": 6e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_video_input": false, + "supports_vision": false + }, + "global.zai.glm-5.3": { + "cache_creation_input_token_cost": 2.1e-06, + "cache_creation_input_token_cost_batches": 1.05e-06, + "cache_creation_input_token_cost_flex": 1.05e-06, + "cache_creation_input_token_cost_priority": 3.675e-06, + "cache_read_input_token_cost": 3.12e-07, + "cache_read_input_token_cost_batches": 1.56e-07, + "cache_read_input_token_cost_flex": 1.56e-07, + "cache_read_input_token_cost_priority": 5.46e-07, + "input_cost_per_token": 1.68e-06, + "input_cost_per_token_batches": 8.4e-07, + "input_cost_per_token_flex": 8.4e-07, + "input_cost_per_token_priority": 2.94e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.28e-06, + "output_cost_per_token_batches": 2.64e-06, + "output_cost_per_token_flex": 2.64e-06, + "output_cost_per_token_priority": 9.24e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "us.zai.glm-5.3": { + "cache_creation_input_token_cost": 2.31e-06, + "cache_creation_input_token_cost_batches": 1.155e-06, + "cache_creation_input_token_cost_flex": 1.155e-06, + "cache_creation_input_token_cost_priority": 4.0425e-06, + "cache_read_input_token_cost": 3.432e-07, + "cache_read_input_token_cost_batches": 1.716e-07, + "cache_read_input_token_cost_flex": 1.716e-07, + "cache_read_input_token_cost_priority": 6.006e-07, + "input_cost_per_token": 1.848e-06, + "input_cost_per_token_batches": 9.24e-07, + "input_cost_per_token_flex": 9.24e-07, + "input_cost_per_token_priority": 3.234e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.808e-06, + "output_cost_per_token_batches": 2.904e-06, + "output_cost_per_token_flex": 2.904e-06, + "output_cost_per_token_priority": 1.0164e-05, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_native_structured_output": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "amazon.nova-2-5-sonic": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 3.3e-07, + "litellm_provider": "bedrock", + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2.75e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", + "supports_audio_input": true, + "supports_audio_output": true + }, + "azure/model-router": { + "comment": "The flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it", + "deprecation_date": "2027-05-20", + "input_cost_per_token": 1.4e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/model-router/", + "supports_vision": true + }, + "azure/whisper": { + "deprecation_date": "2026-12-15", + "input_cost_per_second": 0.0001, + "litellm_provider": "azure", + "mode": "audio_transcription", + "output_cost_per_second": 0.0001, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "gemini/gemini-nano-banana-2.1": { + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, + "rpm": 1000.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000.0, + "web_search_billing_unit": "per_query" + }, + "gemini-nano-banana-2.1": { + "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_priority": 2.7e-07, + "input_cost_per_image": 0.00168, + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_priority": 1.35e-05, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "vertex_ai/gemini-nano-banana-2.1": { + "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, + "cache_read_input_token_cost_priority": 2.7e-07, + "input_cost_per_image": 0.00168, + "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, + "input_cost_per_token_priority": 2.7e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0336, + "output_cost_per_image_token": 3e-05, + "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, + "output_cost_per_token_priority": 1.35e-05, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/images/generations", + "/v1/images/edits", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "azure_ai/grok-4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "deprecation_date": "2027-10-05", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://docs.x.ai/developers/models/grok-4.7", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "in.moonshotai.kimi-k3": { + "cache_creation_input_token_cost": 4.125e-06, + "cache_creation_input_token_cost_flex": 2.0625e-06, + "cache_creation_input_token_cost_priority": 7.21875e-06, + "cache_read_input_token_cost": 3.3e-07, + "cache_read_input_token_cost_flex": 1.65e-07, + "cache_read_input_token_cost_priority": 5.775e-07, + "input_cost_per_token": 3.3e-06, + "input_cost_per_token_flex": 1.65e-06, + "input_cost_per_token_priority": 5.775e-06, + "litellm_provider": "bedrock_converse", + "token_count_framing": 64, + "token_count_tokenizer": "kimi_k3", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_flex": 8.25e-06, + "output_cost_per_token_priority": 2.8875e-05, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3.md", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_prompt_cache_breakpoint": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_regex_lookaround": false, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, +"claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens_batches": 2.5e-07, "output_cost_per_token_above_100k_tokens_batches": 1.25e-06, "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07, @@ -77689,6 +75406,11 @@ "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -77714,6 +75436,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77750,6 +75473,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77765,6 +75489,11 @@ "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "au.anthropic.claude-haiku-5-5": { + "token_count_model": { + "model": "au.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "ap-southeast-4" + }, "input_cost_per_token_above_100k_tokens": 5.5e-07, "output_cost_per_token_above_100k_tokens": 2.75e-06, "cache_creation_input_token_cost_above_100k_tokens": 6.875e-07, @@ -77801,6 +75530,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77881,6 +75611,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -77922,6 +75653,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -77931,7 +75663,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-haiku-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "eu.anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5.5e-07, @@ -77970,6 +75707,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -77991,6 +75729,11 @@ "cache_read_input_token_cost": 1e-08, "input_cost_per_token": 1e-07, "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "global.