From db9eda19b4bb7a8c30cd93a037b45efd0b83b6d3 Mon Sep 17 00:00:00 2001 From: ryan-crabbe-berri Date: Mon, 26 Oct 2026 16:04:33 -0700 Subject: [PATCH 001/262] fix(http_handler): name the timeout phase and limit that fired instead of "after None seconds" (#48250) * fix(http_handler): name the timeout phase and the limit that fired instead of 'after None seconds' Every HTTP verb on both handlers raised litellm.Timeout with the per-call timeout argument interpolated into the message, which is None whenever the caller relied on the client default, and always said "Connection" even for a read timeout. One helper now reads the limit httpx actually enforced from the failed request and names the phase that fired Fixes #14635 * fix(rust_bridge): name the timeout phase in the vault timeout message to match the httpx handler * fix(http_handler): drop the unreachable timeout fallbacks httpx already rules out * refactor(rust_bridge): drop a doc comment that restated the timeout helper --- .../src/exception_mapping_utils/mod.rs | 65 +++++------ .../src/exception_mapping_utils/original.rs | 14 +++ .../python-bridge/src/secrets/provider.rs | 19 +-- .../crates/python-bridge/src/secrets/vault.rs | 18 ++- litellm/llms/custom_httpx/http_handler.py | 108 ++++++++---------- .../llms/custom_httpx/test_http_handler.py | 83 ++++++++++++++ 6 files changed, 195 insertions(+), 112 deletions(-) diff --git a/litellm-rust/crates/core-utils/src/exception_mapping_utils/mod.rs b/litellm-rust/crates/core-utils/src/exception_mapping_utils/mod.rs index 162d325e4f4..8b63fadf5a6 100644 --- a/litellm-rust/crates/core-utils/src/exception_mapping_utils/mod.rs +++ b/litellm-rust/crates/core-utils/src/exception_mapping_utils/mod.rs @@ -51,7 +51,7 @@ mod rules; mod status; mod vertex_ai; -pub use original::{ExceptionFamily, OriginalException}; +pub use original::{ExceptionFamily, OriginalException, TimeoutPhase}; pub use public::{MappedFailure, PublicError, UpstreamResponse}; use rules::{Rule, contains_any, first_match}; @@ -67,7 +67,6 @@ const TIMEOUT_MARKERS: &[&str] = &[ pub struct ExceptionContext { pub model: String, pub custom_llm_provider: String, - pub asynchronous: bool, pub vertex_project: Option, pub vertex_location: Option, pub model_group: Option, @@ -105,11 +104,12 @@ pub fn exception_type( (None, message.clone(), None) } OriginalException::Timeout { + phase, timeout_seconds, elapsed_seconds, } => ( None, - timeout_message(context.asynchronous, *timeout_seconds, *elapsed_seconds), + timeout_message(*phase, *timeout_seconds, *elapsed_seconds), None, ), }; @@ -161,21 +161,16 @@ fn family_rules(family: ExceptionFamily) -> &'static [Rule] { } } -/// The text the Python HTTP handler's timeout carries: the sync and async handlers word it -/// differently. -fn timeout_message( - asynchronous: bool, +/// The text the Python HTTP handler's timeout carries: the phase that expired and the limit +/// httpx enforced for it, both rendered as Python would print them. +pub fn timeout_message( + phase: TimeoutPhase, timeout_seconds: Option, elapsed_seconds: Option, ) -> String { let timeout = python_float(timeout_seconds); - if asynchronous { - let elapsed = - python_float(elapsed_seconds.map(|seconds| (seconds * 1000.0).round() / 1000.0)); - format!("Connection timed out. Timeout passed={timeout}, time taken={elapsed} seconds") - } else { - format!("Connection timed out after {timeout} seconds.") - } + let elapsed = python_float(elapsed_seconds.map(|seconds| (seconds * 1000.0).round() / 1000.0)); + format!("{phase} timed out. Timeout passed={timeout}, time taken={elapsed} seconds") } fn python_float(value: Option) -> String { @@ -356,6 +351,7 @@ mod tests { #[test] fn a_handler_timeout_is_a_408_without_a_response() { let original = OriginalException::Timeout { + phase: TimeoutPhase::Read, timeout_seconds: Some(0.5), elapsed_seconds: Some(0.5031), }; @@ -363,7 +359,7 @@ mod tests { mapped("mistral", &original), MappedFailure { error: PublicError::Timeout { status: 408 }, - message: "MistralException - Connection timed out after 0.5 seconds.".into(), + message: "MistralException - Read timed out. Timeout passed=0.5, time taken=0.503 seconds".into(), upstream: None, debug_info: DEBUG.into(), } @@ -440,39 +436,44 @@ mod tests { } #[rstest::rstest] - #[case::sync( - false, + #[case::connect(TimeoutPhase::Connect, "Connection timed out.")] + #[case::read(TimeoutPhase::Read, "Read timed out.")] + #[case::write(TimeoutPhase::Write, "Write timed out.")] + #[case::pool(TimeoutPhase::Pool, "Connection pool timed out.")] + fn timeout_text_names_the_phase_that_expired( + #[case] phase: TimeoutPhase, + #[case] expected: &str, + ) { + assert_eq!( + timeout_message(phase, Some(0.5), Some(0.5031)), + format!("{expected} Timeout passed=0.5, time taken=0.503 seconds") + ); + } + + #[rstest::rstest] + #[case::rounds_the_elapsed_time( Some(0.5), Some(0.5031), - "Connection timed out after 0.5 seconds." - )] - #[case::async_rounds_the_elapsed_time( - true, - Some(0.5), - Some(0.5031), - "Connection timed out. Timeout passed=0.5, time taken=0.503 seconds" + "Timeout passed=0.5, time taken=0.503 seconds" )] #[case::whole_seconds_keep_a_decimal( - true, Some(600.0), Some(2.0), - "Connection timed out. Timeout passed=600.0, time taken=2.0 seconds" + "Timeout passed=600.0, time taken=2.0 seconds" )] #[case::unknown_values_render_as_none( - true, None, None, - "Connection timed out. Timeout passed=None, time taken=None seconds" + "Timeout passed=None, time taken=None seconds" )] - fn timeout_text_follows_the_delivery_mode( - #[case] asynchronous: bool, + fn timeout_text_renders_durations_as_python_floats( #[case] timeout_seconds: Option, #[case] elapsed_seconds: Option, #[case] expected: &str, ) { assert_eq!( - timeout_message(asynchronous, timeout_seconds, elapsed_seconds), - expected + timeout_message(TimeoutPhase::Read, timeout_seconds, elapsed_seconds), + format!("Read timed out. {expected}") ); } diff --git a/litellm-rust/crates/core-utils/src/exception_mapping_utils/original.rs b/litellm-rust/crates/core-utils/src/exception_mapping_utils/original.rs index 4de67e6e7b5..6517b093bbd 100644 --- a/litellm-rust/crates/core-utils/src/exception_mapping_utils/original.rs +++ b/litellm-rust/crates/core-utils/src/exception_mapping_utils/original.rs @@ -10,6 +10,7 @@ pub enum OriginalException { message: String, }, Timeout { + phase: TimeoutPhase, timeout_seconds: Option, elapsed_seconds: Option, }, @@ -20,6 +21,19 @@ pub enum OriginalException { }, } +/// The httpx timeout that expired, spelled the way the Python HTTP handler names it. +#[derive(Clone, Copy, Debug, PartialEq, Eq, strum::Display, strum::VariantArray)] +pub enum TimeoutPhase { + #[strum(serialize = "Connection")] + Connect, + #[strum(serialize = "Read")] + Read, + #[strum(serialize = "Write")] + Write, + #[strum(serialize = "Connection pool")] + Pool, +} + /// Which provider-specific text rules apply before the shared status table. #[derive(Clone, Copy, Debug, PartialEq, Eq)] pub enum ExceptionFamily { diff --git a/litellm-rust/crates/python-bridge/src/secrets/provider.rs b/litellm-rust/crates/python-bridge/src/secrets/provider.rs index 568a0cd2228..5f4cd193fcf 100644 --- a/litellm-rust/crates/python-bridge/src/secrets/provider.rs +++ b/litellm-rust/crates/python-bridge/src/secrets/provider.rs @@ -88,20 +88,23 @@ fn aws_context( } fn read_timeout(value: Option<&Bound<'_, PyAny>>) -> PyResult> { - let Some(value) = value.filter(|value| !value.is_none()) else { - return Ok(None); - }; - let seconds = match value.extract::() { - Ok(value) => Some(value), - Err(_) => value.getattr("read")?.extract::>()?, - }; - seconds + read_timeout_seconds(value)? .map(|value| { Duration::try_from_secs_f64(value).map_err(|_| PyValueError::new_err("invalid timeout")) }) .transpose() } +pub(super) fn read_timeout_seconds(value: Option<&Bound<'_, PyAny>>) -> PyResult> { + let Some(value) = value.filter(|value| !value.is_none()) else { + return Ok(None); + }; + match value.extract::() { + Ok(value) => Ok(Some(value)), + Err(_) => value.getattr("read")?.extract::>(), + } +} + fn vault_context(params: Option<&Bound<'_, PyAny>>) -> PyResult { let params = params.and_then(|value| value.cast::().ok()); let nested = params diff --git a/litellm-rust/crates/python-bridge/src/secrets/vault.rs b/litellm-rust/crates/python-bridge/src/secrets/vault.rs index 46b29839fe4..79281662848 100644 --- a/litellm-rust/crates/python-bridge/src/secrets/vault.rs +++ b/litellm-rust/crates/python-bridge/src/secrets/vault.rs @@ -2,10 +2,12 @@ mod operation; pub(super) use operation::{Failure, FailureKind, FailureStage, delete, rotate, write}; +use litellm_core_utils::exception_mapping_utils::{TimeoutPhase, timeout_message}; use litellm_secrets::hashicorp::{Error, RawOperationError}; use pyo3::prelude::*; use super::mutation::{error_value, http_message, json_value}; +use super::provider::read_timeout_seconds; const HTTP_TRANSPORT_MODULE: &str = "litellm.rust_bridge.host.http_transport"; @@ -69,21 +71,17 @@ fn cause_message(py: Python<'_>, kind: FailureKind, context: &ErrorContext) -> P } FailureKind::Native(RawOperationError::Timeout { method, elapsed }) => { if method == "POST" { - let elapsed = py - .import("builtins")? - .call_method1("round", (elapsed.as_secs_f64(), 3))?; let kwargs = pyo3::types::PyDict::new(py); kwargs.set_item( "message", - format!( - "Connection timed out. Timeout passed={}, time taken={} seconds", - context.timeout.as_deref().unwrap_or("None"), - elapsed.str()? + timeout_message( + TimeoutPhase::Read, + context.timeout, + Some(elapsed.as_secs_f64()), ), )?; kwargs.set_item("model", "default-model-name")?; kwargs.set_item("llm_provider", "litellm-httpx-handler")?; - kwargs.set_item("headers", pyo3::types::PyDict::new(py))?; py.import("litellm.exceptions")? .getattr("Timeout")? .call((), Some(&kwargs))? @@ -159,7 +157,7 @@ fn response_text(py: Python<'_>, body: &[u8]) -> PyResult { #[derive(Default)] pub(super) struct ErrorContext { - timeout: Option, + timeout: Option, aiohttp: bool, } @@ -173,7 +171,7 @@ impl ErrorContext { return Ok(Self::default()); } Ok(Self { - timeout: timeout.map(|value| value.str()?.extract()).transpose()?, + timeout: read_timeout_seconds(timeout)?, aiohttp: py .import(HTTP_TRANSPORT_MODULE)? .getattr("uses_aiohttp_transport")? diff --git a/litellm/llms/custom_httpx/http_handler.py b/litellm/llms/custom_httpx/http_handler.py index cffeb44f12c..0b64885df45 100644 --- a/litellm/llms/custom_httpx/http_handler.py +++ b/litellm/llms/custom_httpx/http_handler.py @@ -20,6 +20,7 @@ from aiohttp import ClientSession, DummyCookieJar, TCPConnector from httpx import USE_CLIENT_DEFAULT, AsyncHTTPTransport, HTTPTransport from httpx._types import CertTypes, RequestFiles from httpx._utils import get_environment_proxies +from pydantic import TypeAdapter import litellm from litellm._logging import verbose_logger @@ -566,6 +567,34 @@ async def _raise_masked_async_error(e: httpx.HTTPStatusError, stream: bool) -> N raise MaskedHTTPStatusError(e, message=_text, text=_text) from None +_TIMEOUT_PHASES: Final[Mapping[type[httpx.TimeoutException], tuple[str, str]]] = MappingProxyType( + { + httpx.ConnectTimeout: ("Connection", "connect"), + httpx.ReadTimeout: ("Read", "read"), + httpx.WriteTimeout: ("Write", "write"), + httpx.PoolTimeout: ("Connection pool", "pool"), + } +) +_UNKNOWN_TIMEOUT_PHASE: Final = ("Request", "read") +_TIMEOUT_EXTENSION: Final = TypeAdapter(dict[str, float | None]) + + +def _timeout_phase_seconds(error: httpx.TimeoutException, phase: str) -> float | None: + """The limit httpx enforced for ``phase`` on the request that raised ``error``, from the request itself.""" + return _TIMEOUT_EXTENSION.validate_python(error.request.extensions["timeout"]).get(phase) + + +def _raise_timeout(error: httpx.TimeoutException, started_at: float) -> NoReturn: + label, phase = _TIMEOUT_PHASES.get(type(error), _UNKNOWN_TIMEOUT_PHASE) + seconds: Final = _timeout_phase_seconds(error, phase) + time_taken: Final = round(time.time() - started_at, 3) + raise litellm.Timeout( + message=f"{label} timed out. Timeout passed={seconds}, time taken={time_taken} seconds", + model="default-model-name", + llm_provider="litellm-httpx-handler", + ) + + class HTTPResponseLimitError(ValueError): pass @@ -870,20 +899,7 @@ class AsyncHTTPHandler: finally: await new_client.aclose() except httpx.TimeoutException as e: - end_time: Final = time.time() - time_delta: Final = round(end_time - start_time, 3) - headers = {} - error_response: Final[httpx.Response | None] = getattr(e, "response", None) - if error_response is not None: - for key, value in error_response.headers.items(): - headers[f"response_headers-{key}"] = value - - raise litellm.Timeout( - message=f"Connection timed out. Timeout passed={timeout}, time taken={time_delta} seconds", - model="default-model-name", - llm_provider="litellm-httpx-handler", - headers=headers, - ) + _raise_timeout(e, start_time) except httpx.HTTPStatusError as e: await _raise_masked_async_error(e, stream) except Exception as e: @@ -902,6 +918,7 @@ class AsyncHTTPHandler: follow_redirects: bool | None = None, ): _follow_redirects: Final = follow_redirects if follow_redirects is not None else USE_CLIENT_DEFAULT + start_time: Final = time.time() try: if timeout is None: timeout = self.timeout @@ -946,18 +963,7 @@ class AsyncHTTPHandler: finally: await new_client.aclose() except httpx.TimeoutException as e: - headers = {} - error_response: Final[httpx.Response | None] = getattr(e, "response", None) - if error_response is not None: - for key, value in error_response.headers.items(): - headers[f"response_headers-{key}"] = value - - raise litellm.Timeout( - message=f"Connection timed out after {timeout} seconds.", - model="default-model-name", - llm_provider="litellm-httpx-handler", - headers=headers, - ) + _raise_timeout(e, start_time) except httpx.HTTPStatusError as e: await _raise_masked_async_error(e, stream) except Exception as e: @@ -974,6 +980,7 @@ class AsyncHTTPHandler: stream: bool = False, content: _RequestContent | None = None, ): + start_time: Final = time.time() try: if timeout is None: timeout = self.timeout @@ -1012,18 +1019,7 @@ class AsyncHTTPHandler: finally: await new_client.aclose() except httpx.TimeoutException as e: - headers = {} - error_response: Final[httpx.Response | None] = getattr(e, "response", None) - if error_response is not None: - for key, value in error_response.headers.items(): - headers[f"response_headers-{key}"] = value - - raise litellm.Timeout( - message=f"Connection timed out after {timeout} seconds.", - model="default-model-name", - llm_provider="litellm-httpx-handler", - headers=headers, - ) + _raise_timeout(e, start_time) except httpx.HTTPStatusError as e: await _raise_masked_async_error(e, stream) except Exception as e: @@ -1514,6 +1510,7 @@ class HTTPHandler: content: _RequestContent | None = None, logging_obj: LiteLLMLoggingObject | None = None, ): + start_time: Final = time.time() try: # Prepare data/content parameters to prevent httpx DeprecationWarning (memory leak fix) request_data, request_content = _prepare_request_data_and_content(data, content) @@ -1546,12 +1543,8 @@ class HTTPHandler: _anchor_handler_to(response, self) response.raise_for_status() return response - except httpx.TimeoutException: - raise litellm.Timeout( - message=f"Connection timed out after {timeout} seconds.", - model="default-model-name", - llm_provider="litellm-httpx-handler", - ) + except httpx.TimeoutException as e: + _raise_timeout(e, start_time) except httpx.HTTPStatusError as e: _raise_masked_sync_error(e, stream) except Exception as e: @@ -1568,6 +1561,7 @@ class HTTPHandler: timeout: float | httpx.Timeout | None = None, content: _RequestContent | None = None, ): + start_time: Final = time.time() try: # Prepare data/content parameters to prevent httpx DeprecationWarning (memory leak fix) request_data, request_content = _prepare_request_data_and_content(data, content) @@ -1598,12 +1592,8 @@ class HTTPHandler: _anchor_handler_to(response, self) response.raise_for_status() return response - except httpx.TimeoutException: - raise litellm.Timeout( - message=f"Connection timed out after {timeout} seconds.", - model="default-model-name", - llm_provider="litellm-httpx-handler", - ) + except httpx.TimeoutException as e: + _raise_timeout(e, start_time) except httpx.HTTPStatusError as e: _raise_masked_sync_error(e, stream) except Exception as e: @@ -1620,6 +1610,7 @@ class HTTPHandler: timeout: float | httpx.Timeout | None = None, content: _RequestContent | None = None, ): + start_time: Final = time.time() try: # Prepare data/content parameters to prevent httpx DeprecationWarning (memory leak fix) request_data, request_content = _prepare_request_data_and_content(data, content) @@ -1649,12 +1640,8 @@ class HTTPHandler: if stream: _anchor_handler_to(response, self) return response - except httpx.TimeoutException: - raise litellm.Timeout( - message=f"Connection timed out after {timeout} seconds.", - model="default-model-name", - llm_provider="litellm-httpx-handler", - ) + except httpx.TimeoutException as e: + _raise_timeout(e, start_time) except httpx.HTTPStatusError as e: _raise_masked_sync_error(e, stream) except Exception as e: @@ -1671,6 +1658,7 @@ class HTTPHandler: stream: bool = False, content: _RequestContent | None = None, ): + start_time: Final = time.time() try: # Prepare data/content parameters to prevent httpx DeprecationWarning (memory leak fix) request_data, request_content = _prepare_request_data_and_content(data, content) @@ -1701,12 +1689,8 @@ class HTTPHandler: _anchor_handler_to(response, self) response.raise_for_status() return response - except httpx.TimeoutException: - raise litellm.Timeout( - message=f"Connection timed out after {timeout} seconds.", - model="default-model-name", - llm_provider="litellm-httpx-handler", - ) + except httpx.TimeoutException as e: + _raise_timeout(e, start_time) except httpx.HTTPStatusError as e: _raise_masked_sync_error(e, stream) except Exception as e: diff --git a/tests/unit/llms/custom_httpx/test_http_handler.py b/tests/unit/llms/custom_httpx/test_http_handler.py index bd4ed4c99cc..1607447f7bf 100644 --- a/tests/unit/llms/custom_httpx/test_http_handler.py +++ b/tests/unit/llms/custom_httpx/test_http_handler.py @@ -2172,3 +2172,86 @@ async def test_async_ollama_ssl_verify_false_builds_a_client_that_skips_certific assert route.call_count == 1 assert text == "Sunny" assert _cached_clients_verify_modes(client_cache, AsyncHTTPHandler) == (ssl.CERT_NONE,) + + +_TIMEOUT_CLIENT_LIMITS: Final = httpx.Timeout(42.0, connect=7.0) +_TIMEOUT_PHASES: Final = ( + (httpx.ConnectTimeout, "Connection timed out", "Timeout passed=7.0"), + (httpx.ReadTimeout, "Read timed out", "Timeout passed=42.0"), + (httpx.WriteTimeout, "Write timed out", "Timeout passed=42.0"), + (httpx.PoolTimeout, "Connection pool timed out", "Timeout passed=42.0"), +) + + +def _timing_out(kind: type[httpx.TimeoutException]) -> httpx.MockTransport: + def _raise(request: httpx.Request) -> httpx.Response: + raise kind("simulated", request=request) + + return httpx.MockTransport(_raise) + + +@pytest.mark.parametrize("verb", ["post", "put", "patch", "delete"]) +@pytest.mark.parametrize(("kind", "label", "limit"), _TIMEOUT_PHASES) +def test_sync_timeout_without_a_per_call_timeout_names_the_phase_and_the_limit_that_fired( + verb: str, kind: type[httpx.TimeoutException], label: str, limit: str +) -> None: + """Issue #14635: the handler used to print the caller's absent argument as 'after None seconds'.""" + handler: Final = HTTPHandler() + handler.client.close() + handler.client = httpx.Client(transport=_timing_out(kind), timeout=_TIMEOUT_CLIENT_LIMITS) + try: + with pytest.raises(LitellmTimeout) as raised: + getattr(handler, verb)("https://example.com/v1/embeddings", json={"input": "hi"}) + finally: + handler.close() + + message: Final = str(raised.value) + assert label in message, message + assert limit in message, message + assert "None" not in message, message + + +@pytest.mark.parametrize("verb", ["post", "put", "patch"]) +@pytest.mark.parametrize(("kind", "label", "limit"), _TIMEOUT_PHASES) +async def test_async_timeout_without_a_per_call_timeout_names_the_phase_and_the_limit_that_fired( + verb: str, kind: type[httpx.TimeoutException], label: str, limit: str +) -> None: + handler: Final = AsyncHTTPHandler(timeout=_TIMEOUT_CLIENT_LIMITS) + await handler.client.aclose() + handler.client = httpx.AsyncClient(transport=_timing_out(kind), timeout=_TIMEOUT_CLIENT_LIMITS) + try: + with pytest.raises(LitellmTimeout) as raised: + await getattr(handler, verb)("https://example.com/v1/embeddings", json={"input": "hi"}) + finally: + await handler.close() + + message: Final = str(raised.value) + assert label in message, message + assert limit in message, message + assert "None" not in message, message + + +def test_sync_timeout_reports_the_per_call_timeout_as_a_float_when_one_is_given() -> None: + handler: Final = HTTPHandler() + handler.client.close() + handler.client = httpx.Client(transport=_timing_out(httpx.ReadTimeout), timeout=_TIMEOUT_CLIENT_LIMITS) + try: + with pytest.raises(LitellmTimeout) as raised: + handler.post("https://example.com/v1/embeddings", json={"input": "hi"}, timeout=30) + finally: + handler.close() + + assert "Read timed out. Timeout passed=30.0, time taken=" in str(raised.value), str(raised.value) + + +async def test_async_timeout_reports_the_per_call_timeout_as_a_float_when_one_is_given() -> None: + handler: Final = AsyncHTTPHandler(timeout=_TIMEOUT_CLIENT_LIMITS) + await handler.client.aclose() + handler.client = httpx.AsyncClient(transport=_timing_out(httpx.ReadTimeout), timeout=_TIMEOUT_CLIENT_LIMITS) + try: + with pytest.raises(LitellmTimeout) as raised: + await handler.post("https://example.com/v1/embeddings", json={"input": "hi"}, timeout=30) + finally: + await handler.close() + + assert "Read timed out. Timeout passed=30.0, time taken=" in str(raised.value), str(raised.value) From bc0f598db5866d1d3fdb5c99ce627fb5ea19a788 Mon Sep 17 00:00:00 2001 From: tin-berri Date: Mon, 26 Oct 2026 19:11:38 -0400 Subject: [PATCH 002/262] fix(proxy): validate JSON object bodies before request handling (#48438) --- litellm/proxy/auth/auth_exception_handler.py | 12 +- .../proxy/common_utils/http_parsing_utils.py | 43 +++++-- .../proxy/auth/test_auth_exception_handler.py | 62 ++++++++++ .../test_user_api_key_auth_request_flow.py | 6 +- .../common_utils/test_http_parsing_utils.py | 112 +++++++++++++++++- tests/unit/proxy/lens/test_buffering.py | 17 ++- .../test_llm_pass_through_endpoints.py | 1 + 7 files changed, 226 insertions(+), 27 deletions(-) diff --git a/litellm/proxy/auth/auth_exception_handler.py b/litellm/proxy/auth/auth_exception_handler.py index f6637a1fdf3..2eb25cc6105 100644 --- a/litellm/proxy/auth/auth_exception_handler.py +++ b/litellm/proxy/auth/auth_exception_handler.py @@ -12,7 +12,7 @@ import litellm from litellm._logging import verbose_proxy_logger, verbose_proxy_stdout_logger from litellm.constants import EMPTY_MAPPING from litellm.integrations.otel.runtime import seed_request_identity -from litellm.litellm_core_utils.core_helpers import is_expected_client_error +from litellm.litellm_core_utils.core_helpers import as_str_mapping, is_expected_client_error from litellm.proxy._types import ( LitellmUserRoles, ModelAccessDeniedProxyException, @@ -139,7 +139,7 @@ class UserAPIKeyAuthExceptionHandler: async def handle_authentication_error( e: Exception, request: Request, - request_data: dict[str, object], + request_data: object, route: str, parent_otel_span: Span | None, api_key: str, @@ -190,6 +190,8 @@ class UserAPIKeyAuthExceptionHandler: request_route=route, ) else: + request_mapping: Final = as_str_mapping(request_data) + request_context: Final[dict[str, object]] = dict(request_mapping) if request_mapping is not None else {} # raise the exception to the caller requester_ip: Final = get_request_ip_address( request=request, @@ -229,7 +231,7 @@ class UserAPIKeyAuthExceptionHandler: # without this the failed trace would carry no team/key attributes. seed_request_identity( user_api_key_dict, - model=request_data.get("model"), + model=request_context.get("model"), ) # Budget checks live in tenant-scoped helpers (key / team / org / tag) @@ -242,14 +244,14 @@ class UserAPIKeyAuthExceptionHandler: resolve_llm_provider_for_rate_limit, ) - budget_model: Final = request_data.get("model") + budget_model: Final = request_context.get("model") _, e.llm_provider = resolve_llm_provider_for_rate_limit( budget_model if isinstance(budget_model, str) else None ) # Allow callbacks to transform the error response transformed_exception: Final = await proxy_logging_obj.post_call_failure_hook( - request_data=_with_client_context(request_data, requester_ip, user_agent), + request_data=_with_client_context(request_context, requester_ip, user_agent), original_exception=e, user_api_key_dict=user_api_key_dict, error_type=ProxyErrorTypes.auth_error, diff --git a/litellm/proxy/common_utils/http_parsing_utils.py b/litellm/proxy/common_utils/http_parsing_utils.py index a38769ac41b..9f7fed40ab3 100644 --- a/litellm/proxy/common_utils/http_parsing_utils.py +++ b/litellm/proxy/common_utils/http_parsing_utils.py @@ -6,7 +6,7 @@ from typing import Annotated, Any, Final, Literal, Union, get_args, get_origin import orjson from fastapi import Request, UploadFile, status -from pydantic import TypeAdapter +from pydantic import TypeAdapter, ValidationError from starlette._utils import get_route_path from starlette.requests import HTTPConnection from typing_extensions import NotRequired, ReadOnly, Required, assert_never @@ -162,13 +162,11 @@ def coerce_numeric_form_fields( } -def _parse_binary_body(body: bytes) -> dict: +def _parse_binary_body(body: bytes) -> dict[str, object]: """JSON sent under a binary content type still parses; real binary (protobuf) carries no params -> {}.""" try: - parsed: Final = _DECODED_JSON.validate_python(orjson.loads(body)) - if isinstance(parsed, dict): - return parsed - except orjson.JSONDecodeError: + return dict(_JSON_REQUEST_BODY.validate_python(orjson.loads(body))) + except (orjson.JSONDecodeError, ValidationError): pass return {} @@ -299,8 +297,9 @@ async def read_request_body(request: Request | None) -> dict: body_str = re.sub(r"(? dict: safe_set_request_parsed_body(request=request, parsed_body=parsed_body) return parsed_body + except ValidationError as e: + from fastapi.routing import APIRoute + + from litellm.proxy.auth.auth_utils import ( + request_dispatched_to_pass_through_endpoint, + request_dispatched_to_provider_pass_through, + ) + from litellm.proxy.lens.buffering import LensRoute + + route: Final[object] = request.scope.get("route") if request is not None else None + if request is not None and ( + request_dispatched_to_pass_through_endpoint(request) + or request_dispatched_to_provider_pass_through(request) + or isinstance(route, LensRoute) + or ( + isinstance(route, APIRoute) + and route.body_field is not None + and not route.body_field.field_info.is_required() + and (await request.body()).strip() == b"null" + ) + ): + return {} + raise ProxyException( + message="Invalid JSON payload: expected an object", + type="invalid_request_error", + param="request_body", + code=status.HTTP_400_BAD_REQUEST, + ) from e except (json.JSONDecodeError, orjson.JSONDecodeError, ProxyException) as e: # Re-raise ProxyException as-is verbose_proxy_logger.error("Invalid JSON payload received: %s", e) diff --git a/tests/unit/proxy/auth/test_auth_exception_handler.py b/tests/unit/proxy/auth/test_auth_exception_handler.py index d83a8aa2fcd..e21491fd996 100644 --- a/tests/unit/proxy/auth/test_auth_exception_handler.py +++ b/tests/unit/proxy/auth/test_auth_exception_handler.py @@ -1,5 +1,7 @@ import asyncio import json +from collections.abc import Mapping +from typing import Final from unittest.mock import AsyncMock, MagicMock, patch import httpx @@ -29,6 +31,7 @@ import litellm from litellm._logging import verbose_proxy_logger from litellm.constants import INVALID_VIRTUAL_KEY_ERROR_MARKER from litellm.exceptions import BudgetExceededError +from litellm.integrations.custom_logger import CustomLogger from litellm.proxy._types import ( ModelAccessDeniedProxyException, ProxyErrorTypes, @@ -812,6 +815,65 @@ def _http_request(client_host: str | None = "10.1.2.3", headers: dict[str, str] ) +class _AuthFailureRecorder(CustomLogger): + def __init__(self) -> None: + super().__init__() + self.data: dict[str, object] | None = None + self.error: Exception | None = None + + async def async_post_call_failure_hook( + self, + request_data: dict[str, object], + original_exception: Exception, + user_api_key_dict: UserAPIKeyAuth, + traceback_str: str | None = None, + ) -> HTTPException | None: + self.data = dict(request_data) + self.error = original_exception + return None + + +@pytest.mark.asyncio +@pytest.mark.parametrize("request_data", [[], None, "metadata", 1, True]) +@pytest.mark.parametrize("error_kind", ["auth", "budget", "database"]) +async def test_auth_error_preserves_classification_with_non_object_context( + monkeypatch: pytest.MonkeyPatch, request_data: object, error_kind: str +) -> None: + import litellm.proxy.proxy_server as proxy_server + + monkeypatch.setattr(litellm, "budget_exceeded_status_code", 429) + errors: Final = { + "auth": HTTPException(status_code=401, detail="Invalid API key"), + "budget": BudgetExceededError(current_cost=2, max_budget=1), + "database": httpx.ConnectError("Database unavailable"), + } + error: Final = errors[error_kind] + expected: Final = _as_proxy_exception(error) + recorder: Final = _AuthFailureRecorder() + monkeypatch.setattr(litellm, "callbacks", [recorder]) + monkeypatch.setattr(proxy_server, "general_settings", {"allow_requests_on_db_unavailable": False}) + + with pytest.raises(ProxyException) as exc_info: + await UserAPIKeyAuthExceptionHandler.handle_authentication_error( + error, + _http_request(headers={"user-agent": "shape-regression"}), + request_data, + "/key/info", + None, + "sk-test", + ) + + assert exc_info.value.code == expected.code + assert exc_info.value.type == expected.type + assert exc_info.value.message == expected.message + assert recorder.error is error + assert recorder.data is not None + metadata: Final = recorder.data["metadata"] + assert isinstance(metadata, Mapping) + assert metadata["requester_ip_address"] == "10.1.2.3" + assert metadata["user_agent"] == "shape-regression" + + @pytest.mark.asyncio @pytest.mark.parametrize( "auth_error, general_settings, request_kwargs, expected_ip", diff --git a/tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py b/tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py index 108f7ce2983..2d9c781b0d1 100644 --- a/tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py +++ b/tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py @@ -7724,7 +7724,8 @@ async def test_user_api_key_auth_does_not_overwrite_end_user_id_set_by_builder() @pytest.mark.asyncio -async def test_user_api_key_auth_authenticates_before_raising_malformed_body_error(): +@pytest.mark.parametrize("body", [b'{}{"model": "gpt-4o"}', b"[]", b"null", b"[1e400]"]) +async def test_user_api_key_auth_authenticates_before_raising_malformed_body_error(body: bytes) -> None: """Regression (LIT-4780): a body that fails to parse must still be authenticated first, so the rejected request's trace carries the caller's key / team / user identity instead of an anonymous root span. The parse error is re-raised @@ -7742,10 +7743,11 @@ async def test_user_api_key_auth_authenticates_before_raising_malformed_body_err "headers": [(b"content-type", b"application/json")], "method": "POST", "path": "/chat/completions", + "query_string": b"probe=1", } ) request._url = URL(url="/chat/completions") - request._body = b'{}{"model": "gpt-4o"}' + request._body = body attrs = _proxy_attrs_for_centralized_checks(user_custom_auth=None) originals = {a: getattr(_proxy_server_mod, a, None) for a in attrs} diff --git a/tests/unit/proxy/common_utils/test_http_parsing_utils.py b/tests/unit/proxy/common_utils/test_http_parsing_utils.py index cd5820fa2fd..354feb0bab1 100644 --- a/tests/unit/proxy/common_utils/test_http_parsing_utils.py +++ b/tests/unit/proxy/common_utils/test_http_parsing_utils.py @@ -64,6 +64,100 @@ def _starlette_request( return Request(scope, receive) +@pytest.mark.asyncio +@pytest.mark.parametrize( + "body", + [b"[]", b'[["model", "test"]]', b"null", b'"s"', b"1", b"true", b"false"], +) +@pytest.mark.parametrize("path", ["/v1/messages", "/vertex_ai/v1/messages", "/lens/datasets"]) +async def test_read_request_body_rejects_non_object_json(body: bytes, path: str) -> None: + request: Final = _starlette_request(body, "application/json", path) + + for _ in range(2): + with pytest.raises(ProxyException) as exc_info: + await read_request_body(request) + assert exc_info.value.code == "400" + assert exc_info.value.type == "invalid_request_error" + assert exc_info.value.param == "request_body" + assert exc_info.value.message == "Invalid JSON payload: expected an object" + assert _safe_get_request_parsed_body(request) is None + assert await request.body() == body + + +@pytest.mark.asyncio +@pytest.mark.parametrize("body", [b"[1e400]", b"1e400", b"[NaN]"]) +async def test_read_request_body_rejects_non_objects_from_json_fallback(body: bytes) -> None: + with pytest.raises(ProxyException) as exc_info: + await read_request_body(_starlette_request(body, "application/json")) + assert exc_info.value.code == "400" + assert exc_info.value.message == "Invalid JSON payload: expected an object" + + +@pytest.mark.asyncio +@pytest.mark.parametrize( + "body, invalid_unicode", + [ + (b"[]", False), + (b"null", False), + (b'"value"', False), + (b"[1e400]", False), + (b'"\\ud800"', True), + (b'["\\ud800"]', True), + (b'{"value":"\\ud800"}', True), + ], +) +@pytest.mark.parametrize("dispatch", ["custom", "provider", "lens"]) +async def test_pass_through_body_validation_preserves_bytes(dispatch: str, body: bytes, invalid_unicode: bool) -> None: + from fastapi.routing import APIRoute + from litellm.proxy.lens.adapter import lens_request + from litellm.proxy.lens.buffering import LensRoute + from litellm.proxy.pass_through_endpoints.llm_passthrough_endpoints import vertex_proxy_route + from litellm.proxy.pass_through_endpoints.pass_through_endpoints import create_pass_through_route + + path: Final = {"custom": "/v1/messages", "provider": "/vertex_ai/predict", "lens": "/lens/datasets"}[dispatch] + route: Final = { + "custom": APIRoute(path, create_pass_through_route(path, "https://upstream.test"), methods=["POST"]), + "provider": APIRoute("/vertex_ai/{endpoint:path}", vertex_proxy_route, methods=["POST"]), + "lens": LensRoute("/lens/{path:path}", lens_request, methods=["POST"]), + }[dispatch] + incoming: Final = _starlette_request(body, "application/json", path) + _, dispatched_scope = route.matches(incoming.scope) + request: Final = Request({**incoming.scope, **dispatched_scope}, incoming.receive) + + for _ in range(2): + if invalid_unicode: + with pytest.raises(ProxyException) as exc_info: + await read_request_body(request) + assert exc_info.value.code == "400" + else: + assert await read_request_body(request) == {} + assert await request.body() == body + + +@pytest.mark.asyncio +@pytest.mark.parametrize("optional", [False, True]) +@pytest.mark.parametrize("body", [b"null", b" \nnull\t", b"[]", b'"value"']) +async def test_null_body_respects_the_dispatched_body_requirement(optional: bool, body: bytes) -> None: + from fastapi.routing import APIRoute + from litellm.proxy.management_endpoints.key_management_endpoints import generate_key_fn + from litellm.proxy.spend_tracking.spend_management_endpoints import global_spend_end_users + + endpoint: Final = global_spend_end_users if optional else generate_key_fn + route: Final = APIRoute("/audit", endpoint, methods=["POST"]) + incoming: Final = _starlette_request(body, "application/json", "/audit") + _, dispatched_scope = route.matches(incoming.scope) + request: Final = Request({**incoming.scope, **dispatched_scope}, incoming.receive) + + if optional and body.strip() == b"null": + assert await read_request_body(request) == {} + assert await request.json() is None + else: + with pytest.raises(ProxyException) as exc_info: + await read_request_body(request) + assert exc_info.value.code == "400" + assert await request.body() == body + + @pytest.mark.asyncio async def test_read_request_body_marks_body_received_once_with_its_size(monkeypatch: pytest.MonkeyPatch): events: list[tuple[str, dict[str, str | int]]] = [] # mutable-ok: recorder for the injected phase_event double @@ -131,14 +225,20 @@ async def test_read_raw_json_body_is_none_for_form_bodies(): @pytest.mark.asyncio @pytest.mark.parametrize("content_type", ["application/x-protobuf", "application/protobuf; charset=binary"]) -async def test_protobuf_body_is_not_parsed_as_json(content_type): - # OTLP trace exports (POST /v1/traces) are binary protobuf; arbitrary bytes like these - # used to hit the JSON surrogate-repair path and fail auth with a 400. - body = b"\n\xa2\x01\n\x1c\n\x0cservice.name\x12\x0c\n\nswarm\xed\xa0\x80\xff" - request = _starlette_request(body, content_type) +@pytest.mark.parametrize( + "body", + [ + b"\n\xa2\x01\n\x1c\n\x0cservice.name\x12\x0c\n\nswarm\xed\xa0\x80\xff", + pytest.param(b"100000000", id="protobuf-also-json-number"), + ], +) +async def test_protobuf_body_is_not_parsed_as_json(content_type: str, body: bytes) -> None: + request: Final = _starlette_request(body, content_type) assert await read_request_body(request) == {} - assert await request.body() == body # body is still readable by the endpoint + assert await read_request_body(request) == {} + assert await read_raw_json_body(request) == body + assert await request.body() == body @pytest.mark.asyncio diff --git a/tests/unit/proxy/lens/test_buffering.py b/tests/unit/proxy/lens/test_buffering.py index b544b70d36b..2b868e72096 100644 --- a/tests/unit/proxy/lens/test_buffering.py +++ b/tests/unit/proxy/lens/test_buffering.py @@ -249,7 +249,10 @@ async def test_admission_releases_upload_on_disconnect_or_cancellation(cancel: b @pytest.mark.asyncio @pytest.mark.parametrize("reject_auth", [False, True]) -async def test_admitted_bytes_survive_auth_parsing_and_remain_reserved_until_sent(reject_auth: bool) -> None: +@pytest.mark.parametrize("body", [b" {} ", b"[]", b"null", b'"s"']) +async def test_admitted_bytes_survive_auth_parsing_and_remain_reserved_until_sent( + reject_auth: bool, body: bytes +) -> None: app: Final = FastAPI() router: Final = APIRouter(route_class=LensRoute) @@ -264,9 +267,11 @@ async def test_admitted_bytes_survive_auth_parsing_and_remain_reserved_until_sen if reject_auth: raise HTTPException(401, "Invalid key") - async with httpx.AsyncClient( - transport=httpx.MockTransport(lambda _: httpx.Response(200, content=b"result")) - ) as upstream: + def upstream_response(incoming: httpx.Request) -> httpx.Response: + assert incoming.content == body + return httpx.Response(200, content=b"result") + + async with httpx.AsyncClient(transport=httpx.MockTransport(upstream_response)) as upstream: @router.post("/lens/datasets") async def endpoint(request: Request, auth: Annotated[None, Depends(auth_reader)]) -> Response: @@ -284,14 +289,14 @@ async def test_admitted_bytes_survive_auth_parsing_and_remain_reserved_until_sen sending.set() await finish.wait() - incoming: Final = request(b" {} ") + incoming: Final = request(body) task: Final = asyncio.create_task(app(incoming.scope, incoming.receive, send)) try: await asyncio.wait_for(sending.wait(), 2) async with httpx.AsyncClient( transport=httpx.ASGITransport(app=app), base_url="http://gateway.test" ) as client: - blocked: Final = await client.post("/lens/datasets", content=b" {} " * 2) + blocked: Final = await client.post("/lens/datasets", content=b" " * (11 - len(body))) unrelated: Final = await client.post("/ordinary", content=b"ordinary body") assert blocked.status_code == 503 assert unrelated.content == b"ordinary body" diff --git a/tests/unit/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py b/tests/unit/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py index 0186a33dbc4..60043daa402 100644 --- a/tests/unit/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py +++ b/tests/unit/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py @@ -4357,6 +4357,7 @@ class TestVertexRawPredictStreamingClassification: "type": "http", "method": "POST", "path": f"/vertex_ai/{endpoint}", + "path_params": {"endpoint": endpoint}, "headers": [ (b"content-type", b"application/json"), (b"x-litellm-api-key", b"test-key"), From a4ee9524441381c012c5f4b1bc2c3f7827a2a77b Mon Sep 17 00:00:00 2001 From: yucheng-berri Date: Mon, 26 Oct 2026 16:45:35 -0700 Subject: [PATCH 003/262] fix(proxy)!: gate key budget_duration and budget_id updates like max_budget (#47681) * fix(proxy): gate key budget_duration and budget_id updates like max_budget A key owner or team member could shorten budget_duration or swap budget_id on /key/update without the budget authorization max_budget gets, so the reset job cleared spend on a capped key or a bigger tier lifted its cap Fixes #46916 * test(proxy): cover tier keys and self-serve budget policies for key budget updates --------- Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com> --- litellm/litellm_core_utils/duration_parser.py | 10 +- .../management_endpoints/key_budget_change.py | 44 +++- .../test_key_budget_owner_updates.py | 195 ++++++++++++++++++ .../test_key_budget_change.py | 109 ++++++++++ 4 files changed, 349 insertions(+), 9 deletions(-) create mode 100644 tests/integration/authorization/test_key_budget_owner_updates.py diff --git a/litellm/litellm_core_utils/duration_parser.py b/litellm/litellm_core_utils/duration_parser.py index d52716951df..95bc77e3eba 100644 --- a/litellm/litellm_core_utils/duration_parser.py +++ b/litellm/litellm_core_utils/duration_parser.py @@ -22,7 +22,7 @@ _BUDGET_DURATION_WORD_ALIASES: Final[dict[str, str]] = { } -def _normalize_duration(duration: str) -> str: +def normalize_duration(duration: str) -> str: return _BUDGET_DURATION_WORD_ALIASES.get(duration.strip().lower(), duration) @@ -61,7 +61,7 @@ def duration_in_seconds(duration: str) -> int: Returns time in seconds till when budget needs to be reset """ - value, unit = _extract_from_regex(duration=_normalize_duration(duration)) + value, unit = _extract_from_regex(duration=normalize_duration(duration)) if unit == "s": return value @@ -89,7 +89,7 @@ def duration_in_seconds_from(start: datetime, duration: str) -> int: month of a different length needs its own start to know when it ends. Every other unit is a fixed length and ignores `start`. """ - value, unit = _extract_from_regex(duration=_normalize_duration(duration)) + value, unit = _extract_from_regex(duration=normalize_duration(duration)) if unit == "mo": return _months_in_seconds(start=start, months=value) return duration_in_seconds(duration) @@ -129,7 +129,7 @@ def get_next_standardized_reset_time( current_time, _ = _setup_timezone(current_time, timezone_str) # Parse duration - value, unit = _parse_duration(_normalize_duration(duration)) + value, unit = _parse_duration(normalize_duration(duration)) if value is None: verbose_logger.warning( "Unrecognized budget_duration %r; falling back to a next-midnight reset. " @@ -171,7 +171,7 @@ def get_budget_window_start(duration: str, reset_at: datetime) -> datetime: """Start of the budget period that ends at `reset_at`, under the same rules `get_next_standardized_reset_time` used to pick it: `30d` and `Nmo` span calendar months and a duration it does not recognize resets at the next midnight.""" - value, unit = _parse_duration(_normalize_duration(duration)) + value, unit = _parse_duration(normalize_duration(duration)) if value is None: return reset_at - timedelta(days=1) match unit: diff --git a/litellm/proxy/management_endpoints/key_budget_change.py b/litellm/proxy/management_endpoints/key_budget_change.py index 3143ef53d76..197a13cdb13 100644 --- a/litellm/proxy/management_endpoints/key_budget_change.py +++ b/litellm/proxy/management_endpoints/key_budget_change.py @@ -9,6 +9,7 @@ from typing import Final, Literal, TypeAlias from pydantic import TypeAdapter, ValidationError from litellm._logging import verbose_proxy_logger +from litellm.litellm_core_utils.duration_parser import normalize_duration from litellm.models.team import BudgetLimitEntry from litellm.models.verification_token import LiteLLM_VerificationToken from litellm.proxy._types import UpdateKeyRequest @@ -99,6 +100,30 @@ def _budget_limits_change(data: UpdateKeyRequest, existing: LiteLLM_Verification return "tightened" if kept_or_lowered else "loosened" +def _reset_schedule(budget_duration: str | None) -> str | None: + return None if budget_duration is None else normalize_duration(budget_duration) + + +def _changes_budget_duration(data: UpdateKeyRequest, existing: LiteLLM_VerificationToken) -> bool: + return "budget_duration" in data.model_fields_set and _reset_schedule(data.budget_duration) != _reset_schedule( + existing.budget_duration + ) + + +def _changes_budget_id(data: UpdateKeyRequest, existing: LiteLLM_VerificationToken) -> bool: + return "budget_id" in data.model_fields_set and data.budget_id != existing.budget_id + + +def _budget_duration_change(data: UpdateKeyRequest, existing: LiteLLM_VerificationToken) -> _FieldChange: + """ + Any new `budget_duration` restarts the reset schedule from now, so only clearing it tightens the + stored `max_budget`. A key with no `max_budget` has no cap for the schedule to reset. + """ + if existing.max_budget is None or not _changes_budget_duration(data, existing): + return "unchanged" + return "tightened" if data.budget_duration is None else "loosened" + + @dataclass(frozen=True, slots=True) class EffectiveKeyBudget: max_budget: float | None @@ -122,12 +147,23 @@ def effective_key_budget(data: UpdateKeyRequest, existing: LiteLLM_VerificationT def classify_key_budget_change(data: UpdateKeyRequest, existing: LiteLLM_VerificationToken) -> KeyBudgetChange: - overrides_linked_budget: Final = ( - existing.budget_id is not None and _max_budget_change(data, existing) != "unchanged" + overrides_linked_budget: Final = existing.budget_id is not None and ( + _max_budget_change(data, existing) != "unchanged" or _changes_budget_duration(data, existing) ) - if data.spend is not None or "soft_budget" in data.model_fields_set or overrides_linked_budget: + if ( + data.spend is not None + or "soft_budget" in data.model_fields_set + or overrides_linked_budget + or _changes_budget_id(data, existing) + ): return KeyBudgetAdminOnly() - changes: Final = frozenset((_max_budget_change(data, existing), _budget_limits_change(data, existing))) + changes: Final = frozenset( + ( + _max_budget_change(data, existing), + _budget_limits_change(data, existing), + _budget_duration_change(data, existing), + ) + ) if "loosened" in changes: return KeyBudgetLoosened() if "tightened" in changes: diff --git a/tests/integration/authorization/test_key_budget_owner_updates.py b/tests/integration/authorization/test_key_budget_owner_updates.py new file mode 100644 index 00000000000..8415c044b6f --- /dev/null +++ b/tests/integration/authorization/test_key_budget_owner_updates.py @@ -0,0 +1,195 @@ +from collections.abc import Iterator +from hashlib import sha256 +from pathlib import Path +from types import MappingProxyType +from typing import Final + +import pytest +import yaml +from integration._support.client import ( + JSON_OBJECT, + Gateway, + Scenario, + eventually, + gateway_from_environment, + string_value, +) +from integration._support.process import owned_proxy +from pydantic import JsonValue + +pytestmark: Final = pytest.mark.shares_worker_state + +CAP: Final = 0.1 +BUDGET_EXCEEDED: Final = 422 +FAST_RESET_TICK: Final = MappingProxyType( + {"PROXY_BUDGET_RESCHEDULER_MIN_TIME": "2", "PROXY_BUDGET_RESCHEDULER_MAX_TIME": "2"} +) + + +@pytest.fixture(scope="module") +def resetting(tmp_path_factory: pytest.TempPathFactory) -> Iterator[Gateway]: + with ( + gateway_from_environment() as