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -78016,6 +75759,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -78062,6 +75806,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -78112,6 +75857,7 @@ "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, @@ -78121,7 +75867,12 @@ "supports_sampling_params": false, "supports_tool_choice": true, "supports_vision": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "token_count_model": { + "model": "anthropic.claude-haiku-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-gov-west-1" + } }, "us.anthropic.claude-haiku-5-5": { "input_cost_per_token_above_100k_tokens": 5.5e-07, @@ -78135,6 +75886,11 @@ "cache_read_input_token_cost": 1.1e-08, "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock_converse", + "token_count_model": { + "model": "us.anthropic.claude-opus-5-5", + "litellm_provider": "bedrock_mantle", + "region": "us-east-1" + }, "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -78160,6 +75916,7 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, + "supports_bedrock_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", @@ -78259,89 +76016,913 @@ "prompt_cache_min_tokens": 512, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "openrouter/anthropic/claude-haiku-5.5": { - "input_cost_per_token": 1e-07, + "microsoft_365_copilot/chat": { + "litellm_provider": "microsoft_365_copilot", + "mode": "chat", + "supports_mid_conversation_system": true, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0 + }, + "us.twelvelabs.pegasus-1-5-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "litellm_provider": "bedrock", + "max_input_tokens": 261120, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", + "supports_video_input": true + }, + "global.twelvelabs.pegasus-1-5-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "litellm_provider": "bedrock", + "max_input_tokens": 261120, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", + "supports_video_input": true + }, + "twelvelabs.pegasus-1-5-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "litellm_provider": "bedrock", + "max_input_tokens": 261120, + "max_output_tokens": 98304, + "max_tokens": 98304, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-twelvelabs-pegasus-v1-5.html", + "supports_video_input": true + }, + "azure_ai/Microsoft-Decision-1": { + "input_cost_per_token": 4.2e-08, + "litellm_provider": "azure_ai", + "mode": "evaluation", + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=productName eq 'Microsoft Decision Models'" + }, + "gpt-rosalind-discovery": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://developers.openai.com/api/docs/pricing" + }, + "chatgpt/gpt-rosalind-discovery": { + "litellm_provider": "chatgpt", + "mode": "responses", + "source": "https://developers.openai.com/api/docs/pricing", + "supported_endpoints": [ + "/v1/responses" + ] + }, + "azure_ai/Cohere-Embed-V5-Fast": { + "deprecation_date": "2027-01-23", + "input_cost_per_image_token": 4e-07, + "input_cost_per_token": 8e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supported_modalities": [ + "text", + "image" + ], + "supports_embedding_image_input": true + }, + "azure_ai/Cohere-Embed-V5-Pro": { + "deprecation_date": "2027-01-23", + "input_cost_per_image_token": 4e-07, + "input_cost_per_token": 1.2e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=productName%20eq%20'Cohere%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supported_modalities": [ + "text", + "image" + ], + "supports_embedding_image_input": true + }, + "scaledown/extract": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_response_schema": false, + "supports_system_messages": false, + "supports_vision": false, + "supports_function_calling": false + }, + "scaledown/summarize": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": true, + "supports_vision": false, + "supports_function_calling": false + }, + "scaledown/compress": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": true, + "supports_function_calling": false, + "supports_vision": false + }, + "scaledown/classify": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": false, + "supports_vision": false, + "supports_function_calling": false + }, + "scaledown/decisions": { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "scaledown", + "mode": "chat", + "supports_system_messages": false, + "supports_vision": false, + "supports_function_calling": false + }, + "vertex_ai/gemini-robotics-er-2-preview": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "vertex_ai", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "gemini-robotics-er-2-preview": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "gemini/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 1.8e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 4096.0, + "rpm": 2000.0, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000.0, + "web_search_billing_unit": "per_query" + }, + "vertex_ai/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, + "cache_read_input_token_cost_flex": 5e-08, + "cache_read_input_token_cost_priority": 1.8e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token": 2e-06, + "input_cost_per_audio_token_batches": 1e-06, + "input_cost_per_audio_token_priority": 3.6e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 1.8e-05, + "prompt_cache_min_tokens": 6144.0, + "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "vertex_ai/gemini-4-argon-cyber-permissive": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "cache_read_input_token_cost_flex": 1e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "google_maps_grounding_cost_per_query": 0.014, + "input_cost_per_audio_token": 4e-06, + "input_cost_per_audio_token_batches": 2e-06, + "input_cost_per_audio_token_priority": 7.2e-06, + "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2e-06, + "input_cost_per_token_flex": 2e-06, + "input_cost_per_token_priority": 7.2e-06, + "litellm_provider": "vertex_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_reasoning_token": 2e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, + "output_cost_per_token_flex": 1e-05, + "output_cost_per_token_priority": 3.6e-05, + "prompt_cache_min_tokens": 6144.0, + "regional_endpoint_uplift_multiplier": 1.1, + "search_context_cost_per_query": {"search_context_size_low":0.014,"search_context_size_medium":0.014,"search_context_size_high":0.014}, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "web_search_billing_unit": "per_query" + }, + "github_copilot/gemini-4-argon": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_vision": true + }, + "openinfer/@oi/GLM-5.3-Flash": { + "max_tokens": 393216, + "max_input_tokens": 393216, + "max_output_tokens": 393216, + "input_cost_per_token": 1.95e-07, + "output_cost_per_token": 1.56e-06, + "litellm_provider": "openinfer", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://api.openinfer.ai/v1/models" + }, + "openinfer/@oi/Qwen3.5-27B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1.95e-07, + "output_cost_per_token": 1.56e-06, + "litellm_provider": "openinfer", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://api.openinfer.ai/v1/models" + }, + "openinfer/@oi/Qwen3.5-9B": { + "max_tokens": 100000, + "max_input_tokens": 100000, + "max_output_tokens": 100000, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "openinfer", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://api.openinfer.ai/v1/models" + }, + "xai/grok-voice-3.0": { + "input_cost_per_second": 0.001333333333333, + "input_cost_per_text_message": 0.004, + "litellm_provider": "xai", + "mode": "realtime", + "source": "https://docs.x.ai/developers/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "xai/grok-voice-latest": { + "input_cost_per_second": 0.001333333333333, + "input_cost_per_text_message": 0.004, + "litellm_provider": "xai", + "mode": "realtime", + "source": "https://docs.x.ai/developers/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "xai/grok-voice-2.0": { + "input_cost_per_second": 0.001333333333333, + "input_cost_per_text_message": 0.004, + "litellm_provider": "xai", + "mode": "realtime", + "source": "https://docs.x.ai/developers/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true + }, + "together_ai/nvidia/NVIDIA-Nemotron-3.5-Super-VL": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", "output_cost_per_token": 5e-07, - "cache_read_input_token_cost": 1e-08, - "cache_creation_input_token_cost": 1.25e-07, - "cache_creation_input_token_cost_above_1hr": 2e-07, - "input_cost_per_token_above_100k_tokens": 5e-07, - "output_cost_per_token_above_100k_tokens": 2.5e-06, - "cache_read_input_token_cost_above_100k_tokens": 5e-08, - "cache_creation_input_token_cost_above_100k_tokens": 6.25e-07, - "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06, - "litellm_provider": "openrouter", + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "jp.amazon.nova-2-lite-v1:0": { + "cache_read_input_token_cost": 9.9e-08, + "cache_read_input_token_cost_flex": 4.95e-08, + "cache_read_input_token_cost_priority": 1.7325e-07, + "input_cost_per_token": 3.96e-07, + "input_cost_per_token_batches": 1.98e-07, + "input_cost_per_token_flex": 1.98e-07, + "input_cost_per_token_priority": 6.93e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 3.311e-06, + "output_cost_per_token_batches": 1.6555e-06, + "output_cost_per_token_flex": 1.6555e-06, + "output_cost_per_token_priority": 5.79425e-06, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/ap-northeast-1/index.json", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, + "vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-deepseek_models", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_regions": [ + "global" + ], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/claude-opus-5-5-fast": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-10-01", + "input_cost_per_token": 8e-06, + "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://openrouter.ai/api/v1/models", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_web_search": true, + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": {"search_context_size_high":0.02,"search_context_size_low":0.02,"search_context_size_medium":0.02}, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models", "supports_adaptive_thinking": true, - "prompt_cache_min_tokens": 512, - "supports_sampling_params": false + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_mid_conversation_system": true, + "supports_native_structured_output": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_xhigh_reasoning_effort": true, + "thinking_always_on": true }, - "gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, - "cache_creation_input_token_cost_batches": 1.25e-06, - "cache_creation_input_token_cost_flex": 1.25e-06, - "cache_creation_input_token_cost_priority": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "cache_read_input_token_cost_above_272k_tokens_batches": 1e-07, - "cache_read_input_token_cost_above_272k_tokens_flex": 1e-07, - "cache_read_input_token_cost_above_272k_tokens_priority": 4e-07, - "cache_read_input_token_cost_batches": 5e-08, - "cache_read_input_token_cost_flex": 5e-08, - "cache_read_input_token_cost_priority": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "input_cost_per_token_above_272k_tokens_batches": 2e-06, - "input_cost_per_token_above_272k_tokens_flex": 2e-06, - "input_cost_per_token_above_272k_tokens_priority": 8e-06, - "input_cost_per_token_batches": 1e-06, - "input_cost_per_token_flex": 1e-06, - "input_cost_per_token_priority": 4e-06, - "litellm_provider": "openai", - "max_input_tokens": 922000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "baseten/meta-models/muse-spark-open": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "output_cost_per_token_above_272k_tokens_batches": 7.5e-06, - "output_cost_per_token_above_272k_tokens_flex": 7.5e-06, - "output_cost_per_token_above_272k_tokens_priority": 3e-05, - "output_cost_per_token_batches": 5e-06, - "output_cost_per_token_flex": 5e-06, - "output_cost_per_token_priority": 2e-05, - "regional_processing_uplift_multiplier_eu": 1.1, - "regional_processing_uplift_multiplier_us": 1.1, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://developers.openai.com/api/docs/pricing", + "output_cost_per_token": 4.25e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "max_tokens": 943718, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "source": "https://openrouter.ai/api/v1/models/nvidia/nemotron-3.5-super-vl/endpoints", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "together_ai/reflection/Beam-1.0-501B-A23B": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 4e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "baseten/reflection/Beam-1.0": { + "cache_read_input_token_cost": 1.3e-07, + "input_cost_per_token": 1.3e-06, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.3e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "nebius/reflection/beam": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/reflection%2Fbeam", + "supports_function_calling": true, + "supports_reasoning": true + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "baseten", + "max_input_tokens": 1048576, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://inference.baseten.co/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017": { + "cache_read_input_token_cost": 6e-09, + "cache_read_input_token_cost_priority": 7.5e-09, + "input_cost_per_token": 3e-07, + "input_cost_per_token_priority": 3.75e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_priority": 1.5e-06, + "source": "https://api.fireworks.ai/v1/serverless/models?format=nested", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "github_copilot/claude-sonnet-4.6": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-09-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", "supported_endpoints": [ "/v1/chat/completions", - "/v1/batch", + "/v1/messages" + ], + "supports_adaptive_thinking": true, + "supports_function_calling": true, + "supports_legacy_thinking": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/gpt-5.4-nano": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "github_copilot", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.25e-06, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/grok-4.5": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "deprecation_date": "2026-10-19", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/grok-4.6": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "github_copilot/grok-4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "github_copilot", + "max_input_tokens": 500000, + "max_output_tokens": 500000, + "max_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://raw.githubusercontent.com/github/docs/main/data/tables/copilot/models-and-pricing.yml", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.ai/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "meta/muse-image-1.0": { + "litellm_provider": "meta", + "mode": "image_generation", + "output_cost_per_image": 0.01, + "source": "https://dev.meta.ai/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits", "/v1/responses" ], "supported_modalities": [ @@ -78349,269 +76930,63 @@ "image" ], "supported_output_modalities": [ - "text" - ], - "supports_computer_use": true, + "image" + ] + }, + "fireworks_ai/accounts/fireworks/models/minimax-m3p1-flash": { + "cache_read_input_token_cost": 1.5e-08, + "cache_read_input_token_cost_priority": 2.25e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_priority": 2.25e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_priority": 9e-07, + "source": "https://platform.minimax.io/docs/guides/pricing", "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_native_streaming": true, - "supports_none_reasoning_effort": false, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_cache_breakpoint": true, - "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_vision": true }, - "azure_ai/gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "azure_ai", - "max_input_tokens": 