shared, + owned_proxy(shared, tmp_path_factory.mktemp("fast-reset"), FAST_RESET_TICK) as replica, + ): + yield replica + + +def _policy_config(directory: Path, policy: str) -> Path: + shared: Final = JSON_OBJECT.validate_python(yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text())) + general_settings: Final = { + **JSON_OBJECT.validate_python(shared["general_settings"]), + "self_serve_budget_policy": policy, + } + path: Final = directory / f"{policy}.yaml" + path.write_text(yaml.safe_dump({**shared, "general_settings": general_settings})) + return path + + +@pytest.fixture(scope="module", params=("lower_only", "ceiling")) +def self_serve( + request: pytest.FixtureRequest, tmp_path_factory: pytest.TempPathFactory +) -> Iterator[tuple[str, Gateway]]: + policy: Final = string_value(request.param) + directory: Final = tmp_path_factory.mktemp(policy) + with ( + gateway_from_environment() as shared, + owned_proxy(shared, directory, {}, config=_policy_config(directory, policy)) as replica, + ): + yield policy, replica + + +def _owner_credential(scenario: Scenario) -> str: + return scenario.key(user_id=scenario.user(user_role="internal_user")) + + +def _owned_key(gateway: Gateway, scenario: Scenario, owner: str, **fields: JsonValue) -> str: + response: Final = gateway.request("POST", "/key/generate", fields, key=owner) + assert response.status_code == 200, response.text + token: Final = string_value(JSON_OBJECT.validate_json(response.content)["key"]) + scenario.cleanups.callback(scenario.delete_key, token) + return token + + +def _key_row(gateway: Gateway, key: str) -> dict[str, JsonValue]: + rows: Final = gateway.rows( + "SELECT spend, max_budget, budget_duration, budget_id, budget_reset_at::text AS reset_at" + ' FROM "LiteLLM_VerificationToken" WHERE token = %s', + (sha256(key.encode()).hexdigest(),), + ) + assert len(rows) == 1, rows + return rows[0] + + +def _exhaust(gateway: Gateway, key: str) -> None: + gateway.post("/key/update", {"key": key, "spend": CAP}) + assert _key_row(gateway, key)["spend"] == CAP + + +def _chat_status(gateway: Gateway, model: str, key: str) -> int: + return gateway.request( + "POST", "/v1/chat/completions", {"model": model, "messages": [{"role": "user", "content": "budget"}]}, key=key + ).status_code + + +def test_key_owner_cannot_shorten_budget_duration_to_restart_an_exhausted_budget(resetting: Gateway) -> None: + with resetting.scenario() as scenario: + model: Final = scenario.model() + owner: Final = _owner_credential(scenario) + target: Final = _owned_key(resetting, scenario, owner, models=[model], max_budget=CAP, budget_duration="30d") + control: Final = _owned_key(resetting, scenario, owner, models=[model], max_budget=CAP, budget_duration="30d") + _exhaust(resetting, target) + _exhaust(resetting, control) + assert _chat_status(resetting, model, target) == BUDGET_EXCEEDED + before: Final = _key_row(resetting, target) + + denied: Final = resetting.request("POST", "/key/update", {"key": target, "budget_duration": "1s"}, key=owner) + + resetting.post("/key/update", {"key": control, "budget_duration": "1s"}) + eventually(lambda: _key_row(resetting, control)["spend"], lambda spend: spend == 0.0, seconds=60) + assert denied.status_code == 403, denied.text + assert _key_row(resetting, target) == before + assert _chat_status(resetting, model, target) == BUDGET_EXCEEDED + + +def test_key_owner_cannot_swap_or_reschedule_a_tier_key(gateway: Gateway) -> None: + with gateway.scenario() as scenario: + model: Final = scenario.model() + low: Final = scenario.budget(max_budget=CAP) + high: Final = scenario.budget(max_budget=100.0) + owner: Final = _owner_credential(scenario) + target: Final = _owned_key(gateway, scenario, owner, models=[model], budget_id=low) + _exhaust(gateway, target) + assert _chat_status(gateway, model, target) == BUDGET_EXCEEDED + before: Final = _key_row(gateway, target) + + swapped: Final = gateway.request("POST", "/key/update", {"key": target, "budget_id": high}, key=owner) + rescheduled: Final = gateway.request("POST", "/key/update", {"key": target, "budget_duration": "1s"}, key=owner) + + assert swapped.status_code == 403, swapped.text + assert rescheduled.status_code == 403, rescheduled.text + assert _key_row(gateway, target) == before + assert _chat_status(gateway, model, target) == BUDGET_EXCEEDED + + +def test_team_member_cannot_shorten_budget_duration_on_a_team_key(gateway: Gateway) -> None: + with gateway.scenario() as scenario: + team: Final = scenario.team(team_member_permissions=["/key/update", "/key/info"]) + member: Final = scenario.key(user_id=scenario.member(team), team_id=team) + target: Final = scenario.key(team_id=team, max_budget=CAP, budget_duration="30d") + before: Final = _key_row(gateway, target) + + denied: Final = gateway.request("POST", "/key/update", {"key": target, "budget_duration": "1s"}, key=member) + + assert denied.status_code == 403, denied.text + assert _key_row(gateway, target) == before + + +def test_key_owner_keeps_edits_that_cannot_restart_a_budget(gateway: Gateway) -> None: + with gateway.scenario() as scenario: + owner: Final = _owner_credential(scenario) + capped: Final = _owned_key(gateway, scenario, owner, max_budget=CAP, budget_duration="monthly") + uncapped: Final = _owned_key(gateway, scenario, owner) + + renamed: Final = gateway.request("POST", "/key/update", {"key": capped, "key_alias": "renamed"}, key=owner) + resent: Final = gateway.request("POST", "/key/update", {"key": capped, "budget_duration": "30d"}, key=owner) + scheduled: Final = gateway.request("POST", "/key/update", {"key": uncapped, "budget_duration": "1d"}, key=owner) + + assert renamed.status_code == 200, renamed.text + assert resent.status_code == 200, resent.text + assert scheduled.status_code == 200, scheduled.text + assert _key_row(gateway, uncapped)["budget_duration"] == "1d" + + +def test_self_serve_policy_keeps_tier_keys_admin_only(self_serve: tuple[str, Gateway]) -> None: + _, proxy = self_serve + with proxy.scenario() as scenario: + low: Final = scenario.budget(max_budget=CAP) + high: Final = scenario.budget(max_budget=100.0) + owner: Final = _owner_credential(scenario) + target: Final = _owned_key(proxy, scenario, owner, budget_id=low) + before: Final = _key_row(proxy, target) + + swapped: Final = proxy.request("POST", "/key/update", {"key": target, "budget_id": high}, key=owner) + rescheduled: Final = proxy.request("POST", "/key/update", {"key": target, "budget_duration": "1d"}, key=owner) + + assert swapped.status_code == 403, swapped.text + assert rescheduled.status_code == 403, rescheduled.text + assert _key_row(proxy, target) == before + + +def test_self_serve_policy_gates_a_new_reset_period_like_a_raised_cap(self_serve: tuple[str, Gateway]) -> None: + policy, proxy = self_serve + with proxy.scenario() as scenario: + owner: Final = _owner_credential(scenario) + shortened: Final = _owned_key(proxy, scenario, owner, max_budget=CAP, budget_duration="30d") + cleared: Final = _owned_key(proxy, scenario, owner, max_budget=CAP, budget_duration="30d") + + shorten: Final = proxy.request("POST", "/key/update", {"key": shortened, "budget_duration": "1s"}, key=owner) + clear: Final = proxy.request("POST", "/key/update", {"key": cleared, "budget_duration": None}, key=owner) + + assert (shorten.status_code, _key_row(proxy, shortened)["budget_duration"]) == ( + (403, "30d") if policy == "lower_only" else (200, "1s") + ), shorten.text + assert clear.status_code == 200, clear.text + assert _key_row(proxy, cleared)["budget_duration"] is None diff --git a/tests/unit/proxy/management_endpoints/test_key_budget_change.py b/tests/unit/proxy/management_endpoints/test_key_budget_change.py index baf8d870117..484f8638513 100644 --- a/tests/unit/proxy/management_endpoints/test_key_budget_change.py +++ b/tests/unit/proxy/management_endpoints/test_key_budget_change.py @@ -45,6 +45,7 @@ def _key( max_budget: float | None = None, budget_limits: Sequence[Mapping[str, object]] | None = None, budget_id: str | None = None, + budget_duration: str | None = None, ) -> LiteLLM_VerificationToken: return LiteLLM_VerificationToken( token="hashed-owner-key", @@ -54,6 +55,7 @@ def _key( max_budget=max_budget, budget_limits=None if budget_limits is None else [dict(window) for window in budget_limits], budget_id=budget_id, + budget_duration=budget_duration, metadata={}, ) @@ -127,6 +129,56 @@ def _window(duration: str, cap: float) -> Mapping[str, object]: (UpdateKeyRequest(key="sk-1", spend=0.0), _key(), KeyBudgetAdminOnly()), (UpdateKeyRequest(key="sk-1", soft_budget=1.0), _key(), KeyBudgetAdminOnly()), (UpdateKeyRequest(key="sk-1", soft_budget=None, max_budget=5.0), _key(max_budget=10.0), KeyBudgetAdminOnly()), + ( + UpdateKeyRequest(key="sk-1", budget_duration="1s"), + _key(max_budget=10.0, budget_duration="30d"), + KeyBudgetLoosened(), + ), + ( + UpdateKeyRequest(key="sk-1", budget_duration="60d"), + _key(max_budget=10.0, budget_duration="30d"), + KeyBudgetLoosened(), + ), + (UpdateKeyRequest(key="sk-1", budget_duration="1d"), _key(max_budget=10.0), KeyBudgetLoosened()), + ( + UpdateKeyRequest(key="sk-1", budget_duration=None), + _key(max_budget=10.0, budget_duration="30d"), + KeyBudgetTightened(), + ), + ( + UpdateKeyRequest(key="sk-1", budget_duration="30d"), + _key(max_budget=10.0, budget_duration="30d"), + KeyBudgetUnchanged(), + ), + ( + UpdateKeyRequest(key="sk-1", budget_duration="30d"), + _key(max_budget=10.0, budget_duration="Monthly"), + KeyBudgetUnchanged(), + ), + (UpdateKeyRequest(key="sk-1", budget_duration="1s"), _key(budget_duration="30d"), KeyBudgetUnchanged()), + (UpdateKeyRequest(key="sk-1", max_budget=5.0, budget_duration="1s"), _key(), KeyBudgetTightened()), + ( + UpdateKeyRequest(key="sk-1", budget_duration="1s"), + _key(budget_id="shared-tier-10", budget_duration="30d"), + KeyBudgetAdminOnly(), + ), + ( + UpdateKeyRequest(key="sk-1", budget_duration=None), + _key(budget_id="shared-tier-10", budget_duration="30d"), + KeyBudgetAdminOnly(), + ), + ( + UpdateKeyRequest(key="sk-1", budget_id="shared-tier-100"), + _key(budget_id="shared-tier-10"), + KeyBudgetAdminOnly(), + ), + (UpdateKeyRequest(key="sk-1", budget_id=None), _key(budget_id="shared-tier-10"), KeyBudgetAdminOnly()), + (UpdateKeyRequest(key="sk-1", budget_id="shared-tier-10"), _key(), KeyBudgetAdminOnly()), + ( + UpdateKeyRequest(key="sk-1", budget_id="shared-tier-10"), + _key(budget_id="shared-tier-10"), + KeyBudgetUnchanged(), + ), ], ) def test_classify_key_budget_change( @@ -465,3 +517,60 @@ async def test_owner_cannot_clear_max_budget_by_default(monkeypatch: pytest.Monk existing=_key(max_budget=10.0), ) assert exc.value.status_code == 403 + + +@pytest.mark.asyncio +@pytest.mark.parametrize( + ("policy", "data", "existing"), + [ + (None, UpdateKeyRequest(key="sk-1", budget_duration="1s"), _key(max_budget=10.0, budget_duration="30d")), + ( + "lower_only", + UpdateKeyRequest(key="sk-1", budget_duration="1s"), + _key(max_budget=10.0, budget_duration="30d"), + ), + ("ceiling", UpdateKeyRequest(key="sk-1", budget_id="shared-tier-100"), _key(budget_id="shared-tier-10")), + ("ceiling", UpdateKeyRequest(key="sk-1", budget_duration="1s"), _key(budget_id="shared-tier-10")), + ], +) +async def test_owner_cannot_restart_or_relink_a_key_budget_without_admin( + monkeypatch: pytest.MonkeyPatch, policy: str | None, data: UpdateKeyRequest, existing: LiteLLM_VerificationToken +) -> None: + with pytest.raises(HTTPException) as exc: + await _update(monkeypatch, policy=policy, data=data, existing=existing) + assert exc.value.status_code == 403 + + +@pytest.mark.asyncio +@pytest.mark.parametrize( + ("policy", "data", "existing"), + [ + (None, UpdateKeyRequest(key="sk-1", budget_duration="1d"), _key(budget_duration="30d")), + (None, UpdateKeyRequest(key="sk-1", budget_duration="24h"), _key(max_budget=10.0, budget_duration="daily")), + ( + "lower_only", + UpdateKeyRequest(key="sk-1", budget_duration=None), + _key(max_budget=10.0, budget_duration="30d"), + ), + ("ceiling", UpdateKeyRequest(key="sk-1", budget_duration="1s"), _key(max_budget=10.0, budget_duration="30d")), + ], +) +async def test_owner_changes_budget_duration_when_it_cannot_restart_a_cap_or_policy_allows( + monkeypatch: pytest.MonkeyPatch, policy: str | None, data: UpdateKeyRequest, existing: LiteLLM_VerificationToken +) -> None: + assert await _denial(monkeypatch, policy=policy, data=data, existing=existing) is None + + +@pytest.mark.asyncio +async def test_team_member_cannot_restart_a_team_key_budget_created_by_someone_else( + monkeypatch: pytest.MonkeyPatch, +) -> None: + with pytest.raises(HTTPException) as exc: + await _update( + monkeypatch, + policy=None, + data=UpdateKeyRequest(key="sk-1", budget_duration="1s"), + existing=_key(created_by=_TEAM_ADMIN, team_id=_TEAM, max_budget=10.0, budget_duration="30d"), + team=_team(["/key/update"]), + ) + assert exc.value.status_code == 403 From df06b2d4fbce65f67dbd714d41d27258b62c8123 Mon Sep 17 00:00:00 2001 From: ryan-crabbe-berri Date: Mon, 26 Oct 2026 16:52:43 -0700 Subject: [PATCH 004/262] chore(lint): add google-convention docstring rules to strict ruff gate (#48245) * chore(lint): add google-convention docstring rules (D202, D403, D417) to strict ruff gate * fix(lint): mark docstring rules external in base ruff config so RUF100 keeps their noqa --- ruff-strict.toml | 5 ++++- ruff.toml | 2 +- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/ruff-strict.toml b/ruff-strict.toml index 28102da3ccd..398cca15df2 100644 --- a/ruff-strict.toml +++ b/ruff-strict.toml @@ -2,7 +2,7 @@ extend = "ruff.toml" [lint] preview = true -select = ["ANN", "ASYNC230", "B004", "B006", "B008", "B009", "B010", "B018", "B019", "B021", "B026", "B033", "BLE", "C401", "C404", "C405", "C408", "C414", "C419", "C901", "D419", "DTZ001", "DTZ003", "DTZ005", "DTZ006", "DTZ007", "DTZ011", "EXE001", "EXE002", "F401", "FURB136", "FURB168", "FURB188", "I001", "LOG015", "N999", "PERF102", "PERF401", "PERF402", "PERF403", "PIE790", "PIE800", "PIE804", "PIE810", "PLC0206", "PLC0208", "PLC0414", "PLR0124", "PLR0206", "PLR0402", "PLR1704", "PLR1711", "PLR1714", "PLR1730", "PLR2044", "PLW0127", "PLW0133", "PLW0602", "PLW0603", "PLW1508", "PLW1510", "PYI030", "PYI036", "PYI041", "PYI064", "RET501", "RET504", "RUF010", "RUF012", "RUF015", "RUF019", "RUF022", "RUF023", "RUF046", "RUF051", "RUF059", "RUF100", "S110", "S112", "SIM101", "SIM102", "SIM103", "SIM113", "SIM114", "SIM115", "SIM117", "SIM118", "SIM201", "SIM210", "SIM211", "SIM222", "SIM401", "TC004", "TC005", "TID251", "TRY002", "TRY004", "TRY201", "TRY203", "TRY300", "UP006", "UP007", "UP008", "UP012", "UP018", "UP024", "UP028", "UP031", "UP032", "UP034", "UP035", "UP036", "UP037", "UP045"] +select = ["ANN", "ASYNC230", "B004", "B006", "B008", "B009", "B010", "B018", "B019", "B021", "B026", "B033", "BLE", "C401", "C404", "C405", "C408", "C414", "C419", "C901", "D202", "D403", "D417", "D419", "DTZ001", "DTZ003", "DTZ005", "DTZ006", "DTZ007", "DTZ011", "EXE001", "EXE002", "F401", "FURB136", "FURB168", "FURB188", "I001", "LOG015", "N999", "PERF102", "PERF401", "PERF402", "PERF403", "PIE790", "PIE800", "PIE804", "PIE810", "PLC0206", "PLC0208", "PLC0414", "PLR0124", "PLR0206", "PLR0402", "PLR1704", "PLR1711", "PLR1714", "PLR1730", "PLR2044", "PLW0127", "PLW0133", "PLW0602", "PLW0603", "PLW1508", "PLW1510", "PYI030", "PYI036", "PYI041", "PYI064", "RET501", "RET504", "RUF010", "RUF012", "RUF015", "RUF019", "RUF022", "RUF023", "RUF046", "RUF051", "RUF059", "RUF100", "S110", "S112", "SIM101", "SIM102", "SIM103", "SIM113", "SIM114", "SIM115", "SIM117", "SIM118", "SIM201", "SIM210", "SIM211", "SIM222", "SIM401", "TC004", "TC005", "TID251", "TRY002", "TRY004", "TRY201", "TRY203", "TRY300", "UP006", "UP007", "UP008", "UP012", "UP018", "UP024", "UP028", "UP031", "UP032", "UP034", "UP035", "UP036", "UP037", "UP045"] extend-select = [] # Overrides the inherited list: rules this gate enforces itself must NOT be external here, # so this config's RUF100 flags their stale `# noqa` directives. What remains external is @@ -39,6 +39,9 @@ external = [ [lint.mccabe] max-complexity = 15 +[lint.pydocstyle] +convention = "google" + [lint.pylint] max-args = 5 diff --git a/ruff.toml b/ruff.toml index 93396a723e7..715e5551fad 100644 --- a/ruff.toml +++ b/ruff.toml @@ -20,7 +20,7 @@ lint.external = [ # Family entries whose every strict rule graduated into extend-select above (FURB), and # standalone graduated codes (I001, RUF010, RUF022, RUF023, RUF051), are dropped so this # config's RUF100 polices their directives itself. - "ANN", "ASYNC230", "B", "C", "D419", "DTZ", "EXE", "LOG015", "N999", "PERF", + "ANN", "ASYNC230", "B", "C", "D202", "D403", "D417", "D419", "DTZ", "EXE", "LOG015", "N999", "PERF", "PIE", "PL", "PYI", "RET", "RUF012", "RUF015", "RUF019", "RUF046", "RUF059", "S110", "S112", "SIM", "TC", "TID251", "TRY", "UP", # Enforced by upstream litellm's ruff config, but not run in this repo's CI From 7fd8740ad5cc39c47ba433ef7444b52d301a3084 Mon Sep 17 00:00:00 2001 From: moe-berri Date: Mon, 26 Oct 2026 16:54:38 -0700 Subject: [PATCH 005/262] fix(router): isolate forwarded Anthropic subscription cooldowns (#48485) * fix: isolate forwarded Anthropic subscription cooldowns * test: fix the clock for Anthropic cooldown regression --- litellm/router.py | 2 +- tests/unit/test_router/test_router.py | 81 +++++++++++++++++++++++++++ 2 files changed, 82 insertions(+), 1 deletion(-) diff --git a/litellm/router.py b/litellm/router.py index c76e4ec843f..d5093384a17 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -563,7 +563,7 @@ _ALIAS_PARAMS_NEVER_FORWARDED: Final = frozenset( {"model", "api_base", "api_key", "api_version", "responses_api_version"} ) _ALIAS_MARKER_FORWARDED_PARAMS_KWARG: Final = "_alias_marker_forwarded_params" -_FORWARDED_CREDENTIAL_ISOLATION_PROVIDERS: Final = frozenset({"chatgpt"}) +_FORWARDED_CREDENTIAL_ISOLATION_PROVIDERS: Final = frozenset({"chatgpt", "anthropic"}) _CLAUDE_CODE_SESSION_ID_RE: Final = re.compile(r"^[a-zA-Z0-9_\-]{8,}$") _CLAUDE_CODE_SESSION_ROUTER_TTL_SECONDS: Final = 3600 CLAUDE_CODE_SESSION_ROUTER_BINDING_TARGET: Final = "claude_code_session_router_binding" diff --git a/tests/unit/test_router/test_router.py b/tests/unit/test_router/test_router.py index 6aaa3379f47..55628cb0c34 100644 --- a/tests/unit/test_router/test_router.py +++ b/tests/unit/test_router/test_router.py @@ -30475,3 +30475,84 @@ def test_request_carries_image_sees_chat_parts_and_responses_input_items(): assert litellm.Router._request_carries_image(None, {"input": _IMAGE_RESPONSES_INPUT}) is True assert litellm.Router._request_carries_image([{"role": "user", "content": "Say hi"}], {}) is False assert litellm.Router._request_carries_image(None, {"input": "Say hi"}) is False + + +@pytest.mark.asyncio +@pytest.mark.usefixtures("isolate_litellm_state") +@pytest.mark.parametrize("surface", ["chat", "messages"]) +@pytest.mark.parametrize("credential_kind", ["oauth", "api_key"]) +async def test_anthropic_caller_rate_limit_does_not_block_other_credentials( + respx_mock: respx.MockRouter, monkeypatch: pytest.MonkeyPatch, surface: str, credential_kind: str +) -> None: + from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler + from litellm.types.router import AllowedFailsPolicy + + monkeypatch.setattr(litellm, "disable_aiohttp_transport", True) + monkeypatch.setattr("time.time", lambda: 1767225600.0) + + def upstream(request: httpx.Request) -> httpx.Response: + credential: Final = request.headers.get("authorization", request.headers.get("x-api-key", "")) + if credential.endswith("limited") and route.call_count < 2: + return httpx.Response( + 429, + headers={"retry-after": "168307"}, + json={"type": "error", "error": {"type": "rate_limit_error", "message": "usage limit"}}, + ) + return httpx.Response(200, json={ + "id": "msg-healthy", "type": "message", "role": "assistant", "model": "claude-sonnet-5-5", + "content": [{"type": "text", "text": "healthy account"}], "stop_reason": "end_turn", + "usage": {"input_tokens": 2, "output_tokens": 2}, + }) + + route: Final = respx_mock.post("https://api.anthropic.com/v1/messages").mock(side_effect=upstream) + router: Final = Router( + model_list=[{ + "model_name": "claude", "litellm_params": { + "model": "anthropic/claude-sonnet-5-5", "api_key": "fake-gateway-key", + }, "model_info": {"id": "shared-anthropic"}, + }], + num_retries=0, + allowed_fails_policy=AllowedFailsPolicy(RateLimitErrorAllowedFails=1), + ) + client: Final = AsyncHTTPHandler(transport=httpx.AsyncHTTPTransport()) + + async def call(account: str | None) -> object: + credentials: Final = ( + {"provider_specific_header": { + "custom_llm_provider": "anthropic", "extra_headers": { + "Authorization": f"Bearer sk-ant-oat-fake-{account}", + }, + }} if credential_kind == "oauth" else {"api_key": f"fake-{account}"} + ) if account is not None else {} + if surface == "messages": + max_tokens: Final = litellm.get_max_tokens("anthropic/claude-sonnet-5-5") + assert max_tokens is not None + return await router.aanthropic_messages( + model="claude", messages=[{"role": "user", "content": "hello"}], + client=client, max_tokens=max_tokens, **credentials, + ) + return await router.acompletion( + model="claude", messages=[{"role": "user", "content": "hello"}], + client=client, **credentials, + ) + + try: + for _ in range(2): + with pytest.raises(litellm.RateLimitError): + await call("limited") + await GLOBAL_LOGGING_WORKER.flush() + limited_calls: Final = len(route.calls) + assert limited_calls == 2 + await call("healthy") + assert len(route.calls) == limited_calls + 1 + assert route.calls[-1].request.headers.get( + "authorization", route.calls[-1].request.headers.get("x-api-key", "") + ) == ("Bearer sk-ant-oat-fake-healthy" if credential_kind == "oauth" else "fake-healthy") + await call(None) + assert len(route.calls) == limited_calls + 2 + assert route.calls[-1].request.headers["x-api-key"] == "fake-gateway-key" + await call("limited") + assert len(route.calls) == limited_calls + 3 + finally: + await GLOBAL_LOGGING_WORKER.flush() + await client.close() From db1c871c12c2add5242f300031012d324acd4e65 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Mon, 26 Oct 2026 17:03:05 -0700 Subject: [PATCH 006/262] refactor(cost-map): drop the legacy max_tokens field in favor of max_input_tokens and max_output_tokens (#48471) * refactor(cost-map): drop the legacy max_tokens field in favor of max_input_tokens and max_output_tokens Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test: drop assertions that pinned the retired cost-map max_tokens field Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 3573 ++--------------- .../mcp_server/sampling_handler.py | 2 +- litellm/router.py | 1 - .../io_token_rate_limit_check.py | 2 +- litellm/utils.py | 15 +- model_prices_and_context_window.json | 3573 ++--------------- .../test_fallback_generalizations.py | 8 +- .../openai_like/test_openinfer_provider.py | 9 +- .../test_model_prices_and_context_window.py | 23 +- tests/unit/test_together_ai_model_metadata.py | 14 - tests/unit/test_utils.py | 41 +- 11 files changed, 543 insertions(+), 6718 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index d9df9d97d7b..c913c879ccf 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -9,9 +9,8 @@ "input_cost_per_audio_token": 0.0, "input_cost_per_token": 0.0, "litellm_provider": "one of https://docs.litellm.ai/docs/providers", - "max_input_tokens": "max input tokens, if the provider specifies it. if not default to max_tokens", - "max_output_tokens": "max output tokens, if the provider specifies it. if not default to max_tokens", - "max_tokens": "LEGACY parameter. set to max_output_tokens if provider specifies it. IF not set to max_input_tokens, if provider specifies it.", + "max_input_tokens": "max input tokens, if the provider specifies it", + "max_output_tokens": "max output tokens, if the provider specifies it", "mode": "one of: chat, embedding, completion, image_generation, audio_transcription, audio_speech, image_generation, moderation, rerank, search", "output_cost_per_reasoning_token": 0.0, "output_cost_per_token": 0.0, @@ -49,28 +48,24 @@ "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.018 }, "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.036 }, @@ -79,7 +74,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.25e-05, "source": "https://aws.amazon.com/bedrock/pricing/" @@ -89,7 +83,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.88e-05, "source": "https://aws.amazon.com/bedrock/pricing/" @@ -100,7 +93,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-large.md" @@ -111,7 +103,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-mini.md" @@ -121,7 +112,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 70000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -298,7 +288,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", @@ -311,7 +300,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", @@ -324,7 +312,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", @@ -337,7 +324,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", @@ -352,7 +338,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, @@ -368,7 +353,6 @@ "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, @@ -389,7 +373,6 @@ "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, @@ -414,7 +397,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -435,7 +417,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.311e-06, "supports_function_calling": true, @@ -455,7 +436,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://aws.amazon.com/nova/pricing/", @@ -474,7 +454,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.597e-06, "supports_function_calling": true, @@ -494,7 +473,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://aws.amazon.com/nova/pricing/", @@ -518,7 +496,6 @@ "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, @@ -544,7 +521,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -562,7 +538,6 @@ "amazon.nova-2-multimodal-embeddings-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 8172, - "max_tokens": 8172, "mode": "embedding", "input_cost_per_token": 1.35e-07, "input_cost_per_image": 6e-05, @@ -583,7 +558,6 @@ "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, @@ -602,7 +576,6 @@ "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, @@ -626,7 +599,6 @@ "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, @@ -646,7 +618,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2.75e-06, @@ -660,7 +631,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -669,7 +639,6 @@ "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 128, - "max_tokens": 128, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, @@ -684,7 +653,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 @@ -693,7 +661,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 @@ -702,7 +669,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -740,7 +706,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -755,7 +720,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -770,7 +734,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -784,7 +747,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, - "max_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, @@ -798,7 +760,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, - "max_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, @@ -812,7 +773,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, - "max_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, @@ -860,7 +820,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 6e-07 }, @@ -869,7 +828,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 2e-07 }, @@ -878,7 +836,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, @@ -889,7 +846,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -909,7 +865,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", @@ -941,7 +896,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -964,7 +918,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -982,7 +935,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -1001,7 +953,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -1021,7 +972,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -1039,7 +989,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -1054,7 +1003,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true @@ -1067,7 +1015,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -1097,7 +1044,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -1125,7 +1071,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1164,7 +1109,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1204,7 +1148,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1244,7 +1187,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1284,7 +1226,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1324,7 +1265,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1364,7 +1304,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1405,7 +1344,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, @@ -1427,7 +1365,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1470,7 +1407,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1513,7 +1449,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1556,7 +1491,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1596,7 +1530,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1639,7 +1572,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1678,7 +1610,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1721,7 +1652,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1760,7 +1690,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1803,7 +1732,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1842,7 +1770,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1880,7 +1807,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1922,7 +1848,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1965,7 +1890,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "search_context_cost_per_query": { @@ -2010,7 +1934,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -2053,7 +1976,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "search_context_cost_per_query": { @@ -2098,7 +2020,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2141,7 +2062,6 @@ "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": { @@ -2186,7 +2106,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2229,7 +2148,6 @@ "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": { @@ -2269,7 +2187,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2312,7 +2229,6 @@ "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": { @@ -2357,7 +2273,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2395,7 +2310,6 @@ "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": { @@ -2435,7 +2349,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -2480,7 +2393,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -2525,7 +2437,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2570,7 +2481,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2615,7 +2525,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2660,7 +2569,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2703,7 +2611,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2745,7 +2652,6 @@ "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": { @@ -2790,7 +2696,6 @@ "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": { @@ -2835,7 +2740,6 @@ "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": { @@ -2880,7 +2784,6 @@ "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": { @@ -2925,7 +2828,6 @@ "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": { @@ -2970,7 +2872,6 @@ "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": { @@ -3011,7 +2912,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3050,7 +2950,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3089,7 +2988,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -3128,7 +3026,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -3167,7 +3064,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -3206,7 +3102,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -3246,7 +3141,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3286,7 +3180,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3319,7 +3212,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05 }, @@ -3328,7 +3220,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -3338,7 +3229,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07 }, @@ -3347,7 +3237,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -3356,7 +3245,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" @@ -3366,7 +3254,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" @@ -3376,7 +3263,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07 }, @@ -3385,7 +3271,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -3394,7 +3279,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07 }, @@ -3403,7 +3287,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" @@ -3413,7 +3296,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" @@ -3423,7 +3305,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1", @@ -3434,7 +3315,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1", @@ -3445,7 +3325,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1", @@ -3457,7 +3336,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.52e-07, "supports_function_calling": true, @@ -3473,7 +3351,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.48e-07, "supports_function_calling": true, @@ -3489,7 +3366,6 @@ "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, @@ -3508,7 +3384,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -3543,7 +3418,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3595,7 +3469,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -3628,7 +3501,6 @@ "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://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -3640,7 +3512,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 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'", @@ -3670,7 +3541,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -3685,7 +3555,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -3709,7 +3578,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": true, @@ -3734,7 +3602,6 @@ "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, @@ -3765,7 +3632,6 @@ "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, @@ -3797,7 +3663,6 @@ "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, @@ -3830,7 +3695,6 @@ "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, @@ -3868,7 +3732,6 @@ "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, @@ -3899,7 +3762,6 @@ "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, @@ -3938,7 +3800,6 @@ "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, @@ -3971,7 +3832,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -3996,7 +3856,6 @@ "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": { @@ -4030,7 +3889,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": false, @@ -4052,7 +3910,6 @@ "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -4087,7 +3944,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, @@ -4105,7 +3961,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4154,7 +4009,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4203,7 +4057,6 @@ "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, @@ -4252,7 +4105,6 @@ "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, @@ -4304,7 +4156,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4345,7 +4196,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", @@ -4395,7 +4245,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", @@ -4439,7 +4288,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4486,7 +4334,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4533,7 +4380,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4581,7 +4427,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4629,7 +4474,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -4675,7 +4519,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -4717,7 +4560,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_priority": 9e-06, @@ -4759,7 +4601,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_priority": 9e-06, @@ -4801,7 +4642,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_priority": 2.5e-06, @@ -4843,7 +4683,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_priority": 2.5e-06, @@ -4883,7 +4722,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/", "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)" @@ -4895,7 +4733,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/", "comment": "Catalog-name twin of azure_ai/model_router: the flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it" @@ -4908,7 +4745,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -4929,7 +4765,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -4949,7 +4784,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -4968,7 +4802,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -4987,7 +4820,6 @@ "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -5006,7 +4838,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2.2e-05, "output_cost_per_token": 2.64e-06, @@ -5026,7 +4857,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 2.2e-05, @@ -5046,7 +4876,6 @@ "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, @@ -5076,7 +4905,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -5116,7 +4944,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, @@ -5155,7 +4982,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ @@ -5196,7 +5022,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -5228,7 +5053,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-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'", @@ -5261,7 +5085,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, @@ -5298,7 +5121,6 @@ "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, @@ -5317,7 +5139,6 @@ "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, @@ -5335,7 +5156,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -5353,7 +5173,6 @@ "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, @@ -5371,7 +5190,6 @@ "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, @@ -5389,7 +5207,6 @@ "litellm_provider": "azure", "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, @@ -5409,7 +5226,6 @@ "litellm_provider": "azure", "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, @@ -5426,7 +5242,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -5443,7 +5258,6 @@ "litellm_provider": "azure", "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, @@ -5463,7 +5277,6 @@ "litellm_provider": "azure", "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, @@ -5484,7 +5297,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -5525,7 +5337,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 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'", @@ -5557,7 +5368,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-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'", @@ -5587,7 +5397,6 @@ "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -5597,7 +5406,7 @@ "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, - "max_tokens": 4097, + "max_output_tokens": 4097, "mode": "completion", "output_cost_per_token": 2.2e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -5607,7 +5416,6 @@ "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -5619,7 +5427,6 @@ "litellm_provider": "azure", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", @@ -5631,7 +5438,6 @@ "litellm_provider": "azure", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", @@ -5642,7 +5448,7 @@ "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, - "max_tokens": 4097, + "max_output_tokens": 4097, "mode": "completion", "output_cost_per_token": 2.2e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -5651,7 +5457,7 @@ "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, - "max_tokens": 4097, + "max_output_tokens": 4097, "mode": "completion", "output_cost_per_token": 2.2e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -5662,7 +5468,6 @@ "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -5674,7 +5479,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, @@ -5687,7 +5491,6 @@ "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", @@ -5699,7 +5502,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, @@ -5712,7 +5514,6 @@ "litellm_provider": "azure", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00012, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", @@ -5724,7 +5525,6 @@ "litellm_provider": "azure", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00012, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", @@ -5735,7 +5535,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", @@ -5748,7 +5547,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", @@ -5762,7 +5560,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", @@ -5779,7 +5576,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, @@ -5817,7 +5613,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, @@ -5855,7 +5650,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, @@ -5893,7 +5687,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, @@ -5929,7 +5722,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -5963,7 +5755,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -5997,7 +5788,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00015, "output_cost_per_token_batches": 7.5e-05, @@ -6017,7 +5807,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -6034,7 +5823,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -6053,7 +5841,6 @@ "litellm_provider": "azure", "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, @@ -6073,7 +5860,6 @@ "litellm_provider": "azure", "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, @@ -6092,7 +5878,6 @@ "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, @@ -6125,7 +5910,6 @@ "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, @@ -6157,7 +5941,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -6190,7 +5973,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -6225,7 +6007,6 @@ "litellm_provider": "azure", "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, @@ -6257,7 +6038,6 @@ "litellm_provider": "azure", "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, @@ -6290,7 +6070,6 @@ "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, @@ -6322,7 +6101,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -6340,7 +6118,6 @@ "litellm_provider": "azure", "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, @@ -6358,7 +6135,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 6e-07, @@ -6392,7 +6168,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -6414,7 +6189,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -6449,7 +6223,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -6483,7 +6256,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -6518,7 +6290,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -6552,7 +6323,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, @@ -6587,7 +6357,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -6622,7 +6391,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -6656,7 +6424,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -6720,7 +6487,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 0.0002, "output_cost_per_token": 2e-05, @@ -6739,7 +6505,6 @@ "litellm_provider": "azure", "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, @@ -6793,7 +6558,6 @@ "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": [ @@ -6817,7 +6581,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, @@ -6860,7 +6623,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, @@ -6895,7 +6657,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "output_cost_per_token_priority": 3.6e-06, @@ -6932,7 +6693,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -6971,7 +6731,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -7008,7 +6767,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 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'", @@ -7044,7 +6802,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, @@ -7083,7 +6840,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, @@ -7122,7 +6878,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -7158,7 +6913,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -7194,7 +6948,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, @@ -7228,7 +6981,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -7269,7 +7021,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7294,7 +7045,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7316,7 +7066,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7337,7 +7086,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7358,7 +7106,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7380,7 +7127,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7401,7 +7147,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7422,7 +7167,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7444,7 +7188,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7465,7 +7208,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7486,7 +7228,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7502,7 +7243,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7518,7 +7258,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7550,7 +7289,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7582,7 +7320,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7618,7 +7355,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, @@ -7658,7 +7394,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, @@ -7696,7 +7431,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7730,7 +7464,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, @@ -7762,7 +7495,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, @@ -7801,7 +7533,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, @@ -7850,7 +7581,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -7906,7 +7636,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -7956,7 +7685,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -8006,7 +7734,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -8062,7 +7789,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -8112,7 +7838,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -8163,7 +7888,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -8212,7 +7936,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -8266,7 +7989,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -8327,7 +8049,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -8391,7 +8112,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -8455,7 +8175,6 @@ "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, @@ -8519,7 +8238,6 @@ "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, @@ -8583,7 +8301,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, @@ -8647,7 +8364,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, @@ -8699,7 +8415,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -8748,7 +8463,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -8797,7 +8511,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -8846,7 +8559,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -8901,7 +8613,6 @@ "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, @@ -8954,7 +8665,6 @@ "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, @@ -9001,7 +8711,6 @@ "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, @@ -9050,7 +8759,6 @@ "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, @@ -9099,7 +8807,6 @@ "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, @@ -9148,7 +8855,6 @@ "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, @@ -9197,7 +8903,6 @@ "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, @@ -9242,7 +8947,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "reasoning_effort_levels": [ @@ -9279,7 +8983,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "reasoning_effort_levels": [ @@ -9325,7 +9028,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, @@ -9380,7 +9082,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, @@ -9436,7 +9137,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, @@ -9492,7 +9192,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, @@ -9542,7 +9241,6 @@ "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, @@ -9591,7 +9289,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "output_cost_per_token_above_272k_tokens": 8.25e-07, @@ -9646,7 +9343,6 @@ "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, @@ -9689,7 +9385,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.3e-05, "reasoning_effort_levels": [ @@ -9735,7 +9430,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, @@ -9790,7 +9484,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, @@ -9846,7 +9539,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, @@ -9902,7 +9594,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, @@ -9961,7 +9652,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -10020,7 +9710,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, @@ -10075,7 +9764,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, @@ -10127,7 +9815,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -10187,7 +9874,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_batches": 1.5e-05, @@ -10246,7 +9932,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -10299,7 +9984,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -10353,7 +10037,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -10406,7 +10089,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -10453,7 +10135,6 @@ "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -10497,7 +10178,6 @@ "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -10539,7 +10219,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { @@ -10590,7 +10269,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { @@ -10642,7 +10320,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "search_context_cost_per_query": { @@ -10690,7 +10367,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "search_context_cost_per_query": { @@ -11066,7 +10742,7 @@ "input_cost_per_token": 8e-06, "litellm_provider": "azure", "max_input_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_function_calling": true @@ -11075,7 +10751,7 @@ "input_cost_per_token": 8e-06, "litellm_provider": "azure", "max_input_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_function_calling": true @@ -11087,7 +10763,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_function_calling": true, @@ -11105,7 +10780,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_batches": 3e-05, @@ -11124,7 +10798,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -11142,7 +10815,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -11160,7 +10832,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "supported_endpoints": [ @@ -11191,7 +10862,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, @@ -11223,7 +10893,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 4e-05, "search_context_cost_per_query": { @@ -11261,7 +10930,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_prompt_caching": true, @@ -11278,7 +10946,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -11295,7 +10962,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, @@ -11326,7 +10992,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, @@ -11357,7 +11022,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supported_endpoints": [ @@ -11388,7 +11052,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -11433,7 +11096,6 @@ "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -11443,7 +11105,6 @@ "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -11453,7 +11114,6 @@ "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -11504,7 +11164,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, @@ -11542,7 +11201,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, @@ -11578,7 +11236,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, @@ -11612,7 +11269,6 @@ "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, @@ -11633,7 +11289,6 @@ "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, @@ -11653,7 +11308,6 @@ "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, @@ -11672,7 +11326,6 @@ "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11691,7 +11344,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11710,7 +11362,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2.2e-05, "output_cost_per_token": 2.64e-06, @@ -11730,7 +11381,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 2.2e-05, @@ -11750,7 +11400,6 @@ "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, @@ -11780,7 +11429,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -11820,7 +11468,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, @@ -11858,7 +11505,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, @@ -11896,7 +11542,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ @@ -11937,7 +11582,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11969,7 +11613,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12002,7 +11645,6 @@ "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, @@ -12021,7 +11663,6 @@ "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, @@ -12039,7 +11680,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -12057,7 +11697,6 @@ "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, @@ -12090,7 +11729,6 @@ "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, @@ -12123,7 +11761,6 @@ "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, @@ -12141,7 +11778,6 @@ "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, @@ -12159,7 +11795,6 @@ "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, @@ -12180,7 +11815,6 @@ "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, @@ -12204,7 +11838,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -12215,7 +11848,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -12227,7 +11859,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12245,7 +11876,6 @@ "azure_ai/FLUX-1.1-pro": { "litellm_provider": "azure_ai", "max_input_tokens": 5000, - "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", @@ -12256,7 +11886,6 @@ "azure_ai/FLUX.1-Kontext-pro": { "litellm_provider": "azure_ai", "max_input_tokens": 5000, - "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", @@ -12267,7 +11896,6 @@ "azure_ai/flux.2-pro": { "litellm_provider": "azure_ai", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -12279,7 +11907,6 @@ "input_cost_per_pixel": 5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "image_generation", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", "supported_endpoints": [ @@ -12301,7 +11928,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12316,7 +11942,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.828e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12332,7 +11957,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.52e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12348,7 +11972,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12363,7 +11986,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12378,7 +12000,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 7.26e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12393,7 +12014,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.46e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12415,7 +12035,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.3e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12438,7 +12057,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12461,7 +12079,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12484,7 +12101,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ @@ -12513,7 +12129,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12528,7 +12143,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12571,7 +12185,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.64e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12637,7 +12250,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12660,7 +12272,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.1e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -12672,7 +12283,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12685,7 +12295,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 10000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", @@ -12699,7 +12308,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 2048, - "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", @@ -12711,7 +12319,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.54e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12723,7 +12330,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12736,7 +12342,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12749,7 +12354,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12762,7 +12366,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12775,7 +12378,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12788,7 +12390,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12801,7 +12402,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12814,7 +12414,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12827,7 +12426,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12840,7 +12438,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12854,7 +12451,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12867,7 +12463,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12881,7 +12476,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12893,7 +12487,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12935,7 +12528,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 8182, - "max_tokens": 8182, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12975,7 +12567,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12989,7 +12580,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" @@ -13001,7 +12591,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" @@ -13012,7 +12601,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" @@ -13023,7 +12611,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" @@ -13033,7 +12620,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -13048,7 +12634,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -13064,7 +12649,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -13076,7 +12660,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -13092,7 +12675,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 5.1e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -13109,7 +12691,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -13122,7 +12703,6 @@ "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": 3072, @@ -13142,7 +12722,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -13159,7 +12738,6 @@ "litellm_provider": "azure_ai", "max_input_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, @@ -13180,7 +12758,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, @@ -13200,7 +12777,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -13219,7 +12795,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -13236,7 +12811,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, @@ -13250,7 +12824,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, @@ -13264,7 +12837,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -13279,7 +12851,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00971, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" @@ -13290,7 +12861,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 70000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -13302,7 +12872,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -13319,7 +12888,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -13343,7 +12911,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-08, "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", @@ -13356,7 +12923,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 32000, "max_output_tokens": 8191, - "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", @@ -13369,7 +12935,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -13381,7 +12946,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -13393,7 +12957,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 8191, - "max_tokens": 8191, "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'", @@ -13407,7 +12970,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "supports_assistant_prefill": true, @@ -13420,7 +12982,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -13432,7 +12993,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -13445,7 +13005,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -13459,7 +13018,6 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -13471,7 +13029,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -13481,7 +13038,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -13491,7 +13047,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -13501,7 +13056,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -13526,7 +13080,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13536,7 +13089,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { @@ -13545,7 +13097,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13555,7 +13106,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13565,7 +13115,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { @@ -13574,7 +13123,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13583,7 +13131,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 7.55e-06, "supports_tool_choice": true @@ -13593,7 +13140,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -13603,7 +13149,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -13614,7 +13159,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13634,7 +13178,6 @@ "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, @@ -13652,7 +13195,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -13672,7 +13214,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13686,7 +13227,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13704,7 +13244,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -13723,7 +13262,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13737,7 +13275,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13757,7 +13294,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -13768,7 +13304,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -13779,7 +13314,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13799,7 +13333,6 @@ "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, @@ -13817,7 +13350,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -13837,7 +13369,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13851,7 +13382,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13869,7 +13399,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -13887,7 +13416,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -13906,7 +13434,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13926,7 +13453,6 @@ "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, @@ -13944,7 +13470,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -13963,7 +13488,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13981,7 +13505,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -13999,7 +13522,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.03e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -14010,7 +13532,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.9e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -14021,7 +13542,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14041,7 +13561,6 @@ "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, @@ -14059,7 +13578,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14078,7 +13596,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14096,7 +13613,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14106,7 +13622,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { @@ -14115,7 +13630,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14125,7 +13639,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14135,7 +13648,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { @@ -14144,7 +13656,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14153,7 +13664,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 8.38e-06, "supports_tool_choice": true @@ -14163,7 +13673,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05 }, @@ -14172,7 +13681,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -14184,7 +13692,6 @@ "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, @@ -14202,7 +13709,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14221,7 +13727,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -14239,7 +13744,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.78e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -14250,7 +13754,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.5e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -14262,7 +13765,6 @@ "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, @@ -14280,7 +13782,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14299,7 +13800,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -14317,7 +13817,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.55e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -14328,7 +13827,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -14340,7 +13838,6 @@ "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, @@ -14358,7 +13855,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14377,7 +13873,6 @@ "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, @@ -14396,7 +13891,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.86e-06, "output_cost_per_token_flex": 9.3e-07, @@ -14414,7 +13908,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -14425,7 +13918,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.56e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", @@ -14437,7 +13929,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -14450,7 +13941,6 @@ "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, @@ -14468,7 +13958,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14487,7 +13976,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -14504,7 +13992,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Anthropic via Invoke route does not currently support pdf input." }, @@ -14523,7 +14010,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.88e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -14534,7 +14020,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.01e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -14545,7 +14030,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14565,7 +14049,6 @@ "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, @@ -14583,7 +14066,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14603,7 +14085,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14617,7 +14098,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14635,7 +14115,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -14653,7 +14132,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14663,7 +14141,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { @@ -14672,7 +14149,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14682,7 +14158,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14692,7 +14167,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { @@ -14701,7 +14175,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14710,7 +14183,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true @@ -14720,7 +14192,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -14730,7 +14201,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -14741,7 +14211,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -14752,7 +14221,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -14763,7 +14231,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -14774,7 +14241,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", @@ -14786,7 +14252,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -14798,7 +14263,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14818,7 +14282,6 @@ "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, @@ -14838,7 +14301,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -14855,7 +14317,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14869,7 +14330,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14887,7 +14347,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, @@ -14905,7 +14364,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14925,7 +14383,6 @@ "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, @@ -14943,7 +14400,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14963,7 +14419,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14977,7 +14432,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14995,7 +14449,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, @@ -15013,7 +14466,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.84e-06, "supports_function_calling": true, @@ -15027,7 +14479,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 @@ -15036,7 +14487,6 @@ "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -15046,7 +14496,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.7e-06 }, @@ -15055,7 +14504,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-07 }, @@ -15064,7 +14512,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, @@ -15077,7 +14524,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -15106,7 +14552,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -15127,7 +14572,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.5e-06, "supports_pdf_input": true @@ -15137,7 +14581,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 2.65e-06, "supports_pdf_input": true @@ -15145,7 +14588,6 @@ "bedrock/us-gov-west-1/amazon.nova-2-multimodal-embeddings-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 8172, - "max_tokens": 8172, "mode": "embedding", "input_cost_per_token": 1.62e-07, "input_cost_per_image": 7.2e-05, @@ -15164,7 +14606,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.88e-07, "supports_function_calling": true, @@ -15180,7 +14621,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.68e-07, "supports_function_calling": true, @@ -15194,7 +14634,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.84e-06, "supports_function_calling": true, @@ -15208,7 +14647,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 @@ -15217,7 +14655,6 @@ "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -15227,7 +14664,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.6e-06 }, @@ -15236,7 +14672,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-07 }, @@ -15245,7 +14680,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, @@ -15258,7 +14692,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -15287,7 +14720,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -15308,7 +14740,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.5e-06, "supports_pdf_input": true @@ -15318,7 +14749,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 6e-07, "supports_pdf_input": true @@ -15329,7 +14759,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -15340,7 +14769,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -15351,7 +14779,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -15361,7 +14788,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { @@ -15370,7 +14796,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -15380,7 +14805,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -15390,7 +14814,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { @@ -15399,7 +14822,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -15408,7 +14830,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true @@ -15418,7 +14839,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -15428,7 +14848,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -15439,7 +14858,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -15450,7 +14868,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", @@ -15462,7 +14879,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -15474,7 +14890,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -15494,7 +14909,6 @@ "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, @@ -15514,7 +14928,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -15531,7 +14944,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -15545,7 +14957,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -15563,7 +14974,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, @@ -15582,7 +14992,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -15672,7 +15081,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -15683,7 +15091,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -15694,7 +15101,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, @@ -15705,7 +15111,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -15716,7 +15121,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -15727,7 +15131,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.5e-07, "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras", @@ -15742,7 +15145,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://inference-docs.cerebras.ai/support/pricing", @@ -15755,7 +15157,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.49e-06, "source": "https://api.cerebras.ai/public/v1/models/qwen-3.8-27b", @@ -15771,7 +15172,6 @@ "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07 }, @@ -15802,7 +15202,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -15829,7 +15228,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -15858,7 +15256,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -15892,7 +15289,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -15928,7 +15324,6 @@ "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, @@ -15972,7 +15367,6 @@ "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, @@ -16019,7 +15413,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -16063,7 +15456,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -16092,7 +15484,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16126,7 +15517,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16163,7 +15553,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16206,7 +15595,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16249,7 +15637,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16293,7 +15680,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16337,7 +15723,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -16382,7 +15767,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -16428,7 +15812,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, @@ -16474,7 +15857,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16522,7 +15904,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16638,7 +16019,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 3072, "max_output_tokens": 3072, - "max_tokens": 3072, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -16648,7 +16028,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 2048, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -16658,7 +16037,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -16668,7 +16046,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -16678,7 +16055,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-07, "rpm": 300, @@ -16690,7 +16066,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -16700,7 +16075,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 80000, "max_output_tokens": 80000, - "max_tokens": 80000, "mode": "chat", "output_cost_per_token": 3.35e-07, "rpm": 300 @@ -16710,7 +16084,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-08, "rpm": 300 @@ -16720,7 +16093,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 15000, "max_output_tokens": 15000, - "max_tokens": 15000, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -16731,7 +16103,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "rpm": 20, @@ -16743,7 +16114,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 80000, "max_output_tokens": 80000, - "max_tokens": 80000, "mode": "chat", "output_cost_per_token": 4.881e-06, "rpm": 300, @@ -16754,7 +16124,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.87e-07, "rpm": 300 @@ -16764,7 +16133,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 60000, "max_output_tokens": 60000, - "max_tokens": 60000, "mode": "chat", "output_cost_per_token": 2.01e-07, "rpm": 300 @@ -16775,7 +16143,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "rpm": 20, @@ -16787,7 +16154,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-07, "rpm": 300, @@ -16799,7 +16165,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -16809,7 +16174,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 24000, "max_output_tokens": 24000, - "max_tokens": 24000, "mode": "chat", "output_cost_per_token": 2.253e-06, "rpm": 300, @@ -16820,7 +16184,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1.12e-07, "rpm": 300, @@ -16831,7 +16194,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-06, "rpm": 300 @@ -16842,7 +16204,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "rpm": 20, @@ -16854,7 +16215,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-06, "rpm": 300, @@ -16866,7 +16226,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.55e-07, "rpm": 300 @@ -16876,7 +16235,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.35e-07, "rpm": 300, @@ -16888,7 +16246,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 3500, "max_output_tokens": 3500, - "max_tokens": 3500, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -16898,7 +16255,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 3e-07, "rpm": 300, @@ -16910,7 +16266,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.55e-07, "rpm": 300, @@ -16921,7 +16276,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.76e-07, "rpm": 300, @@ -16932,7 +16286,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "rpm": 300, @@ -16944,7 +16297,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 8.5e-07, "rpm": 300, @@ -16955,7 +16307,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 24000, "max_output_tokens": 24000, - "max_tokens": 24000, "mode": "chat", "output_cost_per_token": 1e-06, "rpm": 300, @@ -16966,7 +16317,6 @@ "litellm_provider": "codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/", @@ -16978,7 +16328,6 @@ "litellm_provider": "codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/", @@ -16990,7 +16339,6 @@ "litellm_provider": "bedrock", "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/", @@ -17001,7 +16349,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -17011,7 +16358,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -17021,7 +16367,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -17031,7 +16376,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -17042,7 +16386,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -17053,7 +16396,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -17064,7 +16406,6 @@ "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": 1536, @@ -17076,7 +16417,6 @@ "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, @@ -17087,7 +16427,6 @@ "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, @@ -17109,7 +16448,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-cohere-rerank-3-5.md" @@ -17119,7 +16457,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -17131,7 +16468,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "source": "https://docs.cohere.com/docs/models" }, @@ -17140,7 +16476,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.cohere.com/docs/command-a-plus", @@ -17155,7 +16490,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06 }, @@ -17164,7 +16498,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -17175,7 +16508,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -17186,7 +16518,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.cohere.com/v2/docs/command-r7b", @@ -17199,7 +16530,7 @@ "input_cost_per_token": 1.12e-06, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.coralbricks.ai/pricing", @@ -17222,7 +16553,7 @@ "input_cost_per_token": 1.12e-06, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.coralbricks.ai/pricing", @@ -17245,7 +16576,7 @@ "input_cost_per_token": 1.12e-06, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.coralbricks.ai/pricing", @@ -17268,7 +16599,7 @@ "input_cost_per_token": 1e-08, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.coralbricks.ai/pricing", @@ -17291,7 +16622,7 @@ "input_cost_per_token": 1e-08, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.coralbricks.ai/pricing", @@ -17314,7 +16645,7 @@ "input_cost_per_token": 1e-08, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.coralbricks.ai/pricing", @@ -17337,7 +16668,6 @@ "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": [ @@ -17367,7 +16697,6 @@ "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": [ @@ -17398,7 +16727,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -17420,7 +16748,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -17442,7 +16769,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17458,7 +16784,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17474,7 +16799,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17490,7 +16814,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 202745, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17506,7 +16829,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17522,7 +16844,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 229376, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17538,7 +16859,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17550,7 +16870,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17579,7 +16898,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17609,7 +16927,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 30720, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17622,7 +16939,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17635,7 +16951,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17648,7 +16963,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -17662,7 +16976,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -17675,7 +16988,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17706,7 +17018,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17737,7 +17048,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17769,7 +17079,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -17783,7 +17092,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17796,7 +17104,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -17810,7 +17117,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -17823,7 +17129,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17834,7 +17139,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17883,7 +17187,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17928,7 +17231,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17977,7 +17279,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18022,7 +17323,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18059,7 +17359,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18096,7 +17395,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18134,7 +17432,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18146,7 +17443,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18159,7 +17455,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18172,7 +17467,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18186,7 +17480,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18199,7 +17492,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18212,7 +17504,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 260096, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18250,7 +17541,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18284,7 +17574,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18298,7 +17587,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18334,7 +17622,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18352,7 +17639,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -18371,7 +17657,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -18390,7 +17675,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 98304, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18711,7 +17995,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.qwencloud.com/models", @@ -18727,7 +18010,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.qwencloud.com/models", @@ -18743,7 +18025,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.qwencloud.com/models", @@ -18759,7 +18040,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 202745, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.qwencloud.com/models", @@ -18775,7 +18055,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.qwencloud.com/models", @@ -18791,7 +18070,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 229376, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.qwencloud.com/models", @@ -18807,7 +18085,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.qwencloud.com/models", @@ -18819,7 +18096,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18848,7 +18124,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18878,7 +18153,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 30720, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.qwencloud.com/models", @@ -18891,7 +18165,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -18904,7 +18177,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -18917,7 +18189,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -18931,7 +18202,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -18944,7 +18214,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18975,7 +18244,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19006,7 +18274,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19038,7 +18305,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -19052,7 +18318,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.qwencloud.com/models", @@ -19065,7 +18330,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -19079,7 +18343,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -19092,7 +18355,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19103,7 +18365,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19152,7 +18413,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19197,7 +18457,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19246,7 +18505,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19291,7 +18549,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19328,7 +18585,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19365,7 +18621,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19403,7 +18658,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -19415,7 +18669,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -19428,7 +18681,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.qwencloud.com/models", @@ -19441,7 +18693,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.qwencloud.com/models", @@ -19455,7 +18706,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.qwencloud.com/models", @@ -19468,7 +18718,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.qwencloud.com/models", @@ -19481,7 +18730,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 260096, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19519,7 +18767,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19553,7 +18800,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.qwencloud.com/models", @@ -19567,7 +18813,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19603,7 +18848,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.qwencloud.com/models", @@ -19619,7 +18863,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 98304, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.qwencloud.com/models", @@ -19940,7 +19183,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19956,7 +19198,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19972,7 +19213,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19988,7 +19228,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 202745, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20004,7 +19243,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20020,7 +19258,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 229376, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20036,7 +19273,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20048,7 +19284,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20077,7 +19312,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20107,7 +19341,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 30720, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20120,7 +19353,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20133,7 +19365,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20146,7 +19377,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -20160,7 +19390,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -20173,7 +19402,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20204,7 +19432,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20235,7 +19462,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20267,7 +19493,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -20281,7 +19506,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20294,7 +19518,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -20308,7 +19531,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -20321,7 +19543,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20332,7 +19553,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20381,7 +19601,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20426,7 +19645,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20475,7 +19693,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20520,7 +19737,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20557,7 +19773,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20594,7 +19809,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20632,7 +19846,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -20644,7 +19857,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -20657,7 +19869,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -20670,7 +19881,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -20684,7 +19894,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -20697,7 +19906,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -20710,7 +19918,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 260096, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20748,7 +19955,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20782,7 +19988,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20796,7 +20001,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20832,7 +20036,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20850,7 +20053,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -20869,7 +20071,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -20888,7 +20089,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 98304, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -21210,7 +20410,6 @@ "input_dbu_cost_per_token": 1.429e-06, "litellm_provider": "databricks", "max_input_tokens": 512, - "max_tokens": 512, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21228,7 +20427,6 @@ "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." }, @@ -21257,7 +20455,6 @@ "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." }, @@ -21287,7 +20484,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21311,7 +20507,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21335,7 +20530,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21359,7 +20553,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21384,7 +20577,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21409,7 +20601,6 @@ "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." }, @@ -21436,7 +20627,6 @@ "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." }, @@ -21464,7 +20654,6 @@ "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." }, @@ -21493,7 +20682,6 @@ "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." }, @@ -21528,7 +20716,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21552,7 +20739,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21575,7 +20761,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21599,7 +20784,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21624,7 +20808,6 @@ "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. Introductory launch rates of 28.571 input / 142.857 output / 35.714 cache write / 2.857 cache read DBU run through 2026-08-31; the standard rates are listed here because entries carry no expiry date." }, @@ -21653,7 +20836,6 @@ "token_count_framing": 97, "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." }, @@ -21686,7 +20868,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." }, @@ -21715,7 +20896,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21749,7 +20929,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21784,7 +20963,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21812,7 +20990,6 @@ "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "metadata": { "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." }, @@ -21833,7 +21010,6 @@ "litellm_provider": "databricks", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "metadata": { "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." }, @@ -21858,7 +21034,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21891,7 +21066,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21923,7 +21097,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21939,7 +21112,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." }, @@ -21964,7 +21136,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." }, @@ -21993,7 +21164,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "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." }, @@ -22025,7 +21195,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "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." }, @@ -22056,7 +21225,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "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." }, @@ -22089,7 +21257,6 @@ "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22106,7 +21273,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." }, @@ -22134,7 +21300,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "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." }, @@ -22165,7 +21330,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "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." }, @@ -22195,7 +21359,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22215,7 +21378,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22235,7 +21397,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22255,7 +21416,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22275,7 +21435,6 @@ "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22304,7 +21463,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22333,7 +21491,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22362,7 +21519,6 @@ "litellm_provider": "databricks", "max_input_tokens": 922000, "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. Rates reflect OpenAI's promotional pricing in effect through November 21, 2026; afterwards input, cache and Batch rates are 25% higher and output rates 50% higher." }, @@ -22391,7 +21547,6 @@ "litellm_provider": "databricks", "max_input_tokens": 922000, "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." }, @@ -22420,7 +21575,6 @@ "litellm_provider": "databricks", "max_input_tokens": 922000, "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." }, @@ -22449,7 +21603,6 @@ "litellm_provider": "databricks", "max_input_tokens": 922000, "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." }, @@ -22478,7 +21631,6 @@ "litellm_provider": "databricks", "max_input_tokens": 922000, "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." }, @@ -22507,7 +21659,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22527,7 +21678,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22547,7 +21697,6 @@ "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22564,7 +21713,6 @@ "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22606,7 +21754,6 @@ "input_dbu_cost_per_token": 1.857e-06, "litellm_provider": "databricks", "max_input_tokens": 8192, - "max_tokens": 8192, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22653,7 +21800,6 @@ "token_count_framing": 100, "max_input_tokens": 1000000, "max_output_tokens": 1048576, - "max_tokens": 1048576, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." }, @@ -22687,7 +21833,6 @@ "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." }, @@ -22705,7 +21850,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22722,7 +21866,6 @@ "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22740,7 +21883,6 @@ "litellm_provider": "databricks", "max_input_tokens": 262144, "max_output_tokens": 25000, - "max_tokens": 25000, "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." }, @@ -22790,7 +21932,6 @@ "input_dbu_cost_per_token": 2.86e-07, "litellm_provider": "databricks", "max_input_tokens": 32768, - "max_tokens": 32768, "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." }, @@ -22836,7 +21977,6 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, @@ -23431,7 +22571,6 @@ ] }, "deepinfra/Gryphe/MythoMax-L2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 4e-07, @@ -23443,7 +22582,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-06, @@ -23454,7 +22592,6 @@ "supports_function_calling": true }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 7e-07, @@ -23465,7 +22602,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/QwQ-32B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, @@ -23476,7 +22612,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen2.5-72B-Instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 3.6e-07, @@ -23488,7 +22623,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen2.5-7B-Instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 4e-08, @@ -23498,7 +22632,6 @@ "supports_tool_choice": false }, "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -23510,7 +22643,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-14B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.2e-07, @@ -23522,7 +22654,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.8e-07, @@ -23533,7 +22664,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-08, @@ -23545,7 +22675,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, @@ -23556,7 +22685,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-30B-A3B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.2e-07, @@ -23568,7 +22696,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-32B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 8e-08, @@ -23580,7 +22707,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 4e-07, @@ -23591,7 +22717,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, @@ -23605,7 +22730,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-08, @@ -23617,7 +22741,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.4e-07, @@ -23628,7 +22751,6 @@ "supports_function_calling": true }, "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, @@ -23638,7 +22760,6 @@ "supports_tool_choice": false }, "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 8.5e-07, @@ -23649,7 +22770,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6.5e-07, @@ -23659,7 +22779,6 @@ "supports_tool_choice": false }, "deepinfra/allenai/olmOCR-7B-0725-FP8": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2.7e-07, @@ -23669,7 +22788,6 @@ "supports_tool_choice": false }, "deepinfra/anthropic/claude-3-7-sonnet-latest": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 3.3e-06, @@ -23681,7 +22799,6 @@ "supports_function_calling": true }, "deepinfra/anthropic/claude-4-opus": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 1.65e-05, @@ -23692,7 +22809,6 @@ "supports_function_calling": true }, "deepinfra/anthropic/claude-4-sonnet": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 3.3e-06, @@ -23703,7 +22819,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 7e-07, @@ -23714,7 +22829,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -23726,7 +22840,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-06, @@ -23737,7 +22850,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -23747,7 +22859,6 @@ "supports_tool_choice": false }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.7e-07, @@ -23758,7 +22869,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-06, @@ -23769,7 +22879,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-V3": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 3.2e-07, @@ -23781,7 +22890,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.4e-07, @@ -23795,7 +22903,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.5e-07, @@ -23809,7 +22916,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.7e-07, @@ -23821,7 +22927,6 @@ "supports_function_calling": true }, "deepinfra/google/gemini-2.5-flash": { - "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "input_cost_per_token": 3e-07, @@ -23837,7 +22942,6 @@ "supports_audio_input": true }, "deepinfra/google/gemini-2.5-pro": { - "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "input_cost_per_token": 1.25e-06, @@ -23852,7 +22956,6 @@ "supports_audio_input": true }, "deepinfra/google/gemma-3-12b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-08, @@ -23864,7 +22967,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-27b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 8e-08, @@ -23876,7 +22978,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-4b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-08, @@ -23888,7 +22989,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4.9e-08, @@ -23898,7 +22998,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, @@ -23909,7 +23008,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.3e-07, @@ -23920,7 +23018,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -23932,7 +23029,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 2e-07, @@ -23944,7 +23040,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "max_tokens": 327680, "max_input_tokens": 327680, "max_output_tokens": 327680, "input_cost_per_token": 1e-07, @@ -23956,7 +23051,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-Guard-3-8B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5.5e-08, @@ -23966,7 +23060,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Llama-Guard-4-12B": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.8e-07, @@ -23976,7 +23069,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, @@ -23987,7 +23079,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, @@ -23998,7 +23089,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, @@ -24010,7 +23100,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -24021,7 +23110,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, @@ -24033,7 +23121,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/microsoft/WizardLM-2-8x22B": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 4.8e-07, @@ -24043,7 +23130,6 @@ "supports_tool_choice": false }, "deepinfra/microsoft/phi-4": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 7e-08, @@ -24054,7 +23140,6 @@ "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.9e-08, @@ -24066,7 +23151,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-08, @@ -24077,7 +23161,6 @@ "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 7.5e-08, @@ -24088,7 +23171,6 @@ "supports_function_calling": true }, "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 4e-07, @@ -24099,7 +23181,6 @@ "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-07, @@ -24110,7 +23191,6 @@ "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct-0905": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-07, @@ -24122,7 +23202,6 @@ "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6e-07, @@ -24133,7 +23212,6 @@ "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -24157,7 +23235,6 @@ "supports_prompt_caching": true }, "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-08, @@ -24168,7 +23245,6 @@ "supports_function_calling": true }, "deepinfra/openai/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3.7e-08, @@ -24180,7 +23256,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/openai/gpt-oss-20b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -24192,7 +23267,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.5": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, @@ -24211,7 +23285,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -24234,7 +23307,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07, "supports_assistant_prefill": true, @@ -24249,7 +23321,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.19e-06, "supports_assistant_prefill": true, @@ -24266,7 +23337,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -24291,7 +23361,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.1e-06, "supports_assistant_prefill": true, @@ -24306,7 +23375,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 4e-07, "supports_assistant_prefill": true, @@ -24321,7 +23389,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html", @@ -24338,7 +23405,6 @@ "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, @@ -24358,7 +23424,6 @@ "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "completion", "output_cost_per_token": 5e-07 }, @@ -24367,7 +23432,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 98304, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, @@ -24381,7 +23445,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, @@ -24395,7 +23458,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 229376, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, @@ -24408,7 +23470,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" }, @@ -24420,7 +23481,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" }, @@ -24432,7 +23492,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240915 version with 4096 dimensions" }, @@ -24444,7 +23503,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-250515 version with 2048 dimensions" }, @@ -24456,7 +23514,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions" }, @@ -24569,7 +23626,6 @@ "mode": "search" }, "sail/moonshotai/Kimi-K3": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 2.5e-06, @@ -24591,7 +23647,6 @@ "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, @@ -24613,7 +23668,6 @@ "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, @@ -24635,7 +23689,6 @@ "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, @@ -24657,7 +23710,6 @@ "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, @@ -24679,7 +23731,6 @@ "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, @@ -24701,7 +23752,6 @@ "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, @@ -24724,7 +23774,6 @@ "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, @@ -24747,7 +23796,6 @@ "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, @@ -24770,7 +23818,6 @@ "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, @@ -24792,7 +23839,6 @@ "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, @@ -24808,7 +23854,6 @@ "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, @@ -25047,7 +24092,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -25056,7 +24100,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, @@ -25069,7 +24112,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true @@ -25078,7 +24120,6 @@ "input_cost_per_token": 0.0001, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true @@ -25089,7 +24130,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.12e-07, "supports_function_calling": true, @@ -25105,7 +24145,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.84e-07, "supports_function_calling": true, @@ -25121,7 +24160,6 @@ "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, @@ -25138,7 +24176,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -25161,7 +24198,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -25189,7 +24225,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -25205,7 +24240,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -25224,7 +24258,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -25244,7 +24277,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -25261,7 +24293,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -25292,7 +24323,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -25323,7 +24353,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -25363,7 +24392,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -25397,7 +24425,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -25410,7 +24437,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -25422,7 +24448,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "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", @@ -27688,14 +26713,12 @@ "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat" }, "featherless_ai/featherless-ai/Qwerky-QwQ-32B": { "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat" }, "fireworks-ai-4.1b-to-16b": { @@ -27743,7 +26766,6 @@ "input_cost_per_token": 1.6e-08, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -27753,7 +26775,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/pricing", @@ -27766,7 +26787,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 20480, - "max_tokens": 20480, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://fireworks.ai/pricing", @@ -27778,7 +26798,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 160000, - "max_tokens": 160000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://fireworks.ai/pricing", @@ -27790,7 +26809,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 20480, - "max_tokens": 20480, "mode": "chat", "output_cost_per_token": 2.19e-06, "source": "https://fireworks.ai/pricing", @@ -27802,7 +26820,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -27814,7 +26831,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", @@ -27826,7 +26842,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/pricing", @@ -27839,7 +26854,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/pricing", @@ -27852,7 +26866,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/models/fireworks/deepseek-v3p2", @@ -27867,7 +26880,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -27886,7 +26898,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.96e-06, "output_cost_per_token_priority": 4.95e-06, @@ -27906,7 +26917,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.96e-06, "output_cost_per_token_priority": 4.95e-06, @@ -27922,7 +26932,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -27935,7 +26944,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 96000, - "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 2.19e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p5", @@ -27949,7 +26957,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 96000, - "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://artificialanalysis.ai/models/glm-4-5-air", @@ -27964,7 +26971,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "source": "https://fireworks.ai/pricing", "supports_function_calling": true, @@ -27978,7 +26984,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p7", @@ -27993,7 +26998,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28012,7 +27016,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, @@ -28032,7 +27035,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, @@ -28049,7 +27051,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28064,7 +27065,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct", @@ -28077,7 +27077,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://app.fireworks.ai/models/fireworks/kimi-k2-instruct-0905", @@ -28090,7 +27089,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://fireworks.ai/pricing", @@ -28105,7 +27103,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -28122,7 +27119,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -28142,7 +27138,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -28158,7 +27153,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -28171,7 +27165,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", @@ -28184,7 +27177,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://fireworks.ai/pricing", @@ -28198,7 +27190,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", @@ -28211,7 +27202,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", @@ -28224,7 +27214,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -28237,7 +27226,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://fireworks.ai/pricing", @@ -28249,7 +27237,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://fireworks.ai/pricing", @@ -28262,7 +27249,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 196608, "max_output_tokens": 204800, - "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", @@ -28278,7 +27264,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.8e-06, @@ -28294,7 +27279,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/pricing", @@ -28307,7 +27291,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -28320,7 +27303,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -28333,7 +27315,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -28347,7 +27328,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28363,7 +27343,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p7", @@ -28378,7 +27357,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28394,7 +27372,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28413,7 +27390,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, @@ -28433,7 +27409,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, @@ -28450,7 +27425,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28466,7 +27440,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -28483,7 +27456,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -28501,7 +27473,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28520,7 +27491,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -28538,7 +27508,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28554,7 +27523,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 196608, "max_output_tokens": 204800, - "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", @@ -28570,7 +27538,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.8e-06, @@ -28587,7 +27554,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -28601,7 +27567,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -28610,7 +27575,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -28619,7 +27583,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -28628,7 +27591,6 @@ "input_cost_per_token": 1.6e-08, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -28637,7 +27599,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 3e-08, @@ -28665,7 +27626,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "input_cost_per_token": 1.26e-06, "output_cost_per_token": 3.96e-06, "cache_read_input_token_cost": 2.34e-07, @@ -28693,7 +27653,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 4e-07, "supports_prompt_caching": false, @@ -28716,7 +27675,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, @@ -28743,7 +27701,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "input_cost_per_token": 5e-07, "output_cost_per_token": 1.5e-06, "cache_read_input_token_cost": 2.5e-07, @@ -28767,7 +27724,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 196608, "max_output_tokens": 196608, - "max_tokens": 196608, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 6e-08, @@ -28791,7 +27747,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 202752, "max_output_tokens": 202752, - "max_tokens": 202752, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, @@ -28818,7 +27773,6 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 9e-07, @@ -28831,7 +27785,6 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, @@ -28844,7 +27797,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_batches": 3e-06, @@ -28858,7 +27810,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "supports_system_messages": true, @@ -28870,7 +27821,6 @@ "litellm_provider": "openai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "supports_system_messages": true, @@ -28882,7 +27832,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "supports_system_messages": true, @@ -28894,7 +27843,6 @@ "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", @@ -28911,7 +27859,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -28932,7 +27879,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -28952,7 +27898,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_batches": 6e-07, @@ -28974,7 +27919,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, @@ -28995,7 +27939,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.2e-06, "output_cost_per_token_batches": 1.6e-06, @@ -29016,7 +27959,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, "output_cost_per_token_batches": 4e-07, @@ -29037,7 +27979,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 1.6e-05, "output_cost_per_token_batches": 8e-06, @@ -29060,7 +28001,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -29117,7 +28057,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, @@ -29175,7 +28114,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -29229,7 +28167,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -29281,7 +28218,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, @@ -29327,7 +28263,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, @@ -29376,7 +28311,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, @@ -29416,7 +28350,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -29475,7 +28408,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -29535,7 +28467,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -29591,7 +28522,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -29629,7 +28559,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, @@ -29684,7 +28613,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, @@ -29731,7 +28659,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -29778,7 +28705,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -29824,7 +28750,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -29868,7 +28793,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -29920,7 +28844,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -29982,7 +28905,6 @@ "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, @@ -30035,7 +28957,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -30088,7 +29009,6 @@ "litellm_provider": "vertex_ai", "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, @@ -30149,7 +29069,6 @@ "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, @@ -30196,7 +29115,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -30259,7 +29177,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -30320,7 +29237,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -30384,7 +29300,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -30440,7 +29355,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, @@ -30488,7 +29402,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -30531,7 +29444,6 @@ "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, @@ -30584,7 +29496,6 @@ "litellm_provider": "vertex_ai", "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, @@ -30641,7 +29552,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, @@ -30674,7 +29584,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_reasoning_token": 2.5e-06, @@ -30712,7 +29621,6 @@ "litellm_provider": "gemini", "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, @@ -30759,7 +29667,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -30783,7 +29690,6 @@ "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30800,7 +29706,6 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30818,7 +29723,6 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30837,7 +29741,6 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30856,7 +29759,6 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30870,7 +29772,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30882,7 +29783,6 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "gemini", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30901,7 +29801,6 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "gemini", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30922,7 +29821,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -30968,7 +29866,6 @@ "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 6e-05, @@ -31020,7 +29917,6 @@ "litellm_provider": "gemini", "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, @@ -31080,7 +29976,6 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "gemini", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -31097,7 +29992,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "rpm": 1000, @@ -31134,7 +30028,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "rpm": 1000, @@ -31180,7 +30073,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -31243,7 +30135,6 @@ "supports_reasoning": false, "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, @@ -31295,7 +30186,6 @@ "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, @@ -31344,7 +30234,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -31387,7 +30276,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 6e-05, @@ -31429,7 +30317,6 @@ "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, @@ -31468,7 +30355,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, @@ -31513,7 +30399,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, @@ -31570,7 +30455,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -31629,7 +30513,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -31688,7 +30571,6 @@ "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, @@ -31718,7 +30600,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -31772,7 +30653,6 @@ "litellm_provider": "gemini", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -31815,7 +30695,6 @@ "litellm_provider": "gemini", "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, @@ -31877,7 +30756,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -31940,7 +30818,6 @@ "litellm_provider": "gemini", "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, @@ -32002,7 +30879,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -32067,7 +30943,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -32129,7 +31004,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -32192,7 +31066,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -32250,7 +31123,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -32288,7 +31160,6 @@ "litellm_provider": "gemini", "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, @@ -32352,7 +31223,6 @@ "litellm_provider": "gemini", "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, @@ -32421,7 +31291,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, @@ -32466,7 +31335,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -32501,7 +31369,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -32564,7 +31431,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -32625,7 +31491,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -32689,7 +31554,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -32745,7 +31609,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, @@ -32792,7 +31655,6 @@ "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, @@ -32827,7 +31689,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "metadata": { "notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true @@ -32850,7 +31711,6 @@ "litellm_provider": "gemini", "max_input_tokens": 2097152, "max_output_tokens": 8192, - "max_tokens": 8192, "metadata": { "notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true @@ -32871,7 +31731,7 @@ "input_cost_per_token": 3.5e-07, "litellm_provider": "gemini", "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", @@ -32885,7 +31745,7 @@ "input_cost_per_token": 3.5e-07, "litellm_provider": "gemini", "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", @@ -32909,7 +31769,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, @@ -32929,7 +31788,6 @@ "litellm_provider": "gemini", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, @@ -32945,7 +31803,6 @@ "litellm_provider": "gemini", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, @@ -32981,7 +31838,6 @@ "litellm_provider": "gemini", "max_input_tokens": 32767, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, @@ -33000,7 +31856,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_image": 0.04, "output_cost_per_token": 0, @@ -33025,7 +31880,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -33049,7 +31903,6 @@ "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -33066,7 +31919,6 @@ "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, @@ -33082,7 +31934,6 @@ "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08, @@ -33097,7 +31948,6 @@ "gemini/veo-3.1-fast-generate-001": { "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -33113,7 +31963,6 @@ "gemini/veo-3.1-generate-001": { "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, @@ -33132,7 +31981,6 @@ "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", @@ -33155,7 +32003,6 @@ "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", @@ -33178,7 +32025,6 @@ "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": [ @@ -33199,7 +32045,6 @@ "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, @@ -33224,7 +32069,6 @@ "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", @@ -33247,7 +32091,6 @@ "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", @@ -33270,7 +32113,6 @@ "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", @@ -33292,7 +32134,6 @@ "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", @@ -33315,7 +32156,6 @@ "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", @@ -33337,7 +32177,6 @@ "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", @@ -33360,7 +32199,6 @@ "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", @@ -33379,7 +32217,6 @@ "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", @@ -33396,7 +32233,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -33404,7 +32240,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -33412,7 +32247,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -33420,7 +32254,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -33428,7 +32261,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -33438,7 +32270,6 @@ "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, @@ -33451,7 +32282,6 @@ "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, @@ -33467,7 +32297,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -33477,7 +32306,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -33487,7 +32315,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -33496,7 +32323,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -33506,7 +32332,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -33515,7 +32340,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -33527,7 +32351,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://github.blog/changelog/2026-10-19-github-copilot-models-deprecated-on-october-19-2026", @@ -33542,7 +32365,6 @@ "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": [ @@ -33563,7 +32385,6 @@ "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, @@ -33585,7 +32406,6 @@ "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", @@ -33607,7 +32427,6 @@ "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, @@ -33631,7 +32450,6 @@ "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, @@ -33655,7 +32473,6 @@ "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, @@ -33680,7 +32497,6 @@ "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, @@ -33704,7 +32520,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 922000, "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, @@ -33728,7 +32543,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 922000, "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, @@ -33752,7 +32566,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 922000, "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, @@ -33776,7 +32589,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 922000, "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, @@ -33796,7 +32608,6 @@ "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", @@ -33814,7 +32625,6 @@ "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", @@ -33829,19 +32639,16 @@ "github_copilot/text-embedding-3-small": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding" }, "github_copilot/text-embedding-3-small-inference": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding" }, "github_copilot/text-embedding-ada-002": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding" }, "chatgpt/gpt-6-sol": { @@ -33853,7 +32660,6 @@ ], "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, @@ -33874,7 +32680,6 @@ ], "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, @@ -33895,7 +32700,6 @@ ], "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, @@ -33916,7 +32720,6 @@ ], "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, @@ -33933,7 +32736,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.5", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -33953,7 +32755,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.6-luna", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -33973,7 +32774,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.6-sol", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -33993,7 +32793,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.6-terra", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -34012,7 +32811,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -34032,7 +32830,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -34050,7 +32847,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -34068,7 +32864,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -34082,7 +32877,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -34097,7 +32891,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -34113,7 +32906,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -34128,7 +32920,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -34148,7 +32939,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -34163,7 +32953,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -34179,7 +32968,6 @@ "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, @@ -34190,7 +32978,6 @@ "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, @@ -34202,7 +32989,6 @@ "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, @@ -34213,7 +32999,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -34222,7 +33007,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -34231,7 +33015,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 4096, - "max_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560 @@ -34240,7 +33023,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 4096, - "max_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2048 @@ -34250,7 +33032,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_function_calling": true, @@ -34262,7 +33043,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -34273,7 +33053,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -34284,7 +33063,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -34295,7 +33073,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.4e-05, "supports_function_calling": true @@ -34305,7 +33082,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true @@ -34315,7 +33091,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true @@ -34325,7 +33100,6 @@ "litellm_provider": "gmi", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -34336,7 +33110,6 @@ "litellm_provider": "gmi", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -34347,7 +33120,6 @@ "litellm_provider": "gmi", "max_input_tokens": 163840, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true @@ -34357,7 +33129,6 @@ "litellm_provider": "gmi", "max_input_tokens": 163840, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 8.8e-07, "supports_function_calling": true @@ -34367,7 +33138,6 @@ "litellm_provider": "gmi", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, @@ -34379,7 +33149,6 @@ "litellm_provider": "gmi", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, @@ -34388,7 +33157,6 @@ "litellm_provider": "gmi", "max_input_tokens": 196608, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, @@ -34420,7 +33188,6 @@ "litellm_provider": "baseten", "max_input_tokens": 200000, "max_output_tokens": 200000, - "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://inference.baseten.co/v1/models", @@ -34465,7 +33232,6 @@ "litellm_provider": "baseten", "max_input_tokens": 128072, "max_output_tokens": 128072, - "max_tokens": 128072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inference.baseten.co/v1/models", @@ -34495,7 +33261,6 @@ "litellm_provider": "gmi", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-06, "supports_vision": true @@ -34505,7 +33270,6 @@ "litellm_provider": "gmi", "max_input_tokens": 202752, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2e-06 }, @@ -34518,7 +33282,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.9e-07, "output_cost_per_token_batches": 1.5e-07, @@ -34540,7 +33303,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 3.8e-07, "output_cost_per_token_batches": 1.9e-07, @@ -34562,7 +33324,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-08, "output_cost_per_token_batches": 4e-08, @@ -34594,7 +33355,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -34634,7 +33394,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -34668,7 +33427,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -34700,7 +33458,6 @@ "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, @@ -34721,7 +33478,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://developers.openai.com/api/docs/pricing", @@ -34737,7 +33493,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, @@ -34755,7 +33510,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 2e-06, @@ -34772,7 +33526,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-06, "supports_prompt_caching": true, @@ -34785,7 +33538,6 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06, "source": "https://developers.openai.com/api/docs/pricing" @@ -34795,7 +33547,6 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, "max_output_tokens": 4097, - "max_tokens": 4097, "mode": "completion", "output_cost_per_token": 2e-06 }, @@ -34805,7 +33556,6 @@ "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, "supports_function_calling": true, @@ -34820,7 +33570,6 @@ "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_batches": 3e-05, @@ -34836,7 +33585,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, @@ -34851,7 +33599,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, @@ -34869,7 +33616,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_batches": 1.5e-05, @@ -34891,7 +33637,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, @@ -34935,7 +33680,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_priority": 1.4e-05, @@ -34978,7 +33722,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, @@ -35022,7 +33765,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_priority": 2.8e-06, @@ -35066,7 +33808,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -35104,7 +33845,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_priority": 8e-07, @@ -35141,7 +33881,6 @@ "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, @@ -35164,7 +33903,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -35188,7 +33926,6 @@ "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_priority": 1.7e-05, @@ -35213,7 +33950,6 @@ "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_priority": 1.7e-05, @@ -35235,7 +33971,6 @@ "litellm_provider": "openai", "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, @@ -35253,7 +33988,6 @@ "litellm_provider": "openai", "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, @@ -35271,7 +34005,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -35308,7 +34041,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -35343,7 +34075,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -35381,7 +34112,6 @@ "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, @@ -35419,7 +34149,6 @@ "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, @@ -35456,7 +34185,6 @@ "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, @@ -35497,7 +34225,6 @@ "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, @@ -35527,7 +34254,6 @@ "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_priority": 1e-06, @@ -35554,7 +34280,6 @@ "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": 6e-07, @@ -35574,7 +34299,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -35592,7 +34316,6 @@ "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, @@ -35619,7 +34342,6 @@ "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, @@ -35700,7 +34422,6 @@ "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, @@ -35727,7 +34448,6 @@ "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, @@ -36281,7 +35001,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -36327,7 +35046,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5-codex", @@ -36362,7 +35080,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, @@ -36412,7 +35129,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini", @@ -36443,7 +35159,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-max", @@ -36475,7 +35190,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex", @@ -36507,7 +35221,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-chat-latest", @@ -36542,7 +35255,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, @@ -36594,7 +35306,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, @@ -36645,7 +35356,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-codex", @@ -36677,7 +35387,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-chat-latest", @@ -36712,7 +35421,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, @@ -36762,7 +35470,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, @@ -36804,7 +35511,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, @@ -36884,7 +35590,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "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, @@ -36971,7 +35676,6 @@ "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, @@ -37062,7 +35766,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_decisions": 0.0, @@ -37148,7 +35851,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -37230,7 +35932,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -37314,7 +36015,6 @@ "litellm_provider": "openai", "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, @@ -37397,7 +36097,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, @@ -37455,7 +36154,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-05, "output_cost_per_token_above_272k_tokens": 0.0001125, @@ -37494,7 +36192,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-05, "output_cost_per_token_above_272k_tokens": 0.0001125, @@ -37533,7 +36230,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 7.5e-05, "output_cost_per_token_above_272k_tokens": 0.0001125, @@ -37571,7 +36267,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -37610,7 +36305,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -37644,7 +36338,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "reasoning_effort_levels": [ @@ -37690,7 +36383,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "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, @@ -37753,7 +36445,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "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, @@ -37809,7 +36500,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -37861,7 +36551,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -37920,7 +36609,6 @@ "litellm_provider": "openai", "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, @@ -37978,7 +36666,6 @@ "litellm_provider": "openai", "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, @@ -38029,7 +36716,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -38082,7 +36768,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -38138,7 +36823,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_flex": 2.25e-06, @@ -38193,7 +36877,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_flex": 2.25e-06, @@ -38246,7 +36929,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, @@ -38298,7 +36980,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, @@ -38345,7 +37026,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 272000, - "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, @@ -38388,7 +37068,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 272000, - "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, @@ -38437,7 +37116,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -38483,7 +37161,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -38519,7 +37196,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5-chat-latest", @@ -38552,7 +37228,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, @@ -38596,7 +37271,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest", @@ -38633,7 +37307,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, @@ -38685,7 +37358,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, @@ -38735,7 +37407,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -38785,7 +37456,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -38871,7 +37541,6 @@ "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -38906,7 +37575,6 @@ "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -38941,7 +37609,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, @@ -38976,7 +37643,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, @@ -39013,7 +37679,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -39051,7 +37716,6 @@ "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -39087,7 +37751,6 @@ "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -39113,7 +37776,6 @@ }, "gradient_ai/alibaba-qwen3-32b": { "litellm_provider": "gradient_ai", - "max_tokens": 40960, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" @@ -39128,7 +37790,6 @@ "gradient_ai/anthropic-claude-3-opus": { "input_cost_per_token": 1.5e-05, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 7.5e-05, "supported_endpoints": [ @@ -39144,7 +37805,6 @@ "gradient_ai/anthropic-claude-3.5-haiku": { "input_cost_per_token": 8e-07, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 4e-06, "supported_endpoints": [ @@ -39160,7 +37820,6 @@ "gradient_ai/anthropic-claude-3.5-sonnet": { "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.5e-05, "supported_endpoints": [ @@ -39176,7 +37835,6 @@ "gradient_ai/anthropic-claude-3.7-sonnet": { "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.5e-05, "supported_endpoints": [ @@ -39192,7 +37850,6 @@ "gradient_ai/deepseek-r1-distill-llama-70b": { "input_cost_per_token": 9.9e-07, "litellm_provider": "gradient_ai", - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 9.9e-07, "supported_endpoints": [ @@ -39208,7 +37865,6 @@ "gradient_ai/llama3-8b-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "gradient_ai", - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 2e-07, "supported_endpoints": [ @@ -39224,7 +37880,6 @@ "gradient_ai/llama3.3-70b-instruct": { "input_cost_per_token": 6.5e-07, "litellm_provider": "gradient_ai", - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 6.5e-07, "supported_endpoints": [ @@ -39240,7 +37895,6 @@ "gradient_ai/mistral-nemo-instruct-2407": { "input_cost_per_token": 3e-07, "litellm_provider": "gradient_ai", - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 3e-07, "supported_endpoints": [ @@ -39255,7 +37909,6 @@ }, "gradient_ai/openai-gpt-4o": { "litellm_provider": "gradient_ai", - "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" @@ -39269,7 +37922,6 @@ }, "gradient_ai/openai-gpt-4o-mini": { "litellm_provider": "gradient_ai", - "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" @@ -39284,7 +37936,6 @@ "gradient_ai/openai-o3": { "input_cost_per_token": 2e-06, "litellm_provider": "gradient_ai", - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "supported_endpoints": [ @@ -39300,7 +37951,6 @@ "gradient_ai/openai-o3-mini": { "input_cost_per_token": 1.1e-06, "litellm_provider": "gradient_ai", - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supported_endpoints": [ @@ -39316,7 +37966,6 @@ "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", @@ -39328,7 +37977,6 @@ "lemonade/gpt-oss-20b-mxfp4-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", @@ -39340,7 +37988,6 @@ "lemonade/gpt-oss-120b-mxfp-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", @@ -39352,7 +37999,6 @@ "lemonade/Gemma-3-4b-it-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", @@ -39364,7 +38010,6 @@ "lemonade/Qwen3-4B-Instruct-2507-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", @@ -39378,7 +38023,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, "supports_function_calling": true, @@ -39390,7 +38034,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, "supports_function_calling": true, @@ -39404,7 +38047,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 1000000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.25e-05, "supports_function_calling": true, @@ -39418,7 +38060,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, "supports_function_calling": true, @@ -39432,7 +38073,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "groq", "max_input_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://console.groq.com/docs/model/llama-guard-3-8b" @@ -39442,7 +38083,6 @@ "litellm_provider": "groq", "max_input_tokens": 512, "max_output_tokens": 512, - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://console.groq.com/docs/models" @@ -39452,7 +38092,6 @@ "litellm_provider": "groq", "max_input_tokens": 512, "max_output_tokens": 512, - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 4e-08, "source": "https://console.groq.com/docs/model/meta-llama/llama-prompt-guard-2-86m" @@ -39463,7 +38102,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-07, "search_context_cost_per_query": { @@ -39484,7 +38122,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "search_context_cost_per_query": { @@ -39505,7 +38142,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "search_context_cost_per_query": { @@ -39524,7 +38160,6 @@ "litellm_provider": "groq", "max_input_tokens": 4000, "max_output_tokens": 50000, - "max_tokens": 50000, "mode": "audio_speech", "source": "https://console.groq.com/docs/model/canopylabs/orpheus-v1-english" }, @@ -39533,7 +38168,6 @@ "litellm_provider": "groq", "max_input_tokens": 4000, "max_output_tokens": 50000, - "max_tokens": 50000, "mode": "audio_speech", "source": "https://console.groq.com/docs/models" }, @@ -39551,7 +38185,6 @@ }, "heroku/claude-3-5-haiku": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -39561,7 +38194,6 @@ }, "heroku/claude-3-5-sonnet-latest": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -39571,7 +38203,6 @@ }, "heroku/claude-3-7-sonnet": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -39581,7 +38212,6 @@ }, "heroku/claude-4-sonnet": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -39627,7 +38257,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39640,7 +38269,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -39653,7 +38281,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39666,7 +38293,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39679,7 +38305,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "supports_function_calling": true, @@ -39692,7 +38317,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true, @@ -39705,7 +38329,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_function_calling": true, @@ -39718,7 +38341,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -39731,7 +38353,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true, @@ -39744,7 +38365,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39757,7 +38377,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39770,7 +38389,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39783,7 +38401,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39796,7 +38413,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39809,7 +38425,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39822,7 +38437,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "supports_function_calling": true, @@ -39835,7 +38449,6 @@ "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 3e-06 }, @@ -39844,7 +38457,6 @@ "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 1e-05 }, @@ -39853,7 +38465,6 @@ "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 1.5e-05 }, @@ -39862,7 +38473,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -39872,7 +38482,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -39882,7 +38491,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -39892,7 +38500,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -39902,7 +38509,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -39912,7 +38518,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -39922,7 +38527,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -39932,7 +38536,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -39942,7 +38545,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -39952,7 +38554,6 @@ "litellm_provider": "jina_ai", "max_input_tokens": 1024, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://api.jina.ai/v1/models" @@ -39972,7 +38573,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -40009,7 +38609,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -40037,7 +38636,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 7e-06, "supports_function_calling": false, @@ -40050,7 +38648,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -40063,7 +38660,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -40077,7 +38673,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -40090,7 +38685,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "supports_function_calling": false, @@ -40103,7 +38697,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -40116,7 +38709,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, @@ -40130,7 +38722,6 @@ "litellm_provider": "inception", "max_input_tokens": 128000, "max_output_tokens": 50000, - "max_tokens": 50000, "mode": "chat", "output_cost_per_token": 7.5e-07, "supports_function_calling": true, @@ -40145,7 +38736,6 @@ "litellm_provider": "inception", "max_input_tokens": 260000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-07, "source": "https://docs.inceptionlabs.ai/get-started/models", @@ -40160,7 +38750,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40181,7 +38771,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40202,7 +38792,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40223,7 +38813,7 @@ "input_cost_per_token": 1.72e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5.15e-06, "source": "https://inferenceapis.com/pricing", @@ -40244,7 +38834,7 @@ "input_cost_per_token": 1.72e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5.15e-06, "source": "https://inferenceapis.com/pricing", @@ -40265,7 +38855,7 @@ "input_cost_per_token": 4e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://inferenceapis.com/pricing", @@ -40286,7 +38876,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40307,7 +38897,7 @@ "input_cost_per_token": 4e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://inferenceapis.com/pricing", @@ -40328,7 +38918,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40349,7 +38939,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40370,7 +38960,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40391,7 +38981,7 @@ "input_cost_per_token": 1.72e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5.15e-06, "source": "https://inferenceapis.com/pricing", @@ -40412,7 +39002,7 @@ "input_cost_per_token": 4e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://inferenceapis.com/pricing", @@ -40433,7 +39023,7 @@ "input_cost_per_token": 1.82e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048575, - "max_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", "output_cost_per_token": 5.72e-06, "source": "https://inferenceapis.com/pricing", @@ -40454,7 +39044,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048575, - "max_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://inferenceapis.com/pricing", @@ -40474,7 +39064,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://inferenceapis.com/pricing", @@ -40493,7 +39083,7 @@ "input_cost_per_token": 4e-08, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.9e-07, "source": "https://inferenceapis.com/pricing", @@ -40513,7 +39103,7 @@ "input_cost_per_token": 8.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.42e-06, "source": "https://inferenceapis.com/pricing", @@ -40533,7 +39123,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40552,7 +39142,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40571,7 +39161,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40590,7 +39180,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40609,7 +39199,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40628,7 +39218,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40648,7 +39238,7 @@ "input_cost_per_token": 3.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 524288, - "max_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://inferenceapis.com/pricing", @@ -40669,7 +39259,7 @@ "input_cost_per_token": 3.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 524288, - "max_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://inferenceapis.com/pricing", @@ -40690,7 +39280,7 @@ "input_cost_per_token": 8.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.42e-06, "source": "https://inferenceapis.com/pricing", @@ -40710,7 +39300,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://inferenceapis.com/pricing", @@ -40729,7 +39319,7 @@ "input_cost_per_token": 4e-08, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.9e-07, "source": "https://inferenceapis.com/pricing", @@ -40748,7 +39338,7 @@ "input_cost_per_token": 2.6e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://inferenceapis.com/pricing", @@ -40768,7 +39358,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40788,7 +39378,7 @@ "input_cost_per_token": 2.6e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://inferenceapis.com/pricing", @@ -40807,7 +39397,7 @@ "input_cost_per_token": 2.6e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://inferenceapis.com/pricing", @@ -40827,7 +39417,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40848,7 +39438,7 @@ "input_cost_per_token": 1.82e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048575, - "max_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", "output_cost_per_token": 5.72e-06, "source": "https://inferenceapis.com/pricing", @@ -40869,7 +39459,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048575, - "max_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://inferenceapis.com/pricing", @@ -40891,7 +39481,6 @@ "litellm_provider": "text-completion-inception", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 7.5e-07 }, @@ -40900,7 +39489,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -40914,7 +39502,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -40928,7 +39515,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -40942,7 +39528,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -40955,7 +39540,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -40968,7 +39552,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -40981,7 +39564,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, @@ -40994,7 +39576,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -41007,7 +39588,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, @@ -41020,7 +39600,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -41033,7 +39612,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 16384, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -41046,7 +39624,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -41059,7 +39636,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -41072,7 +39648,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, @@ -41085,7 +39660,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -41098,7 +39672,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-08, "supports_function_calling": true, @@ -41112,7 +39685,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-08, "supports_function_calling": true, @@ -41125,7 +39697,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -41138,7 +39709,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -41151,7 +39721,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -41196,14 +39765,12 @@ "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.036 }, "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.072 }, @@ -41299,7 +39866,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "chat", "output_cost_per_character": 1.5e-05, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", @@ -41310,7 +39876,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_character": 1e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", @@ -41321,7 +39886,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://aws.amazon.com/bedrock/pricing/" @@ -41331,7 +39895,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.56e-06, "source": "https://aws.amazon.com/bedrock/pricing/" @@ -41342,7 +39905,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -41356,7 +39918,6 @@ "litellm_provider": "bedrock", "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, @@ -41371,7 +39932,6 @@ "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, @@ -41385,7 +39945,6 @@ "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", @@ -41399,7 +39958,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -41412,7 +39970,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -41425,7 +39982,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -41440,7 +39996,6 @@ "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, @@ -41454,7 +40009,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -41465,7 +40019,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -41477,7 +40030,6 @@ "litellm_provider": "bedrock_converse", "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, @@ -41500,7 +40052,6 @@ "litellm_provider": "bedrock_converse", "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, @@ -41522,7 +40073,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.25e-06, "search_context_cost_per_query": { @@ -41563,7 +40113,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.25e-06, "search_context_cost_per_query": { @@ -41604,7 +40153,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "search_context_cost_per_query": { @@ -41645,7 +40193,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.25e-06, "search_context_cost_per_query": { @@ -41686,7 +40233,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "search_context_cost_per_query": { @@ -41743,7 +40289,6 @@ "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": { @@ -41784,7 +40329,6 @@ "litellm_provider": "meta_llama", "max_input_tokens": 128000, "max_output_tokens": 4028, - "max_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ @@ -41800,7 +40344,6 @@ "litellm_provider": "meta_llama", "max_input_tokens": 128000, "max_output_tokens": 4028, - "max_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ @@ -41816,7 +40359,6 @@ "litellm_provider": "meta_llama", "max_input_tokens": 1000000, "max_output_tokens": 4028, - "max_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ @@ -41833,7 +40375,6 @@ "litellm_provider": "meta_llama", "max_input_tokens": 10000000, "max_output_tokens": 4028, - "max_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ @@ -41855,7 +40396,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_batches": 6e-07, @@ -41878,7 +40418,6 @@ "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, @@ -41902,7 +40441,6 @@ "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, @@ -42100,7 +40638,6 @@ "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, @@ -42122,7 +40659,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 40000, - "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, @@ -42144,7 +40680,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_batches": 1e-07, @@ -42166,7 +40701,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-07, "output_cost_per_token_batches": 5e-08, @@ -42188,7 +40722,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-07, "output_cost_per_token_batches": 7e-08, @@ -42208,7 +40741,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -42219,7 +40751,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", @@ -42230,7 +40761,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -42245,7 +40775,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, @@ -42265,7 +40794,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, @@ -42278,7 +40806,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -42293,7 +40820,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-08, "output_cost_per_token_batches": 2e-08, @@ -42313,7 +40839,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-07, "output_cost_per_token_batches": 1.5e-07, @@ -42330,7 +40855,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", @@ -42345,7 +40869,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", @@ -42360,7 +40883,6 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://mistral.ai/technology/", @@ -42373,7 +40895,6 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", @@ -42388,7 +40909,6 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://mistral.ai/news/devstral-2-vibe-cli", @@ -42403,7 +40923,6 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://mistral.ai/news/devstral-2-vibe-cli", @@ -42417,7 +40936,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", @@ -42433,7 +40951,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", @@ -42449,7 +40966,6 @@ "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", @@ -42465,7 +40981,6 @@ "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", @@ -42480,7 +40995,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "source": "https://docs.mistral.ai/models/mistral-embed-23-12" }, @@ -42490,7 +41004,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -42671,7 +41184,6 @@ "litellm_provider": "mistral", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://docs.mistral.ai/models/voxtral-small-25-07", @@ -42686,7 +41198,6 @@ "litellm_provider": "mistral", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://docs.mistral.ai/models/voxtral-small-25-07", @@ -42702,7 +41213,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -42728,7 +41238,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -42750,7 +41259,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "reasoning_effort_levels": [ @@ -42773,7 +41281,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -42795,7 +41302,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -42817,7 +41323,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -42896,7 +41401,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", @@ -42913,7 +41417,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", @@ -42928,7 +41431,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding" }, "mistral/codestral-embed": { @@ -42936,7 +41438,6 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding" }, "mistral/codestral-embed-2505": { @@ -42944,7 +41445,6 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding" }, "mistral/mistral-large-4": { @@ -42952,7 +41452,7 @@ "input_cost_per_token": 6.8e-07, "litellm_provider": "mistral", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.09e-06, "reasoning_effort_levels": [ @@ -42973,7 +41473,7 @@ "input_cost_per_token": 6.8e-07, "litellm_provider": "mistral", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.09e-06, "reasoning_effort_levels": [ @@ -42995,7 +41495,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", @@ -43011,7 +41510,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", @@ -43027,7 +41525,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", @@ -43043,7 +41540,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -43064,7 +41560,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -43085,7 +41580,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -43106,7 +41600,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -43127,7 +41620,6 @@ "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-07, "supports_assistant_prefill": true, @@ -43141,7 +41633,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ @@ -43162,7 +41653,6 @@ "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://mistral.ai/pricing", @@ -43178,7 +41668,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://mistral.ai/pricing", @@ -43194,7 +41683,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://mistral.ai/pricing", @@ -43210,7 +41698,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://mistral.ai/pricing", @@ -43226,7 +41713,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://mistral.ai/pricing", @@ -43242,7 +41728,6 @@ "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_assistant_prefill": true, @@ -43255,7 +41740,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://mistral.ai/technology/", @@ -43269,7 +41753,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_assistant_prefill": true, @@ -43286,7 +41769,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, @@ -43308,7 +41790,6 @@ "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, @@ -43328,7 +41809,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://platform.kimi.ai/docs/pricing/chat-k27-code", @@ -43346,7 +41826,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", @@ -43363,7 +41842,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://platform.kimi.ai/docs/pricing/chat-k26", @@ -43380,7 +41858,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ @@ -43401,7 +41878,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43414,7 +41890,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43428,7 +41903,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43441,7 +41915,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43455,7 +41928,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43468,7 +41940,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43482,7 +41953,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43495,7 +41965,6 @@ "litellm_provider": "morph", "max_input_tokens": 16000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": false, @@ -43509,7 +41978,6 @@ "litellm_provider": "morph", "max_input_tokens": 16000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.9e-06, "supports_function_calling": false, @@ -43527,7 +41995,6 @@ "input_cost_per_video_per_second_above_8s_interval": 0.001, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -43551,7 +42018,6 @@ "input_cost_per_video_per_second_above_8s_interval": 0.001, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -43711,7 +42177,6 @@ ] }, "nebius/deepseek-ai/DeepSeek-R1": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 8e-07, @@ -43723,7 +42188,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 164000, "max_input_tokens": 164000, "max_output_tokens": 164000, "input_cost_per_token": 8e-07, @@ -43735,7 +42199,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2.5e-07, @@ -43746,7 +42209,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V3": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 5e-07, @@ -43757,7 +42219,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 5e-07, @@ -43768,7 +42229,6 @@ "source": "https://nebius.com/prices" }, "nebius/google/gemma-3-27b-it": { - "max_tokens": 110000, "max_input_tokens": 110000, "max_output_tokens": 110000, "input_cost_per_token": 1e-07, @@ -43780,7 +42240,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/google%2Fgemma-3-27b-it" }, "nebius/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, @@ -43791,7 +42250,6 @@ "source": "https://nebius.com/prices" }, "nebius/meta-llama/Llama-Guard-3-8B": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-08, @@ -43801,7 +42259,6 @@ "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-08, @@ -43812,7 +42269,6 @@ "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.3e-07, @@ -43823,7 +42279,6 @@ "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-06, @@ -43834,7 +42289,6 @@ "source": "https://nebius.com/prices" }, "nebius/mistralai/Mistral-Nemo-Instruct-2407": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 4e-08, @@ -43845,7 +42299,6 @@ "source": "https://nebius.com/prices" }, "nebius/NousResearch/Hermes-3-Llama-3.1-405B": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-06, @@ -43856,7 +42309,6 @@ "source": "https://nebius.com/prices" }, "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 6e-07, @@ -43867,7 +42319,6 @@ "source": "https://nebius.com/prices" }, "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -43878,7 +42329,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-235B-A22B": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-07, @@ -43889,7 +42339,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-32B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, @@ -43900,7 +42349,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-32B" }, "nebius/Qwen/Qwen3-30B-A3B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -43911,7 +42359,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-14B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 8e-08, @@ -43922,7 +42369,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-4B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 8e-08, @@ -43933,7 +42379,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/QwQ-32B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.5e-07, @@ -43945,7 +42390,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-72B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.3e-07, @@ -43956,7 +42400,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-32B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 6e-08, @@ -43967,7 +42410,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-Coder-7B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-08, @@ -43978,7 +42420,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-VL-72B-Instruct": { - "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 2.5e-07, @@ -43990,7 +42431,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/image2text/Qwen%2FQwen2.5-VL-72B-Instruct" }, "nebius/Qwen/Qwen2-VL-72B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, @@ -44002,7 +42442,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2-VL-7B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, @@ -44013,7 +42452,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V4-Flash": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.4e-07, @@ -44025,7 +42463,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash" }, "nebius/deepseek-ai/DeepSeek-V4-Flash-0731": { - "max_tokens": 1024000, "max_input_tokens": 1024000, "max_output_tokens": 1024000, "input_cost_per_token": 1.4e-07, @@ -44037,7 +42474,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash-0731" }, "nebius/deepseek-ai/DeepSeek-V4-Pro": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.75e-06, @@ -44063,7 +42499,6 @@ "litellm_provider": "nebius", "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", @@ -44072,7 +42507,6 @@ "supports_vision": true }, "nebius/MiniMaxAI/MiniMax-M2.5": { - "max_tokens": 196608, "max_input_tokens": 196608, "max_output_tokens": 196608, "input_cost_per_token": 3e-07, @@ -44084,7 +42518,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M2.5" }, "nebius/MiniMaxAI/MiniMax-M3": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 3e-07, @@ -44097,7 +42530,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M3" }, "nebius/moonshotai/Kimi-K2.6": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9.5e-07, @@ -44110,7 +42542,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K2.6" }, "nebius/moonshotai/Kimi-K2.7-Code": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9.5e-07, @@ -44123,7 +42554,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/moonshotai%2FKimi-K2.7-Code" }, "nebius/moonshotai/Kimi-K3": { - "max_tokens": 1024000, "max_input_tokens": 1024000, "max_output_tokens": 1024000, "input_cost_per_token": 3e-06, @@ -44136,7 +42566,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K3" }, "nebius/NousResearch/Hermes-4-405B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-06, @@ -44148,7 +42577,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-405B" }, "nebius/NousResearch/Hermes-4-70B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, @@ -44160,7 +42588,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-70B" }, "nebius/nvidia/Cosmos3-Super-Reasoner": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-07, @@ -44173,7 +42600,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/image2text/nvidia%2FCosmos3-Super-Reasoner" }, "nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6e-07, @@ -44184,7 +42610,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FLlama-3_1-Nemotron-Ultra-253B-v1" }, "nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 6e-08, @@ -44196,7 +42621,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNVIDIA-Nemotron-3-Nano-30B-A3B" }, "nebius/nvidia/Nemotron-3-Nano-Omni": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 6e-08, @@ -44209,7 +42633,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Nano-Omni" }, "nebius/nvidia/nemotron-3-super-120b-a12b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, @@ -44221,7 +42644,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2Fnemotron-3-super-120b-a12b" }, "nebius/nvidia/Nemotron-3-Ultra-550b-a55b": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1e-06, @@ -44233,7 +42655,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Ultra-550b-a55b" }, "nebius/nvidia/Nemotron-3_5-Lightning": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 6e-08, @@ -44245,7 +42666,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3_5-Lightning" }, "nebius/openai/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, @@ -44257,7 +42677,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/openai%2Fgpt-oss-120b" }, "nebius/openbmb/MiniCPM-V-4_5": { - "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 6.58e-07, @@ -44268,7 +42687,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/image2text/openbmb%2FMiniCPM-V-4_5" }, "nebius/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-07, @@ -44279,7 +42697,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-235B-A22B-Instruct-2507" }, "nebius/Qwen/Qwen3-30B-A3B-Instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-07, @@ -44290,7 +42707,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-30B-A3B-Instruct-2507" }, "nebius/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.5e-07, @@ -44302,7 +42718,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-Next-80B-A3B-Thinking" }, "nebius/Qwen/Qwen3.5-397B-A17B": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 6e-07, @@ -44324,7 +42739,6 @@ "supports_reasoning": true }, "nebius/zai-org/GLM-5.1": { - "max_tokens": 202752, "max_input_tokens": 202752, "max_output_tokens": 202752, "input_cost_per_token": 1.4e-06, @@ -44336,7 +42750,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.1" }, "nebius/zai-org/GLM-5.2": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.4e-06, @@ -44351,7 +42764,7 @@ "input_cost_per_token": 1.4e-06, "litellm_provider": "nebius", "max_input_tokens": 1024000, - "max_tokens": 1024000, + "max_output_tokens": 1024000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", @@ -44359,7 +42772,6 @@ "supports_reasoning": true }, "nebius/zai-org/GLM-5.3-Flash": { - "max_tokens": 1024000, "max_input_tokens": 1024000, "max_output_tokens": 1024000, "input_cost_per_token": 1.5e-07, @@ -44372,7 +42784,6 @@ "supports_vision": true }, "nebius/BAAI/bge-en-icl": { - "max_tokens": 32768, "max_input_tokens": 32768, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -44381,7 +42792,6 @@ "source": "https://nebius.com/prices" }, "nebius/BAAI/bge-multilingual-gemma2": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -44390,7 +42800,6 @@ "source": "https://nebius.com/prices" }, "nebius/intfloat/e5-mistral-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -44399,7 +42808,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-Embedding-8B": { - "max_tokens": 40960, "max_input_tokens": 40960, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -44416,7 +42824,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, @@ -44438,7 +42845,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.3e-07, "output_cost_per_token_batches": 1.2e-07, @@ -44459,7 +42865,6 @@ "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, @@ -44482,7 +42887,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.5e-07, "output_cost_per_token_batches": 3.25e-07, @@ -44505,7 +42909,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_batches": 3e-05, @@ -44528,7 +42931,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_batches": 3e-05, @@ -44550,7 +42952,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.0006, "output_cost_per_token_batches": 0.0003, @@ -44584,7 +42985,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.0006, "output_cost_per_token_batches": 0.0003, @@ -44622,7 +43022,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, @@ -44663,7 +43062,6 @@ "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", @@ -44696,7 +43094,6 @@ "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", @@ -44733,7 +43130,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, @@ -44776,7 +43172,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -44797,7 +43192,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -44816,7 +43210,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, @@ -44854,7 +43247,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, @@ -44897,7 +43289,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -44925,7 +43316,6 @@ "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", @@ -44958,7 +43348,6 @@ "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", @@ -44995,7 +43384,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -45022,7 +43410,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45035,7 +43422,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45048,7 +43434,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.068e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45061,7 +43446,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45075,7 +43459,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45088,7 +43471,6 @@ "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45102,7 +43484,6 @@ "litellm_provider": "oci", "max_input_tokens": 10485760, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45115,7 +43496,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45128,7 +43508,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45141,7 +43520,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45154,7 +43532,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45167,7 +43544,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45180,7 +43556,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -45193,7 +43568,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -45206,7 +43580,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -45219,7 +43592,6 @@ "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45239,7 +43611,6 @@ "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45258,7 +43629,6 @@ "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45278,7 +43648,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -45292,7 +43661,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -45314,7 +43682,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45326,7 +43693,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45339,7 +43705,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 9e-08, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45351,7 +43716,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45363,7 +43727,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45375,7 +43738,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45388,7 +43750,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45400,7 +43761,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45412,7 +43772,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45424,7 +43783,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [], @@ -45437,7 +43795,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45452,7 +43809,6 @@ "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, @@ -45468,7 +43824,6 @@ "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, @@ -45485,7 +43840,6 @@ "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, @@ -45501,7 +43855,6 @@ "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, @@ -45515,7 +43868,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45527,7 +43879,6 @@ "litellm_provider": "oci", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45542,7 +43893,6 @@ "litellm_provider": "oci", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45557,7 +43907,6 @@ "litellm_provider": "oci", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45572,7 +43921,6 @@ "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", @@ -45585,7 +43933,6 @@ "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", @@ -45597,7 +43944,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -45607,7 +43953,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, @@ -45617,7 +43962,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -45627,7 +43971,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, @@ -45637,7 +43980,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -45648,7 +43990,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, @@ -45659,7 +44000,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, @@ -45670,7 +44010,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "oci", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -45682,7 +44021,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": false @@ -45692,7 +44030,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -45701,7 +44038,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -45710,7 +44046,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45720,7 +44055,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45730,7 +44064,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45740,7 +44073,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45750,7 +44082,6 @@ "litellm_provider": "ollama", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45760,7 +44091,6 @@ "litellm_provider": "ollama", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45770,7 +44100,6 @@ "litellm_provider": "ollama", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45780,7 +44109,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45790,7 +44118,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45799,7 +44126,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -45808,7 +44134,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45817,7 +44142,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45826,7 +44150,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45835,7 +44158,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45844,7 +44166,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45854,7 +44175,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45863,7 +44183,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45872,7 +44191,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45882,7 +44200,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45892,7 +44209,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45902,7 +44218,6 @@ "litellm_provider": "ollama", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45912,7 +44227,6 @@ "litellm_provider": "ollama", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45922,7 +44236,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45932,7 +44245,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -45941,7 +44253,6 @@ "litellm_provider": "ollama", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45951,7 +44262,6 @@ "litellm_provider": "ollama", "max_input_tokens": 2048, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -45960,7 +44270,6 @@ "litellm_provider": "openai", "max_input_tokens": 32768, "max_output_tokens": 0, - "max_tokens": 0, "mode": "moderation", "output_cost_per_token": 0.0 }, @@ -45969,7 +44278,6 @@ "litellm_provider": "openai", "max_input_tokens": 32768, "max_output_tokens": 0, - "max_tokens": 0, "mode": "moderation", "output_cost_per_token": 0.0 }, @@ -45987,7 +44295,6 @@ "litellm_provider": "bedrock_converse", "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, @@ -46013,7 +44320,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07, "output_cost_per_token_batches": 1.5e-07, @@ -46033,7 +44339,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, @@ -46055,7 +44360,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_batches": 1e-07, @@ -46074,7 +44378,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46088,7 +44391,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46101,7 +44403,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46114,7 +44415,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46127,7 +44427,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 127000, "max_output_tokens": 127000, - "max_tokens": 127000, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46140,7 +44439,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 118000, "max_output_tokens": 118000, - "max_tokens": 118000, "mode": "chat", "output_cost_per_token": 1.3e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46153,7 +44451,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46167,7 +44464,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.3e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46180,7 +44476,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 8.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46193,7 +44488,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 9.1e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46207,7 +44501,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.3e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46221,7 +44514,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46235,7 +44527,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46249,7 +44540,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.9e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46263,7 +44553,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.9e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46296,7 +44585,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-06 }, @@ -46305,7 +44593,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -46314,7 +44601,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -46323,7 +44609,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -46332,7 +44617,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07 }, @@ -46341,7 +44625,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -46350,7 +44633,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -46359,7 +44641,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -46369,7 +44650,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -46378,7 +44658,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -46388,7 +44667,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -46444,7 +44722,7 @@ "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-06, "search_context_cost_per_query": { @@ -46459,7 +44737,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 8e-06, @@ -46476,7 +44754,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.8e-06 }, @@ -46486,7 +44763,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 12000, "max_output_tokens": 12000, - "max_tokens": 12000, "mode": "chat", "output_cost_per_token": 1.8e-06 }, @@ -46495,7 +44771,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 200000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -46509,7 +44784,7 @@ "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-06, "search_context_cost_per_query": { @@ -46524,7 +44799,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 8e-06, "search_context_cost_per_query": { @@ -46540,7 +44815,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -46550,7 +44824,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 12000, "max_output_tokens": 12000, - "max_tokens": 12000, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -46559,7 +44832,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46571,7 +44843,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46583,7 +44854,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46595,7 +44865,6 @@ "litellm_provider": "publicai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46607,7 +44876,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46619,7 +44887,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46859,7 +45126,6 @@ "input_cost_per_token": 4e-09, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -46869,7 +45135,6 @@ "input_cost_per_token": 3e-08, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560, @@ -46880,7 +45145,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46892,7 +45156,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46905,7 +45168,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46919,7 +45181,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.8e-06, "supports_function_calling": true, @@ -46934,7 +45195,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8.8e-07, "output_cost_per_token_flex": 4.4e-07, @@ -46954,7 +45214,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, @@ -46973,7 +45232,6 @@ "litellm_provider": "bedrock_converse", "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, @@ -46990,7 +45248,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -47006,7 +45263,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", @@ -47022,7 +45278,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", @@ -47038,7 +45293,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.236e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", @@ -47054,7 +45308,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", @@ -47070,7 +45323,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.86e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", @@ -47086,7 +45338,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", @@ -47104,7 +45355,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.66e-06, "output_cost_per_token_batches": 1.33e-06, @@ -47125,7 +45375,6 @@ "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, @@ -47180,7 +45429,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, "supports_tool_choice": true @@ -47190,7 +45438,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, "supports_tool_choice": true @@ -47200,7 +45447,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true @@ -47210,7 +45456,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true @@ -47220,7 +45465,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -47230,7 +45474,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -47240,7 +45483,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true @@ -47250,7 +45492,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true @@ -47260,7 +45501,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8086, "max_output_tokens": 8086, - "max_tokens": 8086, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -47270,7 +45510,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8086, "max_output_tokens": 8086, - "max_tokens": 8086, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -47280,7 +45519,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -47290,7 +45528,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -47300,7 +45537,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06, "supports_tool_choice": true @@ -47429,7 +45665,6 @@ "mode": "chat", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_system_messages": true }, @@ -47584,7 +45819,6 @@ "mode": "chat", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true @@ -47605,7 +45839,6 @@ "mode": "chat", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_reasoning": true, "supports_system_messages": true }, @@ -47615,7 +45848,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -47625,7 +45857,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -47635,7 +45866,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -47645,7 +45875,6 @@ "litellm_provider": "cohere", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cohere.com/pricing" @@ -47656,7 +45885,6 @@ "litellm_provider": "cohere", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cohere.com/pricing" @@ -47687,7 +45915,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -47696,7 +45923,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -47705,7 +45931,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -47714,7 +45939,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -47723,7 +45947,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -47732,7 +45955,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -47741,7 +45963,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 