922000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "meta/sam-3.1": { + "input_cost_per_image": 0.0025, + "litellm_provider": "meta", + "mode": "responses", + "source": "https://dev.meta.ai/docs/pricing-rate-limits.md", "supported_endpoints": [ - "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", - "image" + "image", + "video" ], "supported_output_modalities": [ "text" - ], - "supports_computer_use": true, - "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_native_streaming": true, - "supports_none_reasoning_effort": false, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_cache_breakpoint": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + ] }, - "azure/gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "azure", - "max_input_tokens": 922000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us": { + "cache_read_input_token_cost": 9e-09, + "cache_read_input_token_cost_priority": 1.125e-08, + "input_cost_per_token": 4.5e-07, + "input_cost_per_token_priority": 5.625e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_computer_use": true, + "output_cost_per_token": 1.8e-06, + "output_cost_per_token_priority": 2.25e-06, + "source": "https://docs.fireworks.ai/serverless/us-only-serverless", "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_native_streaming": true, - "supports_none_reasoning_effort": false, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true - }, - "azure/gpt-6.1-sol-2026-09-29": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "azure", - "max_input_tokens": 922000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_computer_use": true, - "supports_function_calling": true, - "supports_max_reasoning_effort": true, - "supports_minimal_reasoning_effort": false, - "supports_native_streaming": true, - "supports_none_reasoning_effort": false, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true, - "supports_xhigh_reasoning_effort": true - }, - "openrouter/openai/gpt-6.1-sol": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6.1-sol-pro": { - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "cache_read_input_token_cost": 1e-07, - "cache_read_input_token_cost_above_272k_tokens": 2e-07, - "input_cost_per_token": 2e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6.1-sol-pro:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_above_272k_tokens": 1e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true - }, - "openrouter/openai/gpt-6.1-sol:batch": { - "cache_creation_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 2.5e-06, - "cache_read_input_token_cost": 5e-08, - "cache_read_input_token_cost_above_272k_tokens": 1e-07, - "input_cost_per_token": 1e-06, - "input_cost_per_token_above_272k_tokens": 2e-06, - "litellm_provider": "openrouter", - "max_input_tokens": 1050000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 5e-06, - "output_cost_per_token_above_272k_tokens": 7.5e-06, - "source": "https://openrouter.ai/api/v1/models", - "supports_audio_input": false, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_web_search": true + "supports_vision": true } } From 9c28744ad56325455b54db8a9a9b5a683f73e5f1 Mon Sep 17 00:00:00 2001 From: Mrinal Chanshetty Date: Tue, 20 Oct 2026 17:34:08 -0700 Subject: [PATCH 60/66] test: retarget cost-map tests to the rows mirrored from main --- .../test_tool_call_cost_tracking.py | 6 +-- .../test_fallback_generalizations.py | 11 ++--- .../test_get_model_cost_map.py | 1 - .../test_agentcore_search_transformation.py | 6 ++- .../test_databricks_cost_calculator.py | 3 ++ tests/unit/test_cost_calculator.py | 8 ++-- tests/unit/test_model_prices_schema.py | 14 +++++- tests/unit/test_utils.py | 44 +++++++++++++++++++ 8 files changed, 76 insertions(+), 17 deletions(-) diff --git a/tests/unit/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py b/tests/unit/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py index 41a2d19b8ab..58ee36d87ad 100644 --- a/tests/unit/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py +++ b/tests/unit/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py @@ -363,15 +363,15 @@ def test_web_search_provider_prefix_fallback_does_not_misprice_non_gemini_model( Regression for the provider-prefix fallback in _handle_web_search_cost. When the initial get_model_info lookup fails for a "/"-containing model, the retry re-resolves model_info from the prefix and must adopt that prefix's provider for routing. Otherwise an unrelated model - (here OpenRouter, which carries no web search pricing) is re-resolved but still routed through + (here Azure, which carries no web search pricing) is re-resolved but still routed through the request's vertex_ai Gemini calculator, which charges its $0.035 per_prompt default for a model that should cost nothing for web search. """ from litellm.types.utils import PromptTokensDetailsWrapper, Usage - model = "openrouter/google/gemini-3.1-flash-lite" + model = "azure/gpt-4o" model_info = litellm.get_model_info(model) - assert model_info["litellm_provider"] == "openrouter" + assert model_info["litellm_provider"] == "azure" assert not model_info.get("search_context_cost_per_query") usage = Usage( diff --git a/tests/unit/litellm_core_utils/test_fallback_generalizations.py b/tests/unit/litellm_core_utils/test_fallback_generalizations.py index f70b52a7026..7b96a1d693c 100644 --- a/tests/unit/litellm_core_utils/test_fallback_generalizations.py +++ b/tests/unit/litellm_core_utils/test_fallback_generalizations.py @@ -970,19 +970,16 @@ def test_shipped_tool_search_rule_version_boundaries(shipped_cost_map, model, pr def test_shipped_tool_search_rule_fills_mapped_claude_entries_without_flag(shipped_cost_map): """A mapped Claude 4.5+ entry with no supports_tool_search key gets it from the rule - on Anthropic direct, Vertex and Bedrock, a mapped pre-4.5 entry stays without one, - and Azure Foundry and reseller copies of the same model are not touched.""" + on Anthropic direct, Azure Foundry, Vertex and Bedrock, a mapped pre-4.5 entry stays + without one, and reseller copies of the same model are not touched.""" for key, model, provider in ( ("claude-opus-4-7", "claude-opus-4-7", "anthropic"), + ("azure_ai/claude-opus-5", "claude-opus-5", "azure_ai"), ("vertex_ai/claude-opus-5", "claude-opus-5", "vertex_ai"), ): assert "supports_tool_search" not in litellm.model_cost[key] assert litellm.get_model_info(model, custom_llm_provider=provider)["supports_tool_search"] is True - assert "supports_tool_search" not in litellm.model_cost["azure_ai/claude-opus-5"] - azure_opus_5_info = litellm.get_model_info("claude-opus-5", custom_llm_provider="azure_ai") - assert azure_opus_5_info.get("supports_tool_search") is None - assert match_fill_missing_generalizations("claude-opus-5", "bedrock")["supports_tool_search"] is True - assert "supports_tool_search" not in match_fill_missing_generalizations("claude-opus-5", "azure_ai") + assert match_fill_missing_generalizations("claude-opus-5", "azure_ai")["supports_tool_search"] is True assert match_fill_missing_generalizations("claude-opus-5", "perplexity") is None diff --git a/tests/unit/litellm_core_utils/test_get_model_cost_map.py b/tests/unit/litellm_core_utils/test_get_model_cost_map.py index 00977d9c3ee..7a3cec592de 100644 --- a/tests/unit/litellm_core_utils/test_get_model_cost_map.py +++ b/tests/unit/litellm_core_utils/test_get_model_cost_map.py @@ -212,7 +212,6 @@ def test_shipped_backup_marks_claude_4_6_plus_adaptive_not_4_0(): "anthropic.claude-opus-4-8", "vertex_ai/claude-opus-4-6@default", "us.anthropic.claude-sonnet-4-6", - "openrouter/anthropic/claude-opus-4.7", "azure_ai/claude-opus-4-7", ]: assert backup[adaptive]["supports_adaptive_thinking"] is True, adaptive diff --git a/tests/unit/llms/bedrock/search/test_agentcore_search_transformation.py b/tests/unit/llms/bedrock/search/test_agentcore_search_transformation.py index 20bf65ee385..a20444ceca5 100644 --- a/tests/unit/llms/bedrock/search/test_agentcore_search_transformation.py +++ b/tests/unit/llms/bedrock/search/test_agentcore_search_transformation.py @@ -634,4 +634,8 @@ class TestAgentCoreSearchEdgeCases: from litellm.search.cost_calculator import search_provider_cost_per_query monkeypatch.setattr(litellm, "model_cost", GetModelCostMap.load_local_model_cost_map()) - assert search_provider_cost_per_query(model="agentcore/search", custom_llm_provider="agentcore") == (0.0, 0.0) + price_per_query = litellm.model_cost["agentcore/search"]["input_cost_per_query"] + assert price_per_query > 0 + assert search_provider_cost_per_query( + model="agentcore/search", custom_llm_provider="agentcore", number_of_queries=3 + ) == (3 * price_per_query, 0.0) diff --git a/tests/unit/llms/databricks/test_databricks_cost_calculator.py b/tests/unit/llms/databricks/test_databricks_cost_calculator.py index de0e547c0cd..494b99c1d11 100644 --- a/tests/unit/llms/databricks/test_databricks_cost_calculator.py +++ b/tests/unit/llms/databricks/test_databricks_cost_calculator.py @@ -16,6 +16,7 @@ NEW_MODELS: Final = ( "databricks/databricks-claude-opus-4-7", "databricks/databricks-claude-opus-4-8", "databricks/databricks-claude-opus-5", + "databricks/databricks-claude-opus-5-5", "databricks/databricks-claude-sonnet-5", "databricks/databricks-claude-fable-5", "databricks/databricks-claude-fable-5-1", @@ -32,6 +33,7 @@ PRICE_FIELDS: Final = ( "cache_read_input_token_cost", ) PUBLISHED_DBU_PER_MILLION: Final = { + "databricks/databricks-claude-opus-5-5": ("57.143", "285.714", "71.429", "2.857"), "databricks/databricks-claude-fable-5-1": ("142.858", "714.286", "178.572", "3.572"), "databricks/databricks-claude-fable-5": ("142.858", "714.286", "178.572", "14.286"), "databricks/databricks-claude-opus-5": ("71.429", "357.143", "89.286", "7.143"), @@ -118,6 +120,7 @@ def _dollars_per_token(dbu_per_million: str) -> float: [ "databricks/databricks-claude-opus-4-8", "databricks/databricks-claude-opus-5", + "databricks/databricks-claude-opus-5-5", "databricks/databricks-claude-sonnet-5", ], ) diff --git a/tests/unit/test_cost_calculator.py b/tests/unit/test_cost_calculator.py index 1e9b7f596bf..fa284ff71cf 100644 --- a/tests/unit/test_cost_calculator.py +++ b/tests/unit/test_cost_calculator.py @@ -964,9 +964,9 @@ def test_per_query_priced_rerank_deployment_completion_cost_is_nonzero(): router: Final = Router( model_list=[ { - "model_name": "semantic-ranker-default-004", + "model_name": "semantic-ranker-custom-test", "litellm_params": { - "model": "vertex_ai/semantic-ranker-default-004", + "model": "vertex_ai/semantic-ranker-custom-test", "vertex_project": "test-project", "vertex_location": "us-east5", }, @@ -975,7 +975,7 @@ def test_per_query_priced_rerank_deployment_completion_cost_is_nonzero(): ] ) router_model_id: Final = router.model_list[0]["model_info"]["id"] - assert litellm.model_cost["vertex_ai/semantic-ranker-default-004"].get("input_cost_per_query") is None + assert litellm.model_cost.get("vertex_ai/semantic-ranker-custom-test", {}).get("input_cost_per_query") is None response: Final = RerankResponse( id="vertex_ai_rerank_test", @@ -985,7 +985,7 @@ def test_per_query_priced_rerank_deployment_completion_cost_is_nonzero(): cost: Final = completion_cost( completion_response=response, - model="vertex_ai/semantic-ranker-default-004", + model="vertex_ai/semantic-ranker-custom-test", custom_llm_provider="vertex_ai", call_type="arerank", custom_pricing=True, diff --git a/tests/unit/test_model_prices_schema.py b/tests/unit/test_model_prices_schema.py index 211a43d2574..709ed93639a 100644 --- a/tests/unit/test_model_prices_schema.py +++ b/tests/unit/test_model_prices_schema.py @@ -509,7 +509,19 @@ def test_deepseek_rows_bill_half_rate_outside_weekday_peak_hours(path: Path): assert all(name in rows for name in DEEPSEEK_PRICED_ROWS) -PROVIDER_LABELS_WITHOUT_A_MODEL_SET: Final = frozenset({"sagemaker", "bedrock_converse"}) +PROVIDER_LABELS_WITHOUT_A_MODEL_SET: Final = frozenset( + { + "sagemaker", + "bedrock_converse", + "coralbricks", + "inferenceapis", + "microsoft_365_copilot", + "openinfer", + "prism", + "sail", + "scaledown", + } +) MODES_SERVED_OUTSIDE_THE_LLM_PROVIDER_REGISTRY: Final = frozenset({"search", "evaluation"}) VERTEX_FAMILIES_A_VERTEX_WILDCARD_GRANT_DOES_NOT_LIST: Final = frozenset( { diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py index b9cf6abd360..a8385b8340d 100644 --- a/tests/unit/test_utils.py +++ b/tests/unit/test_utils.py @@ -756,6 +756,35 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "type": "object", "properties": { "supports_computer_use": {"type": "boolean"}, + "cache_creation_input_token_cost_above_272k_tokens_decisions": {"type": "number"}, + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": {"type": "number"}, + "cache_creation_input_token_cost_decisions": {"type": "number"}, + "cache_creation_input_token_cost_ultrafast": {"type": "number"}, + "cache_read_input_token_cost_above_272k_tokens_decisions": {"type": "number"}, + "cache_read_input_token_cost_above_272k_tokens_ultrafast": {"type": "number"}, + "cache_read_input_token_cost_balanced": {"type": "number"}, + "cache_read_input_token_cost_decisions": {"type": "number"}, + "cache_read_input_token_cost_ultrafast": {"type": "number"}, + "cost_per_second": {"type": "number"}, + "explicit_cache_read_input_token_cost": {"type": "number"}, + "input_cost_per_token_above_272k_tokens_decisions": {"type": "number"}, + "input_cost_per_token_above_272k_tokens_ultrafast": {"type": "number"}, + "input_cost_per_token_balanced": {"type": "number"}, + "input_cost_per_token_decisions": {"type": "number"}, + "input_cost_per_token_ultrafast": {"type": "number"}, + "output_cost_per_image_token_batches": {"type": "number"}, + "output_cost_per_token_above_272k_tokens_decisions": {"type": "number"}, + "output_cost_per_token_above_272k_tokens_ultrafast": {"type": "number"}, + "output_cost_per_token_balanced": {"type": "number"}, + "output_cost_per_token_decisions": {"type": "number"}, + "output_cost_per_token_ultrafast": {"type": "number"}, + "supports_bedrock_converse_tool_result_images": {"type": "boolean"}, + "supports_bedrock_native_structured_output": {"type": "boolean"}, + "supports_bedrock_runtime_chat_completions_inline_reasoning": {"type": "boolean"}, + "supports_box_questions": {"type": "boolean"}, + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": {"type": "boolean"}, + "supports_bedrock_runtime_chat_completions_response_format": {"type": "boolean"}, + "supports_regex_lookaround": {"type": "boolean"}, "cache_creation_input_audio_token_cost": {"type": "number"}, "cache_creation_input_token_cost": {"type": "number"}, "cache_creation_input_token_cost_above_1hr": {"type": "number"}, @@ -833,6 +862,10 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "input_cost_per_request": {"type": "number"}, "input_cost_per_second": {"type": "number"}, "input_cost_per_token": {"type": "number"}, + "cache_read_input_token_cost_above_200k_tokens_batches": {"type": "number"}, + "input_cost_per_token_above_200k_tokens_batches": {"type": "number"}, + "output_cost_per_token_above_200k_tokens_batches": {"type": "number"}, + "input_cost_per_text_message": {"type": "number"}, "input_cost_per_token_above_128k_tokens": {"type": "number"}, "input_cost_per_audio_token_batches": {"type": "number"}, "input_cost_per_image_token_batches": {"type": "number"}, @@ -868,6 +901,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "image_edit", "embedding", "evaluation", + "extraction", "guardrail", "image_generation", "video_generation", @@ -1034,6 +1068,16 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "type": "object", "additionalProperties": {"type": "number"}, }, + "search_free_requests": { + "type": "object", + "properties": { + "count": {"type": "integer", "minimum": 1}, + "period": {"type": "string", "enum": ["day", "month"]}, + "shared_group": {"type": "string"}, + }, + "required": ["count", "period", "shared_group"], + "additionalProperties": False, + }, "search_context_cost_per_query": { "type": "object", "properties": { From b8e89a881b87585b46c3369df6c072cff6b76f87 Mon Sep 17 00:00:00 2001 From: Mrinal Chanshetty Date: Tue, 20 Oct 2026 17:47:02 -0700 Subject: [PATCH 61/66] chore(cost-map): accept the mirrored map's search_free_requests and token_count_model.litellm_provider in the schema --- ci_cd/generate_model_prices_schema.py | 14 +- model_prices_and_context_window.schema.json | 201 +++++++++++++++++--- 2 files changed, 183 insertions(+), 32 deletions(-) diff --git a/ci_cd/generate_model_prices_schema.py b/ci_cd/generate_model_prices_schema.py index a5a4b7f6f3b..73d8d2649bf 100644 --- a/ci_cd/generate_model_prices_schema.py +++ b/ci_cd/generate_model_prices_schema.py @@ -62,6 +62,17 @@ OFF_PEAK_WINDOW: Final[JsonSchema] = { } OBJECT_KEYS: dict[str, JsonSchema] = { + "search_free_requests": { + "type": "object", + "description": "Free Google Search grounding requests per period, shared across models in the same shared_group.", + "required": ["count", "period", "shared_group"], + "additionalProperties": False, + "properties": { + "count": {"type": "integer", "minimum": 0}, + "period": {"type": "string", "enum": ["day", "month"]}, + "shared_group": {"type": "string", "pattern": "\\S"}, + }, + }, "off_peak_pricing": { "type": "object", "description": "Rates that replace the same-named base fields while the request falls inside the stated UTC windows.", @@ -111,8 +122,9 @@ OBJECT_KEYS: dict[str, JsonSchema] = { "properties": { "model": NON_BLANK_STRING, "region": NON_BLANK_STRING, + "litellm_provider": {"type": "string", "enum": ["bedrock", "bedrock_mantle"]}, }, - "description": "Model that counts tokens for this one, and the AWS region its count API runs in.", + "description": "Model that counts tokens for this one, its counting provider, and the AWS region its count API runs in.", }, } diff --git a/model_prices_and_context_window.schema.json b/model_prices_and_context_window.schema.json index 0060f821ba3..d4dfeb25429 100644 --- a/model_prices_and_context_window.schema.json +++ b/model_prices_and_context_window.schema.json @@ -93,11 +93,6 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, - "cache_creation_input_token_cost_above_128k_tokens": { - "type": "number", - "minimum": 0, - "description": "Rate applied once the prompt exceeds the token threshold in the field name." - }, "cache_creation_input_token_cost_above_1hr": { "type": "number", "minimum": 0, @@ -118,11 +113,6 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, - "cache_creation_input_token_cost_above_256k_tokens": { - "type": "number", - "minimum": 0, - "description": "Rate applied once the prompt exceeds the token threshold in the field name." - }, "cache_creation_input_token_cost_above_272k_tokens": { "type": "number", "minimum": 0, @@ -133,6 +123,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "cache_creation_input_token_cost_above_272k_tokens_decisions": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "cache_creation_input_token_cost_above_272k_tokens_flex": { "type": "number", "minimum": 0, @@ -143,7 +138,7 @@ "minimum": 0, "description": "Priority service-tier rate for the same-named base field." }, - "cache_creation_input_token_cost_above_32k_tokens": { + "cache_creation_input_token_cost_above_272k_tokens_ultrafast": { "type": "number", "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." @@ -152,6 +147,10 @@ "type": "number", "minimum": 0 }, + "cache_creation_input_token_cost_decisions": { + "type": "number", + "minimum": 0 + }, "cache_creation_input_token_cost_flex": { "type": "number", "minimum": 0, @@ -162,6 +161,10 @@ "minimum": 0, "description": "Priority service-tier rate for the same-named base field." }, + "cache_creation_input_token_cost_ultrafast": { + "type": "number", + "minimum": 0 + }, "cache_read_input_audio_token_cost": { "type": "number", "minimum": 0 @@ -185,12 +188,12 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, - "cache_read_input_token_cost_above_128k_tokens": { + "cache_read_input_token_cost_above_200k_tokens": { "type": "number", "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, - "cache_read_input_token_cost_above_200k_tokens": { + "cache_read_input_token_cost_above_200k_tokens_batches": { "type": "number", "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." @@ -200,11 +203,6 @@ "minimum": 0, "description": "Priority service-tier rate for the same-named base field." }, - "cache_read_input_token_cost_above_256k_tokens": { - "type": "number", - "minimum": 0, - "description": "Rate applied once the prompt exceeds the token threshold in the field name." - }, "cache_read_input_token_cost_above_272k_tokens": { "type": "number", "minimum": 0, @@ -215,6 +213,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "cache_read_input_token_cost_above_272k_tokens_decisions": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "cache_read_input_token_cost_above_272k_tokens_flex": { "type": "number", "minimum": 0, @@ -225,7 +228,7 @@ "minimum": 0, "description": "Priority service-tier rate for the same-named base field." }, - "cache_read_input_token_cost_above_32k_tokens": { + "cache_read_input_token_cost_above_272k_tokens_ultrafast": { "type": "number", "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." @@ -235,10 +238,18 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "cache_read_input_token_cost_balanced": { + "type": "number", + "minimum": 0 + }, "cache_read_input_token_cost_batches": { "type": "number", "minimum": 0 }, + "cache_read_input_token_cost_decisions": { + "type": "number", + "minimum": 0 + }, "cache_read_input_token_cost_flex": { "type": "number", "minimum": 0, @@ -249,6 +260,10 @@ "minimum": 0, "description": "Priority service-tier rate for the same-named base field." }, + "cache_read_input_token_cost_ultrafast": { + "type": "number", + "minimum": 0 + }, "citation_cost_per_token": { "type": "number", "minimum": 0 @@ -260,6 +275,10 @@ "comment": { "type": "string" }, + "cost_per_second": { + "type": "number", + "minimum": 0 + }, "default_reasoning_effort": { "type": "string", "description": "Reasoning effort the provider applies when the request omits reasoning_effort. Gates whether a non-default temperature or the top_p/logprobs sampling params are accepted, which hold only when the effort resolves to 'none'.", @@ -278,6 +297,10 @@ "format": "date", "pattern": "^\\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$" }, + "explicit_cache_read_input_token_cost": { + "type": "number", + "minimum": 0 + }, "gemini_audio_only_live": { "type": "boolean" }, @@ -361,6 +384,10 @@ "type": "number", "minimum": 0 }, + "input_cost_per_text_message": { + "type": "number", + "minimum": 0 + }, "input_cost_per_token": { "type": "number", "minimum": 0, @@ -386,16 +413,16 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "input_cost_per_token_above_200k_tokens_batches": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "input_cost_per_token_above_200k_tokens_priority": { "type": "number", "minimum": 0, "description": "Priority service-tier rate for the same-named base field." }, - "input_cost_per_token_above_256k_tokens": { - "type": "number", - "minimum": 0, - "description": "Rate applied once the prompt exceeds the token threshold in the field name." - }, "input_cost_per_token_above_272k_tokens": { "type": "number", "minimum": 0, @@ -406,6 +433,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "input_cost_per_token_above_272k_tokens_decisions": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "input_cost_per_token_above_272k_tokens_flex": { "type": "number", "minimum": 0, @@ -416,7 +448,7 @@ "minimum": 0, "description": "Priority service-tier rate for the same-named base field." }, - "input_cost_per_token_above_32k_tokens": { + "input_cost_per_token_above_272k_tokens_ultrafast": { "type": "number", "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." @@ -426,6 +458,10 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "input_cost_per_token_balanced": { + "type": "number", + "minimum": 0 + }, "input_cost_per_token_batches": { "type": "number", "minimum": 0, @@ -435,6 +471,10 @@ "type": "number", "minimum": 0 }, + "input_cost_per_token_decisions": { + "type": "number", + "minimum": 0 + }, "input_cost_per_token_flex": { "type": "number", "minimum": 0, @@ -445,6 +485,10 @@ "minimum": 0, "description": "Priority service-tier rate for the same-named base field." }, + "input_cost_per_token_ultrafast": { + "type": "number", + "minimum": 0 + }, "input_cost_per_video_per_second": { "type": "number", "minimum": 0 @@ -509,6 +553,7 @@ "completion", "embedding", "evaluation", + "extraction", "guardrail", "image_edit", "image_generation", @@ -691,6 +736,10 @@ "type": "number", "minimum": 0 }, + "output_cost_per_image_token_batches": { + "type": "number", + "minimum": 0 + }, "output_cost_per_pixel": { "type": "number", "minimum": 0 @@ -753,16 +802,16 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "output_cost_per_token_above_200k_tokens_batches": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "output_cost_per_token_above_200k_tokens_priority": { "type": "number", "minimum": 0, "description": "Priority service-tier rate for the same-named base field." }, - "output_cost_per_token_above_256k_tokens": { - "type": "number", - "minimum": 0, - "description": "Rate applied once the prompt exceeds the token threshold in the field name." - }, "output_cost_per_token_above_272k_tokens": { "type": "number", "minimum": 0, @@ -773,6 +822,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "output_cost_per_token_above_272k_tokens_decisions": { + "type": "number", + "minimum": 0, + "description": "Rate applied once the prompt exceeds the token threshold in the field name." + }, "output_cost_per_token_above_272k_tokens_flex": { "type": "number", "minimum": 0, @@ -783,7 +837,7 @@ "minimum": 0, "description": "Priority service-tier rate for the same-named base field." }, - "output_cost_per_token_above_32k_tokens": { + "output_cost_per_token_above_272k_tokens_ultrafast": { "type": "number", "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." @@ -793,11 +847,19 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "output_cost_per_token_balanced": { + "type": "number", + "minimum": 0 + }, "output_cost_per_token_batches": { "type": "number", "minimum": 0, "description": "USD per generated token via the provider's batch API." }, + "output_cost_per_token_decisions": { + "type": "number", + "minimum": 0 + }, "output_cost_per_token_flex": { "type": "number", "minimum": 0, @@ -808,6 +870,10 @@ "minimum": 0, "description": "Priority service-tier rate for the same-named base field." }, + "output_cost_per_token_ultrafast": { + "type": "number", + "minimum": 0 + }, "output_cost_per_video_per_second": { "type": "number", "minimum": 0 @@ -889,6 +955,33 @@ }, "additionalProperties": false }, + "search_free_requests": { + "type": "object", + "description": "Free Google Search grounding requests per period, shared across models in the same shared_group.", + "required": [ + "count", + "period", + "shared_group" + ], + "additionalProperties": false, + "properties": { + "count": { + "type": "integer", + "minimum": 0 + }, + "period": { + "type": "string", + "enum": [ + "day", + "month" + ] + }, + "shared_group": { + "type": "string", + "pattern": "\\S" + } + } + }, "source": { "type": "string", "description": "URL of the provider pricing/model page this entry was taken from." @@ -963,6 +1056,24 @@ "supports_audio_output": { "type": "boolean" }, + "supports_bedrock_converse_tool_result_images": { + "type": "boolean" + }, + "supports_bedrock_native_structured_output": { + "type": "boolean" + }, + "supports_bedrock_runtime_chat_completions_inline_reasoning": { + "type": "boolean" + }, + "supports_bedrock_runtime_chat_completions_response_format": { + "type": "boolean" + }, + "supports_bedrock_runtime_chat_completions_tools_with_reasoning": { + "type": "boolean" + }, + "supports_box_questions": { + "type": "boolean" + }, "supports_computer_use": { "type": "boolean" }, @@ -1035,6 +1146,9 @@ "supports_reasoning": { "type": "boolean" }, + "supports_regex_lookaround": { + "type": "boolean" + }, "supports_response_schema": { "type": "boolean" }, @@ -1133,6 +1247,31 @@ "minimum": 0, "description": "Tokens added once per request to a local count estimate, for the provider's chat framing." }, + "token_count_model": { + "type": "object", + "required": [ + "model" + ], + "additionalProperties": false, + "properties": { + "model": { + "type": "string", + "pattern": "\\S" + }, + "region": { + "type": "string", + "pattern": "\\S" + }, + "litellm_provider": { + "type": "string", + "enum": [ + "bedrock", + "bedrock_mantle" + ] + } + }, + "description": "Model that counts tokens for this one, its counting provider, and the AWS region its count API runs in." + }, "token_count_tokenizer": { "type": "string", "description": "Tokenizer litellm counts this model's requests with when the provider cannot count them.", From f13eb6d8fb810570617d306ee9eb81cf0273bf15 Mon Sep 17 00:00:00 2001 From: Mrinal Chanshetty Date: Tue, 20 Oct 2026 16:22:36 -0700 Subject: [PATCH 62/66] chore: bump litellm-enterprise 0.1.71 -> 0.1.71.post1 --- enterprise/pyproject.toml | 4 ++-- pyproject.toml | 2 +- uv.lock | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/enterprise/pyproject.toml b/enterprise/pyproject.toml index e5e54a3df2c..24260fea143 100644 --- a/enterprise/pyproject.toml +++ b/enterprise/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "litellm-enterprise" -version = "0.1.71" +version = "0.1.71.post1" description = "Package for LiteLLM Enterprise features" readme = "README.md" requires-python = ">=3.9" @@ -26,7 +26,7 @@ required-version = ">=0.10.9" module-root = "" [tool.commitizen] -version = "0.1.71" +version = "0.1.71.post1" version_files = [ "pyproject.toml:^version", "../pyproject.toml:litellm-enterprise==", diff --git a/pyproject.toml b/pyproject.toml index fc1ed7ffddc..6f79fe269a1 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -76,7 +76,7 @@ proxy = [ "httpx2>=2.5.0,<3", "pydantic>=2.12.0,<3", "litellm-proxy-extras==0.4.102.post1", - "litellm-enterprise==0.1.71", + "litellm-enterprise==0.1.71.post1", "RestrictedPython>=8.5,<9.0", "rich>=13.9.4,<14.0", "InquirerPy>=0.3.4,<1.0", diff --git a/uv.lock b/uv.lock index 5ff15093bae..94a75c3a14d 100644 --- a/uv.lock +++ b/uv.lock @@ -4964,7 +4964,7 @@ proxy-dev = [ [[package]] name = "litellm-enterprise" -version = "0.1.71" +version = "0.1.71.post1" source = { editable = "enterprise" } [[package]] From 810db3747d79b65ef06a5e2481a2e3696b96300a Mon Sep 17 00:00:00 2001 From: Mrinal Chanshetty Date: Tue, 20 Oct 2026 16:22:37 -0700 Subject: [PATCH 63/66] bump: version 1.104.5 --- pyproject.toml | 4 ++-- uv.lock | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/pyproject.toml b/pyproject.toml index 6f79fe269a1..c1416041522 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "litellm" -version = "1.104.4" +version = "1.104.5" description = "Library to easily interface with LLM API providers" readme = "README.md" requires-python = ">=3.10, <3.15" @@ -355,7 +355,7 @@ litellm-enterprise = { workspace = true } members = ["enterprise", "litellm-proxy-extras"] [tool.commitizen] -version = "1.104.4" +version = "1.104.5" version_files = [ "pyproject.toml:^version", ] diff --git a/uv.lock b/uv.lock index 94a75c3a14d..a3ece317f4d 100644 --- a/uv.lock +++ b/uv.lock @@ -4504,7 +4504,7 @@ wheels = [ [[package]] name = "litellm" -version = "1.104.4" +version = "1.104.5" source = { editable = "." } dependencies = [ { name = "aiohttp" }, From aa960d620a75f1282e8557754f4954e15e353c10 Mon Sep 17 00:00:00 2001 From: Mrinal Chanshetty Date: Tue, 20 Oct 2026 21:27:07 -0700 Subject: [PATCH 64/66] fix(anthropic): carry main's dangerous-tool-use beta map entries; skip worker-kill chaos test The bundled beta map stripped dangerous-tool-use-2026-09-03 for providers main supports it on, so safeguards requests went upstream without the beta whenever the proxy used the bundled map. The worker-SIGKILL chaos test needs OwnedProxy.replacing_worker, which this line's integration harness lacks. Co-Authored-By: Claude Opus 5.5 --- litellm/anthropic_beta_headers_config.json | 4 ++-- .../providers/test_anthropic_safeguards_beta_chaos.py | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/litellm/anthropic_beta_headers_config.json b/litellm/anthropic_beta_headers_config.json index 3a28d65e47c..dbc6060396a 100644 --- a/litellm/anthropic_beta_headers_config.json +++ b/litellm/anthropic_beta_headers_config.json @@ -46,7 +46,7 @@ "computer-use-2025-11-24": "computer-use-2025-11-24", "context-1m-2025-08-07": "context-1m-2025-08-07", "context-management-2025-06-27": "context-management-2025-06-27", - "dangerous-tool-use-2026-09-03": null, + "dangerous-tool-use-2026-09-03": "dangerous-tool-use-2026-09-03", "effort-2025-11-24": "effort-2025-11-24", "fast-mode-2026-02-01": null, "files-api-2025-04-14": "files-api-2025-04-14", @@ -217,7 +217,7 @@ "computer-use-2025-11-24": "computer-use-2025-11-24", "context-1m-2025-08-07": "context-1m-2025-08-07", "context-management-2025-06-27": "context-management-2025-06-27", - "dangerous-tool-use-2026-09-03": null, + "dangerous-tool-use-2026-09-03": "dangerous-tool-use-2026-09-03", "effort-2025-11-24": "effort-2025-11-24", "fast-mode-2026-02-01": "fast-mode-2026-02-01", "files-api-2025-04-14": "files-api-2025-04-14", diff --git a/tests/integration/providers/test_anthropic_safeguards_beta_chaos.py b/tests/integration/providers/test_anthropic_safeguards_beta_chaos.py index 0266bdc190f..40676400184 100644 --- a/tests/integration/providers/test_anthropic_safeguards_beta_chaos.py +++ b/tests/integration/providers/test_anthropic_safeguards_beta_chaos.py @@ -200,6 +200,7 @@ def _open_upstream_connections(pid: int, upstream: str) -> int: ) +@pytest.mark.skip(reason="Needs OwnedProxy.replacing_worker, which this stable line's integration harness does not have") @pytest.mark.timeout(180) async def test_worker_sigkill_mid_burst_leaves_the_sibling_sending_the_beta(gateway: Gateway, tmp_path: Path) -> None: calls: Final = _calls(20, stream=False) From 240d4157f84ed0b4a08624086ba7215991caa44b Mon Sep 17 00:00:00 2001 From: Yuneng Jiang Date: Tue, 20 Oct 2026 22:42:08 -0700 Subject: [PATCH 65/66] bump: litellm 1.104.5 -> 1.104.6, litellm-enterprise 0.1.71 -> 0.1.71.post1 --- enterprise/pyproject.toml | 4 ++-- pyproject.toml | 6 +++--- uv.lock | 4 ++-- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/enterprise/pyproject.toml b/enterprise/pyproject.toml index e5e54a3df2c..24260fea143 100644 --- a/enterprise/pyproject.toml +++ b/enterprise/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "litellm-enterprise" -version = "0.1.71" +version = "0.1.71.post1" description = "Package for LiteLLM Enterprise features" readme = "README.md" requires-python = ">=3.9" @@ -26,7 +26,7 @@ required-version = ">=0.10.9" module-root = "" [tool.commitizen] -version = "0.1.71" +version = "0.1.71.post1" version_files = [ "pyproject.toml:^version", "../pyproject.toml:litellm-enterprise==", diff --git a/pyproject.toml b/pyproject.toml index 970d67d443e..a844ccdeea3 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "litellm" -version = "1.104.5" +version = "1.104.6" description = "Library to easily interface with LLM API providers" readme = "README.md" requires-python = ">=3.10, <3.15" @@ -76,7 +76,7 @@ proxy = [ "httpx2>=2.5.0,<3", "pydantic>=2.12.0,<3", "litellm-proxy-extras==0.4.102.post1", - "litellm-enterprise==0.1.71", + "litellm-enterprise==0.1.71.post1", "RestrictedPython>=8.5,<9.0", "rich>=13.9.4,<14.0", "InquirerPy>=0.3.4,<1.0", @@ -355,7 +355,7 @@ litellm-enterprise = { workspace = true } members = ["enterprise", "litellm-proxy-extras"] [tool.commitizen] -version = "1.104.5" +version = "1.104.6" version_files = [ "pyproject.toml:^version", ] diff --git a/uv.lock b/uv.lock index 81106cf4722..36eaf65c521 100644 --- a/uv.lock +++ b/uv.lock @@ -4501,7 +4501,7 @@ wheels = [ [[package]] name = "litellm" -version = "1.104.5" +version = "1.104.6" source = { editable = "." } dependencies = [ { name = "aiohttp" }, @@ -4961,7 +4961,7 @@ proxy-dev = [ [[package]] name = "litellm-enterprise" -version = "0.1.71" +version = "0.1.71.post1" source = { editable = "enterprise" } [[package]] From 7b0e1596281bdd71e906ca3fc7aed21f8ef67bf4 Mon Sep 17 00:00:00 2001 From: Yuneng Jiang Date: Tue, 20 Oct 2026 22:42:33 -0700 Subject: [PATCH 66/66] bump: litellm 1.104.5 -> 1.104.6 --- pyproject.toml | 4 ++-- uv.lock | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/pyproject.toml b/pyproject.toml index c1416041522..24ef859796e 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "litellm" -version = "1.104.5" +version = "1.104.6" description = "Library to easily interface with LLM API providers" readme = "README.md" requires-python = ">=3.10, <3.15" @@ -355,7 +355,7 @@ litellm-enterprise = { workspace = true } members = ["enterprise", "litellm-proxy-extras"] [tool.commitizen] -version = "1.104.5" +version = "1.104.6" version_files = [ "pyproject.toml:^version", ] diff --git a/uv.lock b/uv.lock index a3ece317f4d..0714560846e 100644 --- a/uv.lock +++ b/uv.lock @@ -4504,7 +4504,7 @@ wheels = [ [[package]] name = "litellm" -version = "1.104.5" +version = "1.104.6" source = { editable = "." } dependencies = [ { name = "aiohttp" },