196608, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://cloud.sambanova.ai/plans/pricing", @@ -47754,7 +45975,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7e-06, "source": "https://cloud.sambanova.ai/plans/pricing" @@ -47764,7 +45984,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" }, @@ -47781,7 +46000,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.sambanova.ai/plans/pricing", @@ -47790,7 +46008,6 @@ "supports_tool_choice": true }, "sambanova/DeepSeek-V3.1": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-06, @@ -47803,7 +46020,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.2e-07, @@ -47816,7 +46032,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/DeepSeek-V3.2": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 3e-06, @@ -47828,7 +46043,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/gemma-4-31B-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3.8e-07, @@ -47844,7 +46058,6 @@ "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", @@ -47859,7 +46072,6 @@ "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", @@ -47875,7 +46087,6 @@ "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", @@ -47891,7 +46102,6 @@ "litellm_provider": "scx-ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.98e-06, "source": "https://scx.ai/pricing", @@ -47908,7 +46118,6 @@ "litellm_provider": "scx-ai", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.99e-06, "source": "https://scx.ai/pricing", @@ -47923,7 +46132,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 200000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, @@ -47939,7 +46147,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 1.35e-06, "output_cost_per_token": 5.4e-06, @@ -47950,56 +46157,48 @@ "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/jamba-1.5-large": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/jamba-1.5-mini": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/jamba-instruct": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama2-70b-chat": { "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3-70b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3-8b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3.1-405b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, @@ -48010,7 +46209,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 7.2e-07, "output_cost_per_token": 7.2e-07, @@ -48021,7 +46219,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 2.4e-07, "output_cost_per_token": 2.4e-07, @@ -48031,18 +46228,15 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3.2-3b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3.3-70b": { - "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 7.2e-07, @@ -48056,21 +46250,18 @@ "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/mistral-large": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/mistral-large2": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, @@ -48082,39 +46273,33 @@ "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/reka-core": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/reka-flash": { "litellm_provider": "snowflake", "max_input_tokens": 100000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-arctic": { "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-llama-3.1-405b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-llama-3.3-70b": { - "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 7.2e-07, @@ -48311,21 +46496,18 @@ "stability.sd3-5-large-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "stability.sd3-large-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "stability.stable-image-core-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, @@ -48501,21 +46683,18 @@ "stability.stable-image-core-v1:1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, "stability.stable-image-ultra-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.14 }, "stability.stable-image-ultra-v1:1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.14 }, @@ -48549,7 +46728,6 @@ "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "completion", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/" @@ -48559,7 +46737,6 @@ "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "completion", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/" @@ -48570,7 +46747,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -48582,7 +46758,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -48593,7 +46768,6 @@ "input_cost_per_token_batches": 6.5e-08, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0, @@ -48605,7 +46779,6 @@ "input_cost_per_token_batches": 1e-08, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0, @@ -48616,7 +46789,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -48627,7 +46799,6 @@ "input_cost_per_token_batches": 5e-08, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0 @@ -48637,7 +46808,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -48647,7 +46817,6 @@ "input_cost_per_token": 6.25e-09, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 3072, - "max_tokens": 3072, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -48659,7 +46828,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -48670,7 +46838,6 @@ "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 2.8e-05, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -48680,7 +46847,6 @@ "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 2.8e-05, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -48706,7 +46872,8 @@ "together-ai-8.1b-21b": { "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", - "max_tokens": 1000, + "max_output_tokens": 1000, + "max_input_tokens": 1000, "mode": "chat", "output_cost_per_token": 3e-07 }, @@ -48759,7 +46926,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "metadata": { "successor": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" }, @@ -48775,7 +46941,7 @@ "input_cost_per_token": 1.04e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.04e-06, "source": "https://api.together.ai/v1/models", @@ -48802,7 +46968,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.together.ai/v1/models", @@ -48823,7 +46989,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 202752, - "max_tokens": 202752, + "max_output_tokens": 202752, "metadata": { "successor": "together_ai/zai-org/GLM-5.2" }, @@ -48840,7 +47006,7 @@ "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 524288, - "max_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", @@ -48857,7 +47023,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://www.together.ai/pricing", @@ -48867,7 +47033,7 @@ "input_cost_per_token": 0.0, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.together.ai/docs/serverless-models" @@ -48876,7 +47042,7 @@ "input_cost_per_token": 1.7e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://api.together.ai/v1/models", @@ -48891,7 +47057,7 @@ "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://api.together.ai/v1/models", @@ -48902,7 +47068,7 @@ "input_cost_per_token": 1.5e-06, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://www.together.ai/pricing", @@ -48912,7 +47078,7 @@ "input_cost_per_token": 3.2e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.28e-06, "source": "https://api.together.ai/v1/models" @@ -48922,7 +47088,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 1010000, - "max_tokens": 1010000, + "max_output_tokens": 1010000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://api.together.ai/v1/models", @@ -48932,7 +47098,7 @@ "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://api.together.ai/v1/models" @@ -48943,7 +47109,7 @@ "input_cost_per_token": 1.4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://api.together.ai/v1/models", @@ -48958,7 +47124,7 @@ "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", @@ -48972,7 +47138,7 @@ "input_cost_per_token": 1.32e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://api.together.ai/v1/models", @@ -48987,7 +47153,7 @@ "input_cost_per_token": 3.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models", @@ -48998,7 +47164,7 @@ "input_cost_per_token": 1.25e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.25e-06, "source": "https://docs.together.ai/docs/serverless-models", @@ -49011,7 +47177,7 @@ "input_cost_per_token": 3e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ @@ -49033,7 +47199,7 @@ "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 524288, - "max_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 4.05e-06, "source": "https://api.together.ai/v1/models", @@ -49049,7 +47215,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models", @@ -49066,7 +47231,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models", @@ -49083,7 +47247,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://api.together.ai/v1/models", @@ -49168,7 +47331,6 @@ "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, @@ -49187,7 +47349,6 @@ "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, @@ -49208,7 +47369,6 @@ "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, @@ -49229,7 +47389,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -49249,7 +47408,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -49277,7 +47435,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -49295,7 +47452,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -49314,7 +47470,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -49332,7 +47487,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -49350,7 +47504,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -49389,7 +47542,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -49431,7 +47583,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -49463,7 +47614,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, @@ -49503,7 +47653,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, @@ -49542,7 +47691,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, @@ -49580,7 +47728,6 @@ "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, @@ -49618,7 +47765,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, @@ -49654,7 +47800,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -49672,7 +47817,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "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", @@ -49688,7 +47832,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "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", @@ -49703,7 +47846,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -49721,7 +47863,6 @@ "litellm_provider": "bedrock_converse", "max_input_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", @@ -49741,7 +47882,6 @@ "litellm_provider": "bedrock_converse", "max_input_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", @@ -49768,7 +47908,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": false, @@ -49785,7 +47924,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "supports_assistant_prefill": true, @@ -49815,7 +47953,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -49843,7 +47980,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -49880,7 +48016,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -49917,7 +48052,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -49957,7 +48091,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -49988,7 +48121,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", @@ -50004,7 +48136,6 @@ "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, @@ -50025,7 +48156,6 @@ "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, @@ -50043,7 +48173,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -50057,7 +48186,6 @@ "litellm_provider": "bedrock", "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, @@ -50072,7 +48200,6 @@ "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, @@ -50086,7 +48213,6 @@ "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", @@ -50100,7 +48226,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -50113,7 +48238,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -50126,7 +48250,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -50141,7 +48264,6 @@ "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, @@ -50156,7 +48278,6 @@ "litellm_provider": "bedrock_converse", "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, @@ -50179,7 +48300,6 @@ "litellm_provider": "bedrock_converse", "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, @@ -50200,7 +48320,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "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", @@ -50212,7 +48331,6 @@ "litellm_provider": "v0", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -50226,7 +48344,6 @@ "litellm_provider": "v0", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -50240,7 +48357,6 @@ "litellm_provider": "v0", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -50254,7 +48370,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.4e-07 }, @@ -50263,7 +48378,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07 }, @@ -50272,7 +48386,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07 }, @@ -50281,7 +48394,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -50292,7 +48404,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 262144, "max_output_tokens": 66536, - "max_tokens": 66536, "mode": "chat", "output_cost_per_token": 1.6e-06, "supports_function_calling": true, @@ -50303,7 +48414,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-07, "supports_vision": true, @@ -50315,7 +48425,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.4e-07, "supports_function_calling": true, @@ -50326,7 +48435,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.2e-06, "supports_vision": true, @@ -50338,7 +48446,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -50349,7 +48456,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_vision": true, @@ -50364,7 +48470,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_vision": true, @@ -50379,7 +48484,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_vision": true, @@ -50394,7 +48498,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -50409,7 +48512,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -50424,7 +48526,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_vision": true, @@ -50439,7 +48540,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -50452,7 +48552,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -50470,7 +48569,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -50488,7 +48586,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -50507,7 +48604,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -50527,7 +48623,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, @@ -50547,7 +48642,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, @@ -50567,7 +48661,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": true, @@ -50590,7 +48683,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": false, @@ -50611,7 +48703,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -50631,7 +48722,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -50648,7 +48738,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -50660,7 +48749,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -50671,7 +48759,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -50682,7 +48769,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -50691,7 +48777,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.19e-06, "supports_tool_choice": true @@ -50701,7 +48786,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 9.9e-07, "supports_function_calling": true, @@ -50713,7 +48797,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "supports_tool_choice": true @@ -50723,7 +48806,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1000000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.5e-06, "supports_vision": true, @@ -50742,7 +48824,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, @@ -50763,7 +48844,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50772,7 +48852,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "supports_vision": true, @@ -50784,7 +48863,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50793,7 +48871,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50802,7 +48879,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -50811,7 +48887,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.9e-07, "supports_tool_choice": true @@ -50821,7 +48896,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8e-08, "supports_tool_choice": true @@ -50831,7 +48905,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_tool_choice": true @@ -50841,7 +48914,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-08, "supports_function_calling": true, @@ -50852,7 +48924,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.6e-07, "supports_vision": true, @@ -50864,7 +48935,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-07 }, @@ -50873,7 +48943,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_function_calling": true, @@ -50884,7 +48953,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_vision": true, @@ -50896,7 +48964,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_function_calling": true, @@ -50907,7 +48974,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "supports_tool_choice": true @@ -50917,7 +48983,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-07, "supports_vision": true, @@ -50929,7 +48994,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 9e-07, "supports_function_calling": true, @@ -50940,7 +49004,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -50949,7 +49012,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.8e-07, "supports_function_calling": true, @@ -50961,7 +49023,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_function_calling": true, @@ -50973,7 +49034,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true @@ -50983,7 +49043,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, @@ -50994,7 +49053,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1e-07, "supports_vision": true, @@ -51006,7 +49064,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -51015,7 +49072,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -51026,7 +49082,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.9e-07 }, @@ -51035,7 +49090,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -51047,7 +49101,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 65536, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true @@ -51057,7 +49110,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_vision": true, @@ -51070,7 +49122,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_vision": true, @@ -51083,7 +49134,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.2e-06, "supports_function_calling": true, @@ -51094,7 +49144,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, @@ -51103,7 +49152,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.9e-06 }, @@ -51112,7 +49160,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -51123,7 +49170,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06 }, @@ -51132,7 +49178,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_vision": true, @@ -51146,7 +49191,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "supports_vision": true, @@ -51161,7 +49205,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "supports_vision": true, @@ -51176,7 +49219,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_vision": true, @@ -51191,7 +49233,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, @@ -51206,7 +49247,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_vision": true, @@ -51221,7 +49261,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_vision": true, @@ -51236,7 +49275,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_vision": true, @@ -51251,7 +49289,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, @@ -51265,7 +49302,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_vision": true, @@ -51278,7 +49314,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51287,7 +49322,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51296,7 +49330,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51305,7 +49338,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -51314,7 +49346,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-05 }, @@ -51323,7 +49354,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 5e-06 }, @@ -51332,7 +49362,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-06 }, @@ -51341,7 +49370,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -51353,7 +49381,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -51365,7 +49392,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -51376,7 +49402,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, @@ -51388,7 +49413,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -51399,7 +49423,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_function_calling": true @@ -51409,7 +49432,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "supports_function_calling": true, @@ -51420,7 +49442,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "supports_function_calling": true, @@ -51431,7 +49452,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -51442,7 +49462,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-06, "supports_function_calling": true, @@ -51453,7 +49472,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 96000, - "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 1.1e-06, "supports_function_calling": true, @@ -51465,7 +49483,6 @@ "input_cost_per_token": 4.5e-07, "max_input_tokens": 200000, "max_output_tokens": 200000, - "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 1.8e-06, "source": "https://vercel.com/ai-gateway/models/glm-4.6", @@ -51516,7 +49533,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -51530,7 +49546,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -51550,7 +49565,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -51579,7 +49593,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -51602,7 +49615,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -51618,7 +49630,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -51633,7 +49644,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_assistant_prefill": true, @@ -51647,7 +49657,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_assistant_prefill": true, @@ -51661,7 +49670,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, @@ -51675,7 +49683,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, @@ -51688,7 +49695,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -51701,7 +49707,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -51721,7 +49726,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -51756,7 +49760,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -51795,7 +49798,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -51833,7 +49835,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -51870,7 +49871,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -51908,7 +49908,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -51946,7 +49945,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -51984,7 +49982,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -52028,7 +50025,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -52066,7 +50062,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -52111,7 +50106,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -52150,7 +50144,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -52187,7 +50180,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1.25e-05, @@ -52228,7 +50220,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1.25e-05, @@ -52271,7 +50262,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -52310,7 +50300,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -52350,7 +50339,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -52380,7 +50368,6 @@ "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, @@ -52419,7 +50406,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -52458,7 +50444,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -52482,7 +50467,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -52494,7 +50478,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -52506,7 +50489,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -52518,7 +50500,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -52530,7 +50511,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -52541,7 +50521,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -52552,7 +50531,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -52566,7 +50544,6 @@ "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.7e-06, "output_cost_per_token_batches": 8.5e-07, @@ -52588,7 +50565,6 @@ "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.68e-06, "output_cost_per_token_batches": 8.4e-07, @@ -52609,7 +50585,6 @@ "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 65336, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "output_cost_per_token_batches": 2.7e-06, @@ -52632,7 +50607,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, @@ -52691,7 +50665,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -52726,7 +50699,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -52759,7 +50731,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, @@ -52787,7 +50758,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, @@ -52817,7 +50787,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, @@ -52857,7 +50826,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -52916,7 +50884,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -52977,7 +50944,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -53034,7 +51000,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -53048,7 +51013,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -53059,7 +51023,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -53070,7 +51033,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -53081,7 +51043,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -53092,7 +51053,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -53122,7 +51082,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "audio_speech", "output_cost_per_image": 0.04, "output_cost_per_token": 0, @@ -53158,7 +51117,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "audio_speech", "output_cost_per_image": 0.08, "output_cost_per_token": 0, @@ -53195,7 +51153,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.6e-05, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", @@ -53208,7 +51165,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", @@ -53221,7 +51177,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." }, @@ -53237,7 +51192,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." }, @@ -53254,7 +51208,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.15e-06, "output_cost_per_token_batches": 5.75e-07, @@ -53276,7 +51229,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.15e-06, "output_cost_per_token_batches": 5.75e-07, @@ -53298,7 +51250,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, - "max_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-07, "output_cost_per_token_batches": 3.5e-07, @@ -53320,7 +51271,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, - "max_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-07, "output_cost_per_token_batches": 3.5e-07, @@ -53341,7 +51291,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", @@ -53352,7 +51301,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", @@ -53363,7 +51311,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", @@ -53376,7 +51323,6 @@ "litellm_provider": "vertex_ai-minimax_models", "max_input_tokens": 196608, "max_output_tokens": 196608, - "max_tokens": 196608, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53390,7 +51336,6 @@ "litellm_provider": "vertex_ai-moonshot_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53405,7 +51350,6 @@ "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53423,7 +51367,6 @@ "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53440,7 +51383,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53452,7 +51394,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53464,7 +51405,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53476,7 +51416,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53488,7 +51427,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -53499,7 +51437,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -53510,7 +51447,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -53521,7 +51457,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -53532,7 +51467,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, @@ -53543,7 +51477,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_function_calling": true, @@ -53554,7 +51487,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -53567,7 +51499,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -53601,7 +51532,6 @@ "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 262144, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/maas/google/gemma-4-26b-a4b-it", @@ -53618,7 +51548,6 @@ "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.6e-07, "output_cost_per_token_batches": 1.8e-07, @@ -53631,7 +51560,6 @@ "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53646,7 +51574,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53663,7 +51590,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53683,7 +51609,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, - "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -53703,7 +51628,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, - "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -53724,7 +51648,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 200000, "max_output_tokens": 200000, - "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -53744,7 +51667,6 @@ "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, @@ -53763,7 +51685,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 8.8e-07, "output_cost_per_token_batches": 4.4e-07, @@ -53783,7 +51704,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-06, "output_cost_per_token_batches": 9e-07, @@ -53800,7 +51720,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53816,7 +51735,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53829,7 +51747,6 @@ "vertex_ai/veo-3.1-generate-preview": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, @@ -53844,7 +51761,6 @@ "vertex_ai/veo-3.1-fast-generate-preview": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -53861,7 +51777,6 @@ "deprecation_date": "2026-11-17", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, @@ -53877,7 +51792,6 @@ "deprecation_date": "2026-11-17", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -53893,7 +51807,6 @@ "vertex_ai/veo-3.1-lite-generate-001": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08, @@ -53911,7 +51824,6 @@ "litellm_provider": "voyage", "max_input_tokens": 16000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -53920,7 +51832,6 @@ "litellm_provider": "voyage", "max_input_tokens": 8000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -53929,7 +51840,6 @@ "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" @@ -53939,7 +51849,6 @@ "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" @@ -53949,7 +51858,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -53958,7 +51866,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -53967,7 +51874,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" @@ -53977,7 +51883,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" @@ -53986,7 +51891,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4000, - "max_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -53994,7 +51898,6 @@ "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54002,7 +51905,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -54012,7 +51914,6 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54020,7 +51921,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54028,7 +51928,6 @@ "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54036,7 +51935,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54044,7 +51942,6 @@ "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 }, @@ -54052,7 +51949,6 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54060,7 +51956,6 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 120000, - "max_tokens": 120000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54068,7 +51963,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54076,7 +51970,6 @@ "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 }, @@ -54084,7 +51977,6 @@ "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, @@ -54094,7 +51986,6 @@ "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 }, @@ -54102,7 +51993,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4096, - "max_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54110,7 +52000,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4000, - "max_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54118,13 +52007,11 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, "wandb/openai/gpt-oss-120b": { "supports_reasoning": true, - "max_tokens": 131072, "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -54135,7 +52022,6 @@ }, "wandb/openai/gpt-oss-20b": { "supports_reasoning": true, - "max_tokens": 131072, "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -54145,7 +52031,6 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/moonshotai/Kimi-K2.5": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "cache_read_input_token_cost": 1e-07, @@ -54160,7 +52045,6 @@ "supports_vision": true }, "wandb/meta-llama/Llama-3.1-8B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 131000, "max_output_tokens": 128000, "input_cost_per_token": 2.2e-07, @@ -54171,7 +52055,6 @@ }, "wandb/deepseek-ai/DeepSeek-V3.1": { "supports_reasoning": true, - "max_tokens": 128000, "max_input_tokens": 161000, "max_output_tokens": 128000, "input_cost_per_token": 5.5e-07, @@ -54181,7 +52064,6 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 7.1e-07, @@ -54195,7 +52077,6 @@ "litellm_provider": "watsonx", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 2e-07, "supports_audio_input": false, @@ -54213,7 +52094,6 @@ "litellm_provider": "watsonx", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_audio_input": false, @@ -54227,7 +52107,6 @@ "supports_vision": false }, "watsonx/bigscience/mt0-xxl-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.908e-06, @@ -54240,7 +52119,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/bigscience/mt0-xxl": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.908e-06, @@ -54253,7 +52131,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/core42/jais-13b-chat": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 0.0005, @@ -54265,7 +52142,6 @@ "supports_vision": false }, "watsonx/google/flan-t5-xl-3b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, @@ -54277,7 +52153,6 @@ "supports_vision": false }, "watsonx/ibm/granite-13b-chat-v2": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, @@ -54289,7 +52164,6 @@ "supports_vision": false }, "watsonx/ibm/granite-13b-instruct-v2": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, @@ -54301,7 +52175,6 @@ "supports_vision": false }, "watsonx/ibm/granite-3-3-8b-instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -54313,7 +52186,6 @@ "supports_vision": false }, "watsonx/ibm/granite-4-h-small": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6.36e-08, @@ -54326,7 +52198,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/ibm/granite-guardian-3-2-2b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -54338,7 +52209,6 @@ "supports_vision": false }, "watsonx/ibm/granite-guardian-3-3-8b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -54350,7 +52220,6 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-1024-96-r2": { - "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, @@ -54362,7 +52231,6 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-1536-96-r2": { - "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, @@ -54374,7 +52242,6 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-512-96-r2": { - "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, @@ -54386,7 +52253,6 @@ "supports_vision": false }, "watsonx/ibm/granite-vision-3-2-2b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -54398,7 +52264,6 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-2-11b-vision-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, @@ -54410,7 +52275,6 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-2-1b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-07, @@ -54422,7 +52286,6 @@ "supports_vision": false }, "watsonx/meta-llama/llama-3-2-3b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.5e-07, @@ -54434,7 +52297,6 @@ "supports_vision": false }, "watsonx/meta-llama/llama-3-2-90b-vision-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-06, @@ -54446,7 +52308,6 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-3-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 7.526e-07, @@ -54459,7 +52320,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, @@ -54472,7 +52332,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, @@ -54485,7 +52344,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-guard-3-11b-vision": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, @@ -54497,7 +52355,6 @@ "supports_vision": true }, "watsonx/mistralai/mistral-medium-2505": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3e-06, @@ -54509,7 +52366,6 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-2503": { - "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 1e-07, @@ -54521,7 +52377,6 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { - "max_tokens": 16384, "max_input_tokens": 131072, "max_output_tokens": 16384, "input_cost_per_token": 1.06e-07, @@ -54534,7 +52389,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/mistralai/pixtral-12b-2409": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, @@ -54546,7 +52400,6 @@ "supports_vision": true }, "watsonx/openai/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.59e-07, @@ -54559,7 +52412,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/sdaia/allam-1-13b-instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1.8e-06, @@ -54596,7 +52448,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -54621,7 +52472,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -54645,7 +52495,6 @@ "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, @@ -54671,7 +52520,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -54699,7 +52547,6 @@ "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_above_200k_tokens": 5e-06, @@ -54727,7 +52574,6 @@ "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_above_200k_tokens": 5e-06, @@ -54751,7 +52597,6 @@ "litellm_provider": "xai", "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, @@ -54773,7 +52618,6 @@ "litellm_provider": "xai", "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, @@ -54795,7 +52639,6 @@ "litellm_provider": "xai", "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, @@ -54817,7 +52660,6 @@ "litellm_provider": "xai", "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, @@ -54839,7 +52681,6 @@ "litellm_provider": "xai", "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, @@ -54861,7 +52702,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, @@ -54884,7 +52724,6 @@ "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, @@ -54907,7 +52746,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -55505,7 +53343,6 @@ } }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 4.5e-07, @@ -55515,7 +53352,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/flux-kontext-pro": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 4e-08, @@ -55524,7 +53360,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/SSD-1B": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -55533,7 +53368,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -55542,7 +53376,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -55551,7 +53384,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -55560,7 +53392,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b-python": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -55569,7 +53400,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -55578,7 +53408,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -55587,7 +53416,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b-python": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -55596,7 +53424,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -55605,7 +53432,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -55614,7 +53440,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b-python": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -55623,7 +53448,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -55632,7 +53456,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -55641,7 +53464,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b-python": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -55650,7 +53472,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 2e-07, @@ -55659,7 +53480,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/codegemma-2b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -55668,7 +53488,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/codegemma-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -55677,7 +53496,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.2e-06, @@ -55686,7 +53504,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -55695,7 +53512,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55704,7 +53520,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55713,7 +53528,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55722,7 +53536,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55731,7 +53544,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-kontext-max": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 8e-08, @@ -55740,7 +53552,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/dbrx-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.2e-06, @@ -55749,7 +53560,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, @@ -55758,7 +53568,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -55767,7 +53576,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -55776,7 +53584,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -55785,7 +53592,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -55794,7 +53600,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -55803,7 +53608,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -55812,7 +53616,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-prover-v2": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.2e-06, @@ -55821,7 +53624,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55830,7 +53632,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55839,7 +53640,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55848,7 +53648,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55857,7 +53656,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -55866,7 +53664,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55875,7 +53672,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55884,7 +53680,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -55893,7 +53688,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-v2p5": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.2e-06, @@ -55902,7 +53696,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/devstral-small-2505": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55911,7 +53704,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55920,7 +53712,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55929,7 +53720,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55938,7 +53728,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -55947,7 +53736,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt": { - "max_tokens": 4096, "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -55956,7 +53744,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt": { - "max_tokens": 4096, "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -55965,7 +53752,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/fare-20b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55974,7 +53760,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firefunction-v1": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -55983,7 +53768,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firellava-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -55992,7 +53776,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56001,7 +53784,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/fireworks-asr-large": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0.0, @@ -56010,7 +53792,6 @@ "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/fireworks-asr-v2": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0.0, @@ -56019,7 +53800,6 @@ "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56028,7 +53808,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-09, @@ -56037,7 +53816,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 5e-10, @@ -56046,7 +53824,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/flux-1-schnell": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56055,7 +53832,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 3.5e-10, @@ -56064,7 +53840,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/gemma-2b-it": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -56073,7 +53848,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-3-27b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56082,7 +53856,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56091,7 +53864,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-7b-it": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56100,7 +53872,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma2-9b-it": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56109,7 +53880,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/glm-4p5v": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.2e-06, @@ -56119,7 +53889,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.2e-06, @@ -56128,7 +53897,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-07, @@ -56137,7 +53905,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56146,7 +53913,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-38b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -56155,7 +53921,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-78b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -56164,7 +53929,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-8b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -56173,7 +53937,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/japanese-stable-diffusion-xl": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -56182,7 +53945,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/kat-coder": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-07, @@ -56191,7 +53953,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/kat-dev-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56200,7 +53961,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56209,7 +53969,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-2-8b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56218,7 +53977,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-3-1b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -56227,7 +53985,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-3-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -56236,7 +53993,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56245,7 +54001,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56254,7 +54009,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-70b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56263,7 +54017,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat": { - "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 9e-07, @@ -56272,7 +54025,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-7b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56281,7 +54033,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56290,7 +54041,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 9e-07, @@ -56299,7 +54049,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 9e-07, @@ -56308,7 +54057,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-8b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56317,7 +54065,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56326,7 +54073,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56335,7 +54081,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56344,7 +54089,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56353,7 +54097,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56362,7 +54105,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -56371,7 +54113,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -56380,7 +54121,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56389,7 +54129,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llamaguard-7b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56398,7 +54137,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llava-yi-34b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -56407,7 +54145,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/minimax-m1-80k": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56416,7 +54153,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/minimax-m2": { - "max_tokens": 4096, "max_input_tokens": 196608, "max_output_tokens": 4096, "input_cost_per_token": 3e-07, @@ -56425,7 +54161,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 2e-07, @@ -56434,7 +54169,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 1e-07, @@ -56443,7 +54177,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 2e-07, @@ -56452,7 +54185,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56461,7 +54193,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56470,7 +54201,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56479,7 +54209,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56488,7 +54217,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56497,7 +54225,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 1.2e-06, @@ -56506,7 +54233,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -56515,7 +54241,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -56524,7 +54249,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56533,7 +54257,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 1.2e-06, @@ -56542,7 +54265,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 1.2e-06, @@ -56551,7 +54273,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -56560,7 +54281,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -56569,7 +54289,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -56578,7 +54297,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mythomax-l2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56587,7 +54305,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl": { - "max_tokens": 4096, "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56596,7 +54313,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56605,7 +54321,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -56614,7 +54329,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -56623,7 +54337,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56632,7 +54345,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -56641,7 +54353,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56650,7 +54361,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2": { - "max_tokens": 131072, "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -56659,7 +54369,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2": { - "max_tokens": 131072, "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -56668,7 +54377,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56677,7 +54385,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56686,7 +54393,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56695,7 +54401,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openorca-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56704,7 +54409,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-2-3b": { - "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 1e-07, @@ -56713,7 +54417,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -56722,7 +54425,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct": { - "max_tokens": 32064, "max_input_tokens": 32064, "max_output_tokens": 32064, "input_cost_per_token": 2e-07, @@ -56731,7 +54433,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -56740,7 +54441,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -56749,7 +54449,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -56758,7 +54457,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/playground-v2-1024px-aesthetic": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -56767,7 +54465,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/playground-v2-5-1024px-aesthetic": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -56776,7 +54473,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/pythia-12b": { - "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 2e-07, @@ -56785,7 +54481,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56794,7 +54489,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56803,7 +54497,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -56812,7 +54505,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56821,7 +54513,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56830,7 +54521,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56839,7 +54529,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56848,7 +54537,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56857,7 +54545,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56866,7 +54553,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-14b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -56875,7 +54561,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56884,7 +54569,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56893,7 +54577,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56902,7 +54585,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-72b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56911,7 +54593,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56920,7 +54601,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56929,7 +54609,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56938,7 +54617,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56947,7 +54625,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56956,7 +54633,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56965,7 +54641,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56974,7 +54649,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56983,7 +54657,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56992,7 +54665,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -57001,7 +54673,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -57010,7 +54681,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 9e-07, @@ -57019,7 +54689,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -57028,7 +54697,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -57037,7 +54705,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -57046,7 +54713,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -57055,7 +54721,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57064,7 +54729,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 9e-07, @@ -57073,7 +54737,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -57082,7 +54745,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 9e-07, @@ -57091,7 +54753,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -57100,7 +54761,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-0p6b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, @@ -57109,7 +54769,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-14b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -57118,7 +54777,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -57127,7 +54785,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-07, @@ -57136,7 +54793,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -57145,7 +54801,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, @@ -57154,7 +54809,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.2e-07, @@ -57163,7 +54817,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -57172,7 +54825,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -57181,7 +54833,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, @@ -57190,7 +54841,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-07, @@ -57199,7 +54849,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-07, @@ -57208,7 +54857,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -57218,7 +54866,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/qwen3-4b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -57227,7 +54874,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-07, @@ -57236,7 +54882,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-8b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -57246,7 +54891,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -57255,7 +54899,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16": { - "max_tokens": 4096, "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57264,7 +54907,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 0.0, @@ -57273,7 +54915,6 @@ "mode": "embedding" }, "fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, @@ -57282,7 +54923,6 @@ "mode": "embedding" }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57291,7 +54931,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57300,7 +54939,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-0p6b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, @@ -57309,7 +54947,6 @@ "mode": "rerank" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-4b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, @@ -57318,7 +54955,6 @@ "mode": "rerank" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -57328,7 +54964,6 @@ "source": "https://api.fireworks.ai/v1/serverless/models" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -57337,7 +54972,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -57346,7 +54980,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -57355,7 +54988,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -57364,7 +54996,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57373,7 +55004,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct": { - "max_tokens": 4096, "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -57387,7 +55017,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -57398,7 +55027,6 @@ "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/qwq-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -57407,7 +55035,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/rolm-ocr": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -57416,7 +55043,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -57425,7 +55051,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/stable-diffusion-xl-1024-v1-0": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -57434,7 +55059,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/stablecode-3b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -57443,7 +55067,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder-16b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -57452,7 +55075,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -57461,7 +55083,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-15b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -57470,7 +55091,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-3b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, @@ -57479,7 +55099,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-7b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -57488,7 +55107,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/toppy-m-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -57497,7 +55115,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57506,7 +55123,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 9e-07, @@ -57515,7 +55131,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b-chat": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57524,7 +55139,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-6b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -57533,7 +55147,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/zephyr-7b-beta": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -57547,7 +55160,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -57564,7 +55176,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -57581,7 +55192,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -57596,7 +55206,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-06, "supports_function_calling": true, @@ -57608,7 +55217,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -57620,7 +55228,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.25e-06, "supports_function_calling": true @@ -57636,7 +55243,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -57647,7 +55253,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true @@ -57663,7 +55268,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 5e-07, "supports_function_calling": true, @@ -57675,7 +55279,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.5e-06, "supports_reasoning": true, @@ -57688,7 +55291,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.5e-07, "supports_function_calling": true, @@ -57699,7 +55301,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, "supports_vision": true, @@ -57717,7 +55318,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 9e-07, "supports_function_calling": true @@ -57729,7 +55329,6 @@ "output_cost_per_token": 4e-07, "max_input_tokens": 163840, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57746,7 +55345,6 @@ "output_cost_per_token": 1.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57762,7 +55360,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57779,7 +55376,6 @@ "output_cost_per_token": 3.3e-07, "max_input_tokens": 262144, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57796,7 +55392,6 @@ "output_cost_per_token": 1.38e-07, "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_vision": true, "supports_system_messages": true }, @@ -57807,7 +55402,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, "max_output_tokens": 100352, - "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57824,7 +55418,6 @@ "output_cost_per_token": 1.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57841,7 +55434,6 @@ "output_cost_per_token": 2e-08, "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_vision": true, "supports_system_messages": true }, @@ -57852,7 +55444,6 @@ "output_cost_per_token": 4.1e-07, "max_input_tokens": 163840, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57867,7 +55458,6 @@ "output_cost_per_token": 3.95e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true, @@ -57881,7 +55471,6 @@ "output_cost_per_token": 9e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57899,7 +55488,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57916,7 +55504,6 @@ "output_cost_per_token": 1.2e-06, "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57932,7 +55519,6 @@ "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57947,7 +55533,6 @@ "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57962,7 +55547,6 @@ "output_cost_per_token": 3e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, @@ -57975,7 +55559,6 @@ "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57992,7 +55575,6 @@ "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58007,7 +55589,6 @@ "output_cost_per_token": 8.45e-06, "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58021,7 +55602,6 @@ "output_cost_per_token": 6e-07, "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, @@ -58034,7 +55614,6 @@ "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58051,7 +55630,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, "max_output_tokens": 100352, - "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58065,7 +55643,6 @@ "output_cost_per_token": 1.55e-06, "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58079,7 +55656,6 @@ "output_cost_per_token": 2.7e-07, "max_input_tokens": 160000, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58093,7 +55669,6 @@ "output_cost_per_token": 2.5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58109,7 +55684,6 @@ "output_cost_per_token": 2.3e-06, "max_input_tokens": 131072, "max_output_tokens": 100352, - "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58123,7 +55697,6 @@ "output_cost_per_token": 1.12e-06, "max_input_tokens": 163840, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58139,7 +55712,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 131072, "max_output_tokens": 98304, - "max_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58155,7 +55727,6 @@ "output_cost_per_token": 3e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58169,7 +55740,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_system_messages": true, "supports_response_schema": true }, @@ -58180,7 +55750,6 @@ "output_cost_per_token": 1e-07, "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, @@ -58193,7 +55762,6 @@ "output_cost_per_token": 1.8e-06, "max_input_tokens": 65536, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58211,7 +55779,6 @@ "output_cost_per_token": 1.5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_tool_choice": true, "supports_vision": false, "supports_system_messages": true, @@ -58225,7 +55792,6 @@ "output_cost_per_token": 5.8e-07, "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58239,7 +55805,6 @@ "output_cost_per_token": 1.5e-07, "max_input_tokens": 32768, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, @@ -58252,7 +55817,6 @@ "output_cost_per_token": 4e-07, "max_input_tokens": 12288, "max_output_tokens": 12288, - "max_tokens": 12288, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58266,7 +55830,6 @@ "output_cost_per_token": 4e-07, "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58280,7 +55843,6 @@ "output_cost_per_token": 1.7e-07, "max_input_tokens": 60288, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -58292,7 +55854,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 1000000, "max_output_tokens": 40000, - "max_tokens": 40000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58307,7 +55868,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 163840, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58324,7 +55884,6 @@ "output_cost_per_token": 3e-07, "max_input_tokens": 64000, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, @@ -58337,7 +55896,6 @@ "output_cost_per_token": 4e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_system_messages": true, "supports_response_schema": true }, @@ -58348,7 +55906,6 @@ "output_cost_per_token": 6.2e-07, "max_input_tokens": 65535, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_system_messages": true, "supports_response_schema": true }, @@ -58359,7 +55916,6 @@ "output_cost_per_token": 9e-08, "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_system_messages": true, "supports_reasoning": true }, @@ -58370,7 +55926,6 @@ "output_cost_per_token": 8e-07, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, @@ -58383,7 +55938,6 @@ "output_cost_per_token": 7.4e-07, "max_input_tokens": 8192, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -58395,7 +55949,6 @@ "output_cost_per_token": 8e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true @@ -58407,7 +55960,6 @@ "output_cost_per_token": 8.5e-07, "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true @@ -58419,7 +55971,6 @@ "output_cost_per_token": 5.9e-07, "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_vision": true, "supports_system_messages": true }, @@ -58430,7 +55981,6 @@ "output_cost_per_token": 1.4e-07, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -58442,7 +55992,6 @@ "output_cost_per_token": 8e-07, "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_vision": true, "supports_system_messages": true }, @@ -58453,7 +56002,6 @@ "output_cost_per_token": 1.48e-06, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58466,7 +56014,6 @@ "output_cost_per_token": 2.8e-07, "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_system_messages": true, "supports_reasoning": true }, @@ -58477,7 +56024,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -58489,7 +56035,6 @@ "output_cost_per_token": 7e-08, "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-424b-a47b": { @@ -58499,7 +56044,6 @@ "output_cost_per_token": 1.25e-06, "max_input_tokens": 123000, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true @@ -58511,7 +56055,6 @@ "output_cost_per_token": 1.1e-06, "max_input_tokens": 123000, "max_output_tokens": 12000, - "max_tokens": 12000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -58523,7 +56066,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 160000, "max_output_tokens": 160000, - "max_tokens": 160000, "supports_system_messages": true }, "novita/qwen/qwen3-32b-fp8": { @@ -58533,7 +56075,6 @@ "output_cost_per_token": 4.5e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true }, @@ -58544,7 +56085,6 @@ "output_cost_per_token": 4.5e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "supports_function_calling": true, @@ -58557,7 +56097,6 @@ "output_cost_per_token": 2e-07, "max_input_tokens": 98304, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_vision": true, "supports_system_messages": true }, @@ -58568,7 +56107,6 @@ "output_cost_per_token": 1.3e-06, "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58581,7 +56119,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58596,7 +56133,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 8192, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58609,7 +56145,6 @@ "output_cost_per_token": 9e-08, "max_input_tokens": 4096, "max_output_tokens": 3200, - "max_tokens": 3200, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-28b-a3b-thinking": { @@ -58619,7 +56154,6 @@ "output_cost_per_token": 3.9e-07, "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58635,7 +56169,6 @@ "output_cost_per_token": 5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58650,7 +56183,6 @@ "output_cost_per_token": 8.5e-07, "max_input_tokens": 131072, "max_output_tokens": 98304, - "max_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58666,7 +56198,6 @@ "output_cost_per_token": 7e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58681,7 +56212,6 @@ "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58696,7 +56226,6 @@ "output_cost_per_token": 9.7e-07, "max_input_tokens": 65536, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58713,7 +56242,6 @@ "output_cost_per_token": 9.7e-07, "max_input_tokens": 65536, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58730,7 +56258,6 @@ "output_cost_per_token": 7.5e-07, "max_input_tokens": 16384, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-28b-a3b": { @@ -58740,7 +56267,6 @@ "output_cost_per_token": 5.6e-07, "max_input_tokens": 30000, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58755,7 +56281,6 @@ "output_cost_per_token": 2.8e-07, "max_input_tokens": 120000, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58768,7 +56293,6 @@ "output_cost_per_token": 1.38e-07, "max_input_tokens": 128000, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true }, @@ -58779,7 +56303,6 @@ "output_cost_per_token": 3e-08, "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_system_messages": true, "supports_reasoning": true, "supports_function_calling": true, @@ -58792,7 +56315,6 @@ "output_cost_per_token": 7e-08, "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58806,7 +56328,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 32768, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58819,7 +56340,6 @@ "output_cost_per_token": 1.48e-06, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58831,8 +56351,7 @@ "input_cost_per_token": 7e-08, "output_cost_per_token": 0, "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768 + "max_output_tokens": 32768 }, "novita/qwen/qwen3-embedding-8b": { "litellm_provider": "novita", @@ -58840,8 +56359,7 @@ "input_cost_per_token": 7e-08, "output_cost_per_token": 0, "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096 + "max_output_tokens": 4096 }, "novita/baai/bge-m3": { "litellm_provider": "novita", @@ -58849,8 +56367,7 @@ "input_cost_per_token": 1e-08, "output_cost_per_token": 1e-08, "max_input_tokens": 8192, - "max_output_tokens": 96000, - "max_tokens": 96000 + "max_output_tokens": 96000 }, "novita/qwen/qwen3-reranker-8b": { "litellm_provider": "novita", @@ -58858,8 +56375,7 @@ "input_cost_per_token": 5e-08, "output_cost_per_token": 5e-08, "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096 + "max_output_tokens": 4096 }, "novita/baai/bge-reranker-v2-m3": { "litellm_provider": "novita", @@ -58867,11 +56383,9 @@ "input_cost_per_token": 1e-08, "output_cost_per_token": 1e-08, "max_input_tokens": 8000, - "max_output_tokens": 8000, - "max_tokens": 8000 + "max_output_tokens": 8000 }, "llamagate/llama-3.1-8b": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, @@ -58882,7 +56396,6 @@ "supports_response_schema": true }, "llamagate/llama-3.2-3b": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, @@ -58893,7 +56406,6 @@ "supports_response_schema": true }, "llamagate/mistral-7b-v0.3": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -58904,7 +56416,6 @@ "supports_response_schema": true }, "llamagate/qwen3-8b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, @@ -58915,7 +56426,6 @@ "supports_response_schema": true }, "llamagate/dolphin3-8b": { - "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 8e-08, @@ -58926,7 +56436,6 @@ "supports_response_schema": true }, "llamagate/deepseek-r1-8b": { - "max_tokens": 16384, "max_input_tokens": 65536, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, @@ -58938,7 +56447,6 @@ "supports_reasoning": true }, "llamagate/deepseek-r1-7b-qwen": { - "max_tokens": 16384, "max_input_tokens": 131072, "max_output_tokens": 16384, "input_cost_per_token": 8e-08, @@ -58950,7 +56458,6 @@ "supports_reasoning": true }, "llamagate/openthinker-7b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 8e-08, @@ -58962,7 +56469,6 @@ "supports_reasoning": true }, "llamagate/qwen2.5-coder-7b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 6e-08, @@ -58973,7 +56479,6 @@ "supports_response_schema": true }, "llamagate/deepseek-coder-6.7b": { - "max_tokens": 4096, "max_input_tokens": 16384, "max_output_tokens": 4096, "input_cost_per_token": 6e-08, @@ -58984,7 +56489,6 @@ "supports_response_schema": true }, "llamagate/codellama-7b": { - "max_tokens": 4096, "max_input_tokens": 16384, "max_output_tokens": 4096, "input_cost_per_token": 6e-08, @@ -58995,7 +56499,6 @@ "supports_response_schema": true }, "llamagate/qwen3-vl-8b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 1.5e-07, @@ -59007,7 +56510,6 @@ "supports_vision": true }, "llamagate/llava-7b": { - "max_tokens": 2048, "max_input_tokens": 4096, "max_output_tokens": 2048, "input_cost_per_token": 1e-07, @@ -59018,7 +56520,6 @@ "supports_vision": true }, "llamagate/gemma3-4b": { - "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, @@ -59030,7 +56531,6 @@ "supports_vision": true }, "llamagate/nomic-embed-text": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 2e-08, "output_cost_per_token": 0, @@ -59038,7 +56538,6 @@ "mode": "embedding" }, "llamagate/qwen3-embedding-8b": { - "max_tokens": 40960, "max_input_tokens": 40960, "input_cost_per_token": 2e-08, "output_cost_per_token": 0, @@ -59046,7 +56545,6 @@ "mode": "embedding" }, "libertai/hermes-3-8b-tee": { - "max_tokens": 16000, "max_input_tokens": 16000, "max_output_tokens": 16000, "input_cost_per_token": 1.5e-07, @@ -59060,7 +56558,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/gemma-4-31b-it": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -59074,7 +56571,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/gemma-4-31b-it-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -59089,7 +56585,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-27b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -59103,7 +56598,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-27b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -59118,7 +56612,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-35b-a3b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -59132,7 +56625,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-35b-a3b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -59147,7 +56639,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.5-122b-a10b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.5e-07, @@ -59161,7 +56652,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.5-122b-a10b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.5e-07, @@ -59176,7 +56666,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/deepseek-v4-flash": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 2.5e-07, @@ -59190,7 +56679,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/deepseek-v4-flash-thinking": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 2.5e-07, @@ -59205,7 +56693,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/bge-m3": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -59221,7 +56708,6 @@ "litellm_provider": "sarvam", "max_input_tokens": 8192, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0, "supports_reasoning": true @@ -59297,7 +56783,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { @@ -59325,7 +56810,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { @@ -59357,7 +56841,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -59467,7 +56950,6 @@ "litellm_provider": "gemini", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_token": 0.0, @@ -59488,7 +56970,6 @@ "litellm_provider": "gemini", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_token": 0.0, @@ -59511,7 +56992,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -59537,7 +57017,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -59564,7 +57043,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -59599,7 +57077,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -59634,7 +57111,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -59668,7 +57144,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -59701,7 +57176,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -59729,7 +57203,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -59758,7 +57231,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -59796,7 +57268,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -59833,7 +57304,6 @@ "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, @@ -59860,7 +57330,6 @@ "litellm_provider": "gemini", "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, @@ -59885,7 +57354,6 @@ "litellm_provider": "gemini", "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, @@ -59905,7 +57373,6 @@ "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, @@ -59925,7 +57392,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -59984,7 +57450,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -60044,7 +57509,6 @@ "litellm_provider": "gemini", "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, @@ -60106,7 +57570,6 @@ "litellm_provider": "gemini", "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, @@ -60167,7 +57630,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -60218,7 +57680,6 @@ "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, @@ -60257,7 +57718,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -60299,7 +57759,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token_batches": 3e-07, "output_cost_per_token_priority": 1.05e-06, @@ -60325,7 +57784,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "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, @@ -60351,7 +57809,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token_batches": 3e-07, "output_cost_per_token_priority": 1.05e-06, @@ -60375,7 +57832,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token_batches": 1e-07, "output_cost_per_token_priority": 3.5e-07, @@ -60405,7 +57861,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -60449,7 +57904,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -60484,7 +57938,6 @@ "litellm_provider": "bedrock_mantle", "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, @@ -60520,7 +57973,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -60560,7 +58012,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -60601,7 +58052,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ @@ -60638,7 +58088,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ @@ -60675,7 +58124,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ @@ -60712,7 +58160,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ @@ -60749,7 +58196,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ @@ -60783,7 +58229,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "supported_modalities": [ @@ -60815,7 +58260,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "supported_modalities": [ @@ -60847,7 +58291,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", "supported_modalities": [ @@ -60879,7 +58322,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", "supported_modalities": [ @@ -60914,7 +58356,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ @@ -60955,7 +58396,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "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, @@ -60996,7 +58436,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -61035,7 +58474,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -61082,7 +58520,6 @@ "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, @@ -61123,7 +58560,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -61162,7 +58598,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -61207,7 +58642,6 @@ "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, @@ -61247,7 +58681,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -61282,7 +58715,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -61320,7 +58752,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -61355,7 +58786,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -61395,7 +58825,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -61435,7 +58864,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -61470,7 +58898,6 @@ "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, @@ -61496,7 +58923,6 @@ "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, @@ -61522,7 +58948,6 @@ "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, @@ -61552,7 +58977,6 @@ "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, @@ -61580,7 +59004,6 @@ "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, @@ -61605,7 +59028,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -61636,7 +59058,6 @@ "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": { @@ -61674,7 +59095,6 @@ "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": { @@ -61722,7 +59142,6 @@ "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, @@ -61750,7 +59169,6 @@ "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, @@ -61765,7 +59183,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -61805,7 +59222,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4.3125e-06, "source": "https://www.volcengine.com/docs/82379/1544106", @@ -61821,7 +59237,6 @@ "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", @@ -61839,7 +59254,6 @@ "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", @@ -61856,7 +59270,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.15625e-06, "source": "https://www.volcengine.com/docs/82379/1544106", @@ -61870,7 +59283,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -61908,7 +59320,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -61946,7 +59357,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -62041,7 +59451,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, @@ -62059,7 +59468,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, @@ -62080,7 +59488,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -62110,7 +59517,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -62132,7 +59538,6 @@ } }, "snowflake/claude-sonnet-4-5": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -62150,7 +59555,6 @@ "snowflake/claude-sonnet-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -62166,7 +59570,6 @@ "prompt_cache_min_tokens": 1024 }, "snowflake/claude-4-sonnet": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -62182,7 +59585,6 @@ "prompt_cache_min_tokens": 1024 }, "snowflake/claude-4-opus": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 5e-06, @@ -62199,7 +59601,6 @@ "prompt_cache_min_tokens": 1024 }, "snowflake/claude-haiku-4-5": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 1e-06, @@ -62215,7 +59616,6 @@ "prompt_cache_min_tokens": 4096 }, "snowflake/claude-3-7-sonnet": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -62231,7 +59631,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-4.1": { - "max_tokens": 16384, "max_input_tokens": 300000, "max_output_tokens": 16384, "input_cost_per_token": 2e-06, @@ -62246,7 +59645,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-5": { - "max_tokens": 16384, "max_input_tokens": 300000, "max_output_tokens": 16384, "input_cost_per_token": 1.25e-06, @@ -62262,7 +59660,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-5-mini": { - "max_tokens": 16384, "max_input_tokens": 1000000, "max_output_tokens": 16384, "input_cost_per_token": 3e-07, @@ -62274,7 +59671,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-5-nano": { - "max_tokens": 16384, "max_input_tokens": 5000000, "max_output_tokens": 16384, "input_cost_per_token": 1.5e-07, @@ -62286,7 +59682,6 @@ "supports_response_schema": true }, "snowflake/llama4-maverick": { - "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 2.4e-07, @@ -62297,7 +59692,6 @@ "supports_system_messages": true }, "snowflake/snowflake-arctic-embed-l-v2.0": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 7e-08, "output_cost_per_token": 0.0, @@ -62305,7 +59699,6 @@ "mode": "embedding" }, "snowflake/snowflake-arctic-embed-m-v2.0": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 7e-08, "output_cost_per_token": 0.0, @@ -62315,7 +59708,7 @@ "soniox/stt-async-v4": { "litellm_provider": "soniox", "max_output_tokens": 8000, - "max_tokens": 8000, + "max_input_tokens": 8000, "input_cost_per_second": 0.0, "output_cost_per_second": 2.77778e-05, "mode": "audio_transcription", @@ -62328,7 +59721,7 @@ "soniox/stt-async-v5": { "litellm_provider": "soniox", "max_output_tokens": 8000, - "max_tokens": 8000, + "max_input_tokens": 8000, "input_cost_per_second": 0.0, "output_cost_per_second": 2.77778e-05, "mode": "audio_transcription", @@ -62505,7 +59898,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -62559,7 +59951,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -62613,7 +60004,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -62667,7 +60057,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 2.2e-08, @@ -62721,7 +60110,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -62775,7 +60163,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -62829,7 +60216,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -62883,7 +60269,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 2.2e-08, @@ -62937,7 +60322,6 @@ "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", @@ -62963,7 +60347,6 @@ "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://www.tencentcloud.com/document/product/1300/78937", @@ -62989,7 +60372,6 @@ "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, @@ -63044,7 +60426,6 @@ "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, @@ -63099,7 +60480,6 @@ "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", @@ -63124,7 +60504,6 @@ "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", @@ -63149,7 +60528,6 @@ "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", @@ -63173,7 +60551,6 @@ "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", @@ -63197,7 +60574,6 @@ "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", @@ -63221,7 +60597,6 @@ "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", @@ -63245,7 +60620,6 @@ "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", @@ -63269,7 +60643,6 @@ "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", @@ -63336,7 +60709,6 @@ "source": "https://docs.devin.ai/desktop/models" }, "pinstripes/ps/glm-4.5-air": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.25e-07, @@ -63349,7 +60721,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3.6-35b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.4e-07, @@ -63362,7 +60733,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3-30b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-08, @@ -63375,7 +60745,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3-coder-30b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-07, @@ -63388,7 +60757,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/deepseek-v4-flash": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1e-07, @@ -63401,7 +60769,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/minimax-m2.7": { - "max_tokens": 1000192, "max_input_tokens": 1000192, "max_output_tokens": 1000192, "input_cost_per_token": 2.55e-07, @@ -63418,7 +60785,6 @@ "litellm_provider": "darkbloom", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.65e-07, "source": "https://www.darkbloom.dev/", @@ -63435,7 +60801,6 @@ "litellm_provider": "darkbloom", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7e-08, "source": "https://www.darkbloom.dev/", @@ -63455,7 +60820,6 @@ "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, @@ -63482,7 +60846,6 @@ "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, @@ -63511,7 +60874,6 @@ "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.x.ai/v1/language-models", @@ -63584,7 +60946,6 @@ "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, - "max_tokens": 2000, "mode": "realtime", "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ @@ -63609,7 +60970,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -63653,7 +61013,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -63696,7 +61055,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "prompt_cache_min_tokens": 512, @@ -63732,7 +61090,6 @@ "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": { @@ -63767,7 +61124,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ @@ -63788,7 +61144,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5", @@ -63878,7 +61233,6 @@ "mode": "chat", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, @@ -63977,7 +61331,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 2.1e-05, "output_cost_per_token": 2.1e-05, @@ -64006,7 +61359,6 @@ "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", @@ -64031,7 +61383,6 @@ "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", @@ -64112,7 +61463,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64122,7 +61472,6 @@ "input_cost_per_token": 5e-08, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560, @@ -64132,7 +61481,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64142,7 +61490,6 @@ "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64152,7 +61499,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64162,7 +61508,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64172,7 +61517,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 120000, - "max_tokens": 120000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64182,7 +61526,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64198,7 +61541,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -64217,7 +61559,6 @@ "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, @@ -64237,7 +61578,6 @@ "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, @@ -64257,7 +61597,7 @@ "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -64275,7 +61615,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_priority": 1.875e-05, @@ -64300,7 +61639,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -64319,7 +61657,6 @@ "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, @@ -64339,7 +61676,6 @@ "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, @@ -64359,7 +61695,7 @@ "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -64376,7 +61712,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -64393,7 +61728,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -64411,7 +61745,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_priority": 1.875e-05, @@ -64433,7 +61766,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "reasoning_effort_levels": [ @@ -64456,7 +61788,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "output_cost_per_token_priority": 2.8125e-05, @@ -64498,7 +61829,6 @@ "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, @@ -64518,7 +61848,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_priority": 2.5e-07, @@ -64538,7 +61867,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, "output_cost_per_token_priority": 3e-06, @@ -64558,7 +61886,6 @@ "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, @@ -64593,7 +61920,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_priority": 2.5e-07, @@ -64613,7 +61939,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, "output_cost_per_token_priority": 3e-06, @@ -64648,7 +61973,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -64665,7 +61989,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -64681,7 +62004,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "reasoning_effort_levels": [ @@ -64704,7 +62026,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "output_cost_per_token_priority": 2.8125e-05, @@ -64726,7 +62047,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -64743,7 +62063,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://novita.ai/pricing", @@ -64760,7 +62079,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://novita.ai/pricing", @@ -64777,7 +62095,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 5.8e-07, "source": "https://novita.ai/pricing", @@ -64794,7 +62111,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://novita.ai/pricing", @@ -64811,7 +62127,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://novita.ai/pricing", @@ -64828,7 +62143,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -64845,7 +62159,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://novita.ai/pricing", @@ -64862,7 +62175,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://novita.ai/pricing", @@ -64878,7 +62190,6 @@ "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", @@ -64895,7 +62206,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://novita.ai/pricing", @@ -64912,7 +62222,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", @@ -64929,7 +62238,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://novita.ai/pricing", @@ -64945,7 +62253,6 @@ "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://novita.ai/pricing", @@ -64962,7 +62269,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://novita.ai/pricing", @@ -64978,7 +62284,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.6e-06, "source": "https://novita.ai/pricing", @@ -64994,7 +62299,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://novita.ai/pricing", @@ -65010,7 +62314,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.0000000000000002e-07, "source": "https://novita.ai/pricing", @@ -65026,7 +62329,6 @@ "litellm_provider": "novita", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.13e-06, "source": "https://novita.ai/pricing", @@ -65042,7 +62344,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.3600000000000004e-07, "source": "https://novita.ai/pricing", @@ -65059,7 +62360,6 @@ "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.75e-06, "source": "https://novita.ai/pricing", @@ -65076,7 +62376,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.044e-06, "source": "https://novita.ai/pricing", @@ -65092,7 +62391,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.6000000000000003e-06, "source": "https://novita.ai/pricing", @@ -65108,7 +62406,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.4e-06, "source": "https://novita.ai/pricing", @@ -65125,7 +62422,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://novita.ai/pricing", @@ -65142,7 +62438,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65159,7 +62454,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65175,7 +62469,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", @@ -65190,7 +62483,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", @@ -65206,7 +62498,6 @@ "litellm_provider": "novita", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65223,7 +62514,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", @@ -65240,7 +62530,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://novita.ai/pricing", @@ -65256,7 +62545,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://novita.ai/pricing", @@ -65271,7 +62559,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", @@ -65286,7 +62573,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://novita.ai/pricing", @@ -65301,7 +62587,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.6000000000000003e-06, "source": "https://novita.ai/pricing", @@ -65317,7 +62602,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", @@ -65334,7 +62618,6 @@ "litellm_provider": "novita", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", @@ -65350,7 +62633,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://novita.ai/pricing", @@ -65364,7 +62646,6 @@ "litellm_provider": "novita", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://novita.ai/pricing", @@ -65376,7 +62657,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://novita.ai/pricing", @@ -65393,7 +62673,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65410,7 +62689,6 @@ "litellm_provider": "novita", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", @@ -65426,7 +62704,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.4850000000000002e-06, "source": "https://novita.ai/pricing", @@ -65441,7 +62718,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 8.900000000000001e-07, "source": "https://api.novita.ai/v3/openai/models", @@ -65454,7 +62730,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65468,7 +62743,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8.900000000000001e-07, "source": "https://api.novita.ai/v3/openai/models", @@ -65481,7 +62755,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65495,7 +62768,6 @@ "litellm_provider": "novita", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.66e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65509,7 +62781,6 @@ "litellm_provider": "novita", "max_input_tokens": 131000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2e-08, "source": "https://api.novita.ai/v3/openai/models", @@ -65518,7 +62789,7 @@ }, "wandb/deepseek-ai/DeepSeek-V4-Flash": { "supports_reasoning": true, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1049000, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, @@ -65532,7 +62803,7 @@ }, "wandb/deepseek-ai/DeepSeek-V4-Flash-0731": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 2.8e-07, @@ -65545,7 +62816,7 @@ }, "wandb/deepseek-ai/DeepSeek-V4-Pro": { "supports_reasoning": true, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1049000, "input_cost_per_token": 1.15e-06, "output_cost_per_token": 2.55e-06, @@ -65559,7 +62830,7 @@ }, "wandb/google/gemma-4-31B-it": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3.4e-07, @@ -65570,7 +62841,7 @@ }, "wandb/ibm-granite/granite-4.1-8b": { "deprecation_date": "2026-10-05", - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, @@ -65581,7 +62852,7 @@ }, "wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": { "deprecation_date": "2026-10-05", - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, @@ -65592,7 +62863,7 @@ }, "wandb/meta-llama/Llama-3.1-70B-Instruct": { "deprecation_date": "2026-10-05", - "max_tokens": 128000, + "max_output_tokens": 128000, "max_input_tokens": 131000, "input_cost_per_token": 8e-07, "output_cost_per_token": 8e-07, @@ -65603,7 +62874,7 @@ }, "wandb/MiniMaxAI/MiniMax-M3": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 2.3e-07, "output_cost_per_token": 9.6e-07, @@ -65616,7 +62887,7 @@ }, "wandb/moonshotai/Kimi-K2.7-Code": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 7.1e-07, "output_cost_per_token": 3.5e-06, @@ -65629,7 +62900,7 @@ }, "wandb/moonshotai/Kimi-K2.6": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 6.5e-07, "output_cost_per_token": 3.41e-06, @@ -65642,7 +62913,7 @@ }, "wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 7e-08, "output_cost_per_token": 2e-07, @@ -65655,7 +62926,7 @@ }, "wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.15e-06, @@ -65668,7 +62939,7 @@ }, "wandb/OpenPipe/Qwen3-14B-Instruct": { "deprecation_date": "2026-10-05", - "max_tokens": 32768, + "max_output_tokens": 32768, "max_input_tokens": 32800, "input_cost_per_token": 5e-08, "output_cost_per_token": 2.2e-07, @@ -65679,7 +62950,7 @@ }, "wandb/Qwen/Qwen3.8-27B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 4e-07, "output_cost_per_token": 3e-06, @@ -65692,7 +62963,7 @@ }, "wandb/Qwen/Qwen3.6-35B-A3B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.25e-06, @@ -65703,7 +62974,7 @@ }, "wandb/Qwen/Qwen3.6-27B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 6e-07, "output_cost_per_token": 3.6e-06, @@ -65718,7 +62989,7 @@ "wandb/Qwen/Qwen3.5-35B-A3B": { "deprecation_date": "2026-10-05", "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.25e-06, @@ -65729,7 +63000,7 @@ }, "wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": { "deprecation_date": "2026-10-05", - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, @@ -65762,7 +63033,7 @@ }, "wandb/zai-org/GLM-5.2": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 1049000, "input_cost_per_token": 7.6e-07, "output_cost_per_token": 2.42e-06, @@ -65774,7 +63045,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "deepinfra/openai/gpt-oss-120b-Turbo": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, @@ -65788,7 +63059,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M2.7": { - "max_tokens": 196608, + "max_output_tokens": 196608, "max_input_tokens": 196608, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1e-06, @@ -65804,7 +63075,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-27B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4e-07, "output_cost_per_token": 3e-06, @@ -65820,7 +63091,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it-Ultra": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2.7e-07, "output_cost_per_token": 7.6e-07, @@ -65834,7 +63105,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.5": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 2.25e-06, @@ -65850,7 +63121,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.7-Flash": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 6e-08, "output_cost_per_token": 4e-07, @@ -65866,7 +63137,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.6": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 5e-07, "output_cost_per_token": 2e-06, @@ -65885,7 +63156,7 @@ "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 1024, @@ -65899,7 +63170,7 @@ "supports_vision": true }, "deepinfra/anthropic/claude-sonnet-4-6": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, @@ -65915,7 +63186,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.5-flash": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 1.5e-06, "output_cost_per_token": 9e-06, @@ -65930,7 +63201,7 @@ "supports_audio_input": true }, "deepinfra/XiaomiMiMo/MiMo-V2.5": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4e-07, "output_cost_per_token": 2e-06, @@ -65946,7 +63217,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Max": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, @@ -65961,7 +63232,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it-turbo": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 9e-08, "output_cost_per_token": 3.4e-07, @@ -65976,7 +63247,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/thinkingmachines/Inkling-Small": { - "max_tokens": 524288, + "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 1.2e-06, @@ -65992,7 +63263,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-models/Muse-Glimmer-30B": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, @@ -66008,7 +63279,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Max-Thinking": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, @@ -66023,7 +63294,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 8.8e-07, @@ -66038,7 +63309,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, @@ -66051,7 +63322,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-27B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2.6e-07, "output_cost_per_token": 2.6e-06, @@ -66065,7 +63336,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.6-35B-A3B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1e-07, "output_cost_per_token": 9.5e-07, @@ -66079,7 +63350,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/Nemotron-Content-Safety-3.5": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -66092,7 +63363,7 @@ "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 512, @@ -66106,7 +63377,7 @@ "supports_vision": true }, "deepinfra/thinkingmachines/Inkling": { - "max_tokens": 524288, + "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 9.5e-07, "output_cost_per_token": 4.05e-06, @@ -66122,7 +63393,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.6": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 3.5e-06, @@ -66138,7 +63409,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1.3e-06, "output_cost_per_token": 2.6e-06, @@ -66153,7 +63424,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.7-Max": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 2.5e-06, "output_cost_per_token": 7.5e-06, @@ -66168,7 +63439,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-mini": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1e-07, "output_cost_per_token": 4e-07, @@ -66184,7 +63455,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-2.4T-A95B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, @@ -66200,7 +63471,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M3": { - "max_tokens": 524288, + "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 2.8e-07, "output_cost_per_token": 1.1e-06, @@ -66216,7 +63487,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.1-flash-lite": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.5e-06, @@ -66231,7 +63502,7 @@ "supports_audio_input": true }, "deepinfra/google/gemini-3.7-flash": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 3.75e-06, @@ -66247,7 +63518,7 @@ "supports_audio_input": true }, "deepinfra/inclusionAI/Ling-3.0-flash": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 6e-08, "output_cost_per_token": 1.8e-07, @@ -66263,7 +63534,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/stepfun-ai/Step-3.7-Flash": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 1.15e-06, @@ -66277,7 +63548,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-35B-A3B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 1e-06, @@ -66293,7 +63564,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-1.8": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, @@ -66309,7 +63580,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/tencent/Hy3": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 5.8e-07, @@ -66325,7 +63596,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-code": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, @@ -66341,7 +63612,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-pro": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, @@ -66357,7 +63628,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 6e-07, "output_cost_per_token": 2.08e-06, @@ -66373,7 +63644,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 5e-08, "output_cost_per_token": 2e-07, @@ -66388,7 +63659,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.7-Code": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 6.8e-07, "output_cost_per_token": 3.4e-06, @@ -66407,7 +63678,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1e-05, "prompt_cache_min_tokens": 1024, @@ -66421,7 +63692,7 @@ "supports_vision": true }, "deepinfra/Qwen/Qwen3.5-397B-A17B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 3e-06, @@ -66437,7 +63708,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 8e-08, "output_cost_per_token": 1.8e-07, @@ -66453,7 +63724,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-E4B-it": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-08, "output_cost_per_token": 1e-07, @@ -66466,7 +63737,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.2": { - "max_tokens": 163840, + "max_output_tokens": 163840, "max_input_tokens": 163840, "input_cost_per_token": 2.6e-07, "output_cost_per_token": 3.8e-07, @@ -66481,7 +63752,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-Max": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.65e-06, "output_cost_per_token": 4.951e-06, @@ -66499,7 +63770,7 @@ "input_cost_per_token": 1e-05, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 5e-05, "prompt_cache_min_tokens": 512, @@ -66514,7 +63785,7 @@ "thinking_always_on": true }, "deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.2e-06, @@ -66530,7 +63801,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-122B-A10B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2.9e-07, "output_cost_per_token": 2.4e-06, @@ -66544,7 +63815,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5.1": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 1.05e-06, "output_cost_per_token": 3.5e-06, @@ -66560,7 +63831,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Pro": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1.3e-06, "output_cost_per_token": 2.6e-06, @@ -66575,7 +63846,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 8.5e-08, "output_cost_per_token": 4e-07, @@ -66589,7 +63860,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5.2": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 2.4e-06, @@ -66605,7 +63876,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K3": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 2.85e-06, "output_cost_per_token": 1.425e-05, @@ -66623,7 +63894,7 @@ "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 2048, @@ -66637,7 +63908,7 @@ "supports_vision": true }, "deepinfra/Qwen/Qwen3.6-27B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 3.2e-07, "output_cost_per_token": 3.2e-06, @@ -66651,7 +63922,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-26B-A4B-it": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 7e-08, "output_cost_per_token": 3.4e-07, @@ -66665,7 +63936,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.1-pro": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 2e-06, "output_cost_per_token": 1.2e-05, @@ -66680,7 +63951,7 @@ "supports_audio_input": true }, "deepinfra/XiaomiMiMo/MiMo-V2.5-Pro": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1e-06, "output_cost_per_token": 3e-06, @@ -66696,7 +63967,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-haiku-4-5": { - "max_tokens": 200000, + "max_output_tokens": 200000, "max_input_tokens": 200000, "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, @@ -66711,7 +63982,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Flash": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 9e-08, "output_cost_per_token": 1.8e-07, @@ -66727,7 +63998,6 @@ "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, @@ -66744,7 +64014,6 @@ "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, @@ -66761,7 +64030,7 @@ "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash-1017" }, "deepinfra/openai/gpt-oss-120b-Ultra": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 9.5e-07, @@ -66775,7 +64044,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-9B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1e-07, "output_cost_per_token": 1.5e-07, @@ -66788,7 +64057,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo": { - "max_tokens": 196608, + "max_output_tokens": 196608, "max_input_tokens": 196608, "input_cost_per_token": 3.8e-07, "output_cost_per_token": 1.7e-06, @@ -66804,7 +64073,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.7": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 4e-07, "output_cost_per_token": 1.75e-06, @@ -66820,7 +64089,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 3.8e-07, @@ -66839,7 +64108,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -66874,7 +64142,6 @@ "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, @@ -66902,7 +64169,6 @@ "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, @@ -66930,7 +64196,6 @@ "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, @@ -67206,7 +64471,6 @@ "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, @@ -67233,7 +64497,6 @@ "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, @@ -67260,7 +64523,6 @@ "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, @@ -67291,7 +64553,6 @@ "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, @@ -67319,7 +64580,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://console.groq.com/docs/model/qwen/qwen3.8-27b", @@ -67335,7 +64595,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -67356,7 +64615,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -67377,7 +64635,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -67398,7 +64655,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ @@ -67419,7 +64675,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", @@ -67434,7 +64689,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", @@ -67449,7 +64703,6 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://mistral.ai/news/devstral-2-vibe-cli", @@ -67550,7 +64803,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5", @@ -67566,7 +64818,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, @@ -67585,7 +64836,6 @@ "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, @@ -67604,7 +64854,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, @@ -67623,7 +64872,6 @@ "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, @@ -67639,7 +64887,7 @@ "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -67681,7 +64929,7 @@ "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -67698,7 +64946,7 @@ "input_cost_per_token_priority": 1.875e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_priority": 6.25e-07, @@ -67716,7 +64964,7 @@ "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, "output_cost_per_token_priority": 9.375e-07, @@ -67733,7 +64981,7 @@ "input_cost_per_token_priority": 1.875e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_priority": 6.25e-07, @@ -67751,7 +64999,7 @@ "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, "output_cost_per_token_priority": 9.375e-07, @@ -67769,7 +65017,7 @@ "input_cost_per_token_priority": 1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.05e-06, "output_cost_per_token_priority": 4.05e-06, @@ -67785,7 +65033,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 40960, "max_output_tokens": 40960, - "max_tokens": 40960, "mode": "embedding", "source": "https://api.fireworks.ai/v1/serverless/models" }, @@ -67808,7 +65055,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://api.together.ai/v1/models" @@ -67868,7 +65115,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 131072, "max_output_tokens": 40960, - "max_tokens": 40960, "mode": "chat", "output_cost_per_token": 1.49e-06, "source": "https://api.cerebras.ai/public/v1/models/gemma-4-31b", @@ -67894,7 +65140,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", @@ -67908,7 +65153,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", @@ -67924,7 +65168,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 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'", @@ -67947,7 +65190,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, @@ -67989,7 +65231,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -68004,7 +65245,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.1e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -68019,7 +65259,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -68034,7 +65273,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.25e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -68050,7 +65288,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -68067,7 +65304,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -68080,7 +65316,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-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'", @@ -68155,7 +65390,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -68173,7 +65407,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "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", @@ -68189,7 +65422,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "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", @@ -68204,7 +65436,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -68222,7 +65453,6 @@ "litellm_provider": "bedrock", "max_input_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", @@ -68242,7 +65472,6 @@ "litellm_provider": "bedrock", "max_input_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", @@ -68267,7 +65496,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, @@ -68306,7 +65534,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, @@ -68344,7 +65571,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, @@ -68381,7 +65607,6 @@ "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, @@ -68419,7 +65644,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, @@ -68454,7 +65678,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -68472,7 +65695,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "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", @@ -68488,7 +65710,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "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", @@ -68503,7 +65724,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -68521,7 +65741,6 @@ "litellm_provider": "bedrock", "max_input_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", @@ -68541,7 +65760,6 @@ "litellm_provider": "bedrock", "max_input_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", @@ -68566,7 +65784,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, @@ -68600,7 +65817,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, @@ -68633,7 +65849,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, @@ -68665,7 +65880,6 @@ "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, @@ -68698,7 +65912,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, @@ -68727,7 +65940,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -68763,7 +65975,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -68799,7 +66010,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -68830,7 +66040,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1048576, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -68854,7 +66063,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -68873,7 +66081,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "use_openai_responses_path": true, "supported_endpoints": [ @@ -68892,7 +66099,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "use_openai_responses_path": true, "supported_endpoints": [ @@ -68911,7 +66117,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "use_openai_responses_path": true, "supported_endpoints": [ @@ -68931,7 +66136,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "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": [ @@ -68951,7 +66155,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "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": [ @@ -68974,7 +66177,6 @@ "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, @@ -69010,7 +66212,6 @@ "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, @@ -69039,7 +66240,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -69072,7 +66272,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -69092,7 +66291,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "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": [ @@ -69112,7 +66310,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "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": [ @@ -69136,7 +66333,6 @@ "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, @@ -69158,7 +66354,6 @@ "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, @@ -69180,7 +66375,6 @@ "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, @@ -69202,7 +66396,6 @@ "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, @@ -69225,7 +66418,6 @@ "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, @@ -69247,7 +66439,6 @@ "litellm_provider": "bedrock_mantle", "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, @@ -69268,7 +66459,6 @@ "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, @@ -69290,7 +66480,6 @@ "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, @@ -69309,7 +66498,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.375e-05, "supported_endpoints": [ @@ -69343,7 +66531,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.05e-06, "supports_prompt_caching": true, @@ -69356,7 +66543,6 @@ "input_cost_per_token": 1.63e-07, "litellm_provider": "azure", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -69364,7 +66550,6 @@ "input_cost_per_token": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -69395,7 +66580,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_image": 0.04, "output_cost_per_token": 0, @@ -69420,7 +66604,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -69445,7 +66628,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -69470,7 +66652,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/models/lyria-realtime-exp", @@ -69843,7 +67024,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://inference.baseten.co/v1/models", @@ -69867,7 +67047,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://inference.baseten.co/v1/models", @@ -69892,7 +67071,7 @@ "output_cost_per_token": 1.5e-07, "source": "https://api.together.ai/v1/models", "max_input_tokens": 128000, - "max_tokens": 128000 + "max_output_tokens": 128000 }, "vertex_ai/gemini-2.5-flash-native-audio": { "deprecation_date": "2026-12-13", @@ -69953,7 +67132,7 @@ "input_cost_per_token": 1.5e-06, "litellm_provider": "vertex_ai", "max_output_tokens": 57920, - "max_tokens": 57920, + "max_input_tokens": 57920, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -70016,7 +67195,7 @@ "output_cost_per_token": 3.5e-06, "source": "https://api.together.ai/v1/models", "max_input_tokens": 4096, - "max_tokens": 4096 + "max_output_tokens": 4096 }, "together_ai/meta-llama/Llama-3.2-1B-Instruct": { "input_cost_per_token": 6e-08, @@ -70025,7 +67204,7 @@ "output_cost_per_token": 6e-08, "source": "https://api.together.ai/v1/models", "max_input_tokens": 131072, - "max_tokens": 131072 + "max_output_tokens": 131072 }, "together_ai/meta-llama/Llama-3.2-3B-Instruct": { "input_cost_per_token": 6e-08, @@ -70034,7 +67213,7 @@ "output_cost_per_token": 6e-08, "source": "https://api.together.ai/v1/models", "max_input_tokens": 131072, - "max_tokens": 131072 + "max_output_tokens": 131072 }, "together_ai/Qwen/Qwen2-1.5B-Instruct": { "input_cost_per_token": 2e-08, @@ -70043,7 +67222,7 @@ "output_cost_per_token": 2e-08, "source": "https://api.together.ai/v1/models", "max_input_tokens": 32768, - "max_tokens": 32768 + "max_output_tokens": 32768 }, "together_ai/Qwen/Qwen2.5-14B-Instruct": { "input_cost_per_token": 8e-07, @@ -70052,7 +67231,7 @@ "output_cost_per_token": 8e-07, "source": "https://api.together.ai/v1/models", "max_input_tokens": 32768, - "max_tokens": 32768 + "max_output_tokens": 32768 }, "together_ai/Qwen/Qwen2.5-72B-Instruct": { "input_cost_per_token": 1.2e-06, @@ -70061,14 +67240,13 @@ "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", "max_input_tokens": 32768, - "max_tokens": 32768 + "max_output_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" @@ -70077,7 +67255,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 16384, "mode": "completion", "output_cost_per_token": 2e-07, "source": "https://api.together.xyz/v1/models" @@ -70095,7 +67273,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.together.ai/v1/models" @@ -70105,7 +67283,7 @@ "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" @@ -70115,7 +67293,7 @@ "input_cost_per_token": 9e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://api.together.ai/v1/models" @@ -70125,7 +67303,7 @@ "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" @@ -70135,7 +67313,7 @@ "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" @@ -70145,7 +67323,7 @@ "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "max_input_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://api.together.ai/v1/models" @@ -70155,7 +67333,7 @@ "input_cost_per_token": 1.95e-06, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://api.together.ai/v1/models" @@ -70165,7 +67343,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models" @@ -70175,7 +67353,7 @@ "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" @@ -70185,7 +67363,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models" @@ -70195,7 +67373,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models" @@ -70205,7 +67383,7 @@ "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models" @@ -70215,7 +67393,7 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 6.8e-07, "source": "https://api.together.ai/v1/models" @@ -70226,7 +67404,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.6e-06, "source": "https://api.together.ai/v1/models" @@ -70236,7 +67414,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models" @@ -70246,7 +67424,7 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://api.together.ai/v1/models" @@ -70256,7 +67434,7 @@ "input_cost_per_token": 1.6e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://api.together.ai/v1/models" @@ -70266,7 +67444,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.7e-06, "source": "https://api.together.ai/v1/models" @@ -70276,7 +67454,7 @@ "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "max_input_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://api.together.ai/v1/models" @@ -70286,7 +67464,7 @@ "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://api.together.ai/v1/models" @@ -70296,7 +67474,7 @@ "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 9.7e-07, "source": "https://api.together.ai/v1/models" @@ -70306,7 +67484,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://api.together.ai/v1/models" @@ -70316,7 +67494,7 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5.9e-07, "source": "https://api.together.ai/v1/models" @@ -70326,7 +67504,7 @@ "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://api.together.ai/v1/models" @@ -70336,7 +67514,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://api.together.ai/v1/models" @@ -70346,7 +67524,7 @@ "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://api.together.ai/v1/models" @@ -70356,7 +67534,7 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://api.together.ai/v1/models" @@ -70366,7 +67544,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://api.together.ai/v1/models" @@ -70376,7 +67554,7 @@ "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://api.together.ai/v1/models" @@ -70386,7 +67564,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.together.ai/v1/models" @@ -70397,7 +67575,7 @@ "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://api.together.ai/v1/models" @@ -70408,7 +67586,7 @@ "input_cost_per_token": 9.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.together.ai/v1/models" @@ -70418,7 +67596,7 @@ "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://api.together.ai/v1/models" @@ -70429,7 +67607,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 512288, - "max_tokens": 512288, + "max_output_tokens": 512288, "mode": "chat", "output_cost_per_token": 3.6e-06, "source": "https://api.together.ai/v1/models" @@ -70439,7 +67617,7 @@ "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://api.together.ai/v1/models" @@ -70449,7 +67627,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.1e-06, "source": "https://api.together.ai/v1/models" @@ -70459,7 +67637,7 @@ "input_cost_per_token": 4.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 202752, - "max_tokens": 202752, + "max_output_tokens": 202752, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models" @@ -70469,7 +67647,7 @@ "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 202752, - "max_tokens": 202752, + "max_output_tokens": 202752, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://api.together.ai/v1/models" @@ -70480,7 +67658,7 @@ "input_cost_per_token": 1.4e-06, "litellm_provider": "together_ai", "max_input_tokens": 202752, - "max_tokens": 202752, + "max_output_tokens": 202752, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models" @@ -70547,7 +67725,6 @@ "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, @@ -70720,7 +67897,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_above_272k_tokens": 9e-05, @@ -70764,7 +67940,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_above_272k_tokens": 9e-07, @@ -70813,7 +67988,6 @@ "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, @@ -70869,7 +68043,6 @@ "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, @@ -70883,7 +68056,6 @@ "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, @@ -70906,7 +68078,6 @@ "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, @@ -70920,7 +68091,6 @@ "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, @@ -70955,7 +68125,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -70977,7 +68146,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -71053,7 +68221,6 @@ "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, @@ -71266,7 +68433,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, @@ -71314,7 +68480,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "audio_transcription", "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": [ @@ -71355,7 +68520,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "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_modalities": [ @@ -71373,7 +68537,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 512000, "max_output_tokens": 65500, - "max_tokens": 65500, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71386,7 +68549,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71399,7 +68561,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 200000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71414,7 +68575,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71435,7 +68595,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71453,7 +68612,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71473,7 +68631,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71494,7 +68651,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71513,7 +68669,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71528,7 +68683,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.61333e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71557,7 +68711,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.6e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71573,7 +68726,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71587,7 +68739,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71602,7 +68753,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.84e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71617,7 +68767,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.38e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71632,7 +68781,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.411e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71648,7 +68796,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.4246e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71665,7 +68812,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.0136e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71682,7 +68828,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.411e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71699,7 +68844,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.32375e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71716,7 +68860,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 119000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.5353e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71729,7 +68872,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71746,7 +68888,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71763,7 +68904,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71780,7 +68920,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71797,7 +68936,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.499999e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71815,7 +68953,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.75e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71832,7 +68969,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 3.9998e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71844,7 +68980,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 3.9998e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71857,7 +68992,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 7.889e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71872,7 +69006,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.9438e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71887,7 +69020,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.9438e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71903,7 +69035,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 200000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.09848e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71917,7 +69048,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71933,7 +69063,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71950,7 +69079,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71967,7 +69095,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71984,7 +69111,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72001,7 +69127,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://aihubmix.com/api/v1/models", @@ -72017,7 +69142,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00018, "source": "https://aihubmix.com/api/v1/models", @@ -72034,7 +69158,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72051,7 +69174,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "source": "https://aihubmix.com/api/v1/models", @@ -72068,7 +69190,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://aihubmix.com/api/v1/models", @@ -72084,7 +69205,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://aihubmix.com/api/v1/models", @@ -72129,7 +69249,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72145,7 +69264,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72161,7 +69279,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.248e-07, "source": "https://aihubmix.com/api/v1/models", @@ -72177,7 +69294,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.535e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72193,7 +69309,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.9995e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72209,7 +69324,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.999e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72225,7 +69339,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -72241,7 +69354,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.0984e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72254,7 +69366,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72290,7 +69401,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 204800, "max_output_tokens": 204800, - "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.1832e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72304,7 +69414,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 524288, - "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.152e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72329,7 +69438,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 5.48e-07, "source": "https://aihubmix.com/api/v1/models", @@ -72341,7 +69449,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9.008e-07, "source": "https://aihubmix.com/api/v1/models", @@ -72356,7 +69463,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9.864e-07, "source": "https://aihubmix.com/api/v1/models", @@ -72371,7 +69477,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.532e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72386,7 +69491,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.524e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72403,7 +69507,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.608e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72420,7 +69523,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.128e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72437,7 +69539,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72454,7 +69555,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.80025e-07, "source": "https://aihubmix.com/api/v1/models", @@ -72472,7 +69572,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5.07e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72657,7 +69756,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.5e-07, "source": "https://wandb.ai/site/pricing/tokens/", @@ -72670,7 +69769,7 @@ "input_cost_per_token": 1e-07, "litellm_provider": "wandb", "max_input_tokens": 262000, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://wandb.ai/site/pricing/tokens/", @@ -72711,7 +69810,6 @@ "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, @@ -72743,7 +69841,6 @@ "token_count_tokenizer": "kimi_k3", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_flex": 7.5e-06, @@ -72775,7 +69872,6 @@ "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, @@ -72797,7 +69893,6 @@ "litellm_provider": "xiaomi_mimo", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.7e-07, "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", @@ -72820,7 +69915,6 @@ "litellm_provider": "xiaomi_mimo", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", @@ -72845,7 +69939,6 @@ "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, @@ -72871,7 +69964,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -72893,7 +69985,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -72915,7 +70006,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -72937,7 +70027,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -72958,7 +70047,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -72980,7 +70068,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73001,7 +70088,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73023,7 +70109,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73045,7 +70130,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73066,7 +70150,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73088,7 +70171,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73110,7 +70192,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73131,7 +70212,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73153,7 +70233,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73178,7 +70257,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73203,7 +70281,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73228,7 +70305,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73249,7 +70325,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73271,7 +70346,6 @@ "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", @@ -73289,7 +70363,6 @@ "litellm_provider": "baseten", "max_input_tokens": 262000, "max_output_tokens": 262000, - "max_tokens": 262000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://inference.baseten.co/v1/models", @@ -73307,7 +70380,6 @@ "litellm_provider": "baseten", "max_input_tokens": 262000, "max_output_tokens": 262000, - "max_tokens": 262000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://inference.baseten.co/v1/models", @@ -73324,7 +70396,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://inference.baseten.co/v1/models", @@ -73341,7 +70412,6 @@ "litellm_provider": "baseten", "max_input_tokens": 202800, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://inference.baseten.co/v1/models", @@ -73359,7 +70429,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4.05e-06, "source": "https://inference.baseten.co/v1/models", @@ -73377,7 +70446,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://inference.baseten.co/v1/models", @@ -73394,7 +70462,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://inference.baseten.co/v1/models", @@ -73411,7 +70478,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inference.baseten.co/v1/models", @@ -73428,7 +70494,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.6e-07, "source": "https://inference.baseten.co/v1/models", @@ -73446,7 +70511,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.48e-06, "source": "https://inference.baseten.co/v1/models", @@ -73463,7 +70527,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://inference.baseten.co/v1/models", @@ -73480,7 +70543,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://inference.baseten.co/v1/models", @@ -73500,7 +70562,6 @@ "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_above_200k_tokens": 4e-06, @@ -73521,7 +70582,6 @@ "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_above_200k_tokens": 4e-06, @@ -73542,7 +70602,6 @@ "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_above_200k_tokens": 4e-06, @@ -73563,7 +70622,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.2e-06, @@ -73581,7 +70639,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 196608, "max_output_tokens": 196608, - "max_tokens": 196608, "mode": "chat", "output_cost_per_token_priority": 1.2e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -73647,7 +70704,6 @@ "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -73665,7 +70721,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, @@ -73684,7 +70739,6 @@ "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", @@ -73700,7 +70754,6 @@ "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -73717,7 +70770,6 @@ "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.5, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", @@ -73764,7 +70816,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -73797,7 +70848,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -73830,7 +70880,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -73863,7 +70912,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -73901,7 +70949,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -73934,7 +70981,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -73970,7 +71016,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -74009,7 +71054,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -74049,7 +71093,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -74087,7 +71130,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -74126,7 +71168,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -74159,7 +71200,6 @@ "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, @@ -74197,7 +71237,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, @@ -74217,7 +71256,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, @@ -74237,7 +71275,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, @@ -74259,7 +71296,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", @@ -74272,7 +71308,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -74285,7 +71320,6 @@ "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/", @@ -74321,7 +71355,6 @@ "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": { @@ -74359,7 +71392,6 @@ "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, @@ -74405,7 +71437,6 @@ "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": { @@ -74447,7 +71478,6 @@ "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": { @@ -74484,7 +71514,6 @@ "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, @@ -74521,7 +71550,6 @@ "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, @@ -74562,7 +71590,6 @@ "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": { @@ -74609,7 +71636,6 @@ "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": { @@ -74651,7 +71677,6 @@ "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": { @@ -74783,7 +71808,6 @@ "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, @@ -74829,7 +71853,6 @@ "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": { @@ -74874,7 +71897,6 @@ "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, @@ -74914,7 +71936,6 @@ "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, @@ -74947,7 +71968,6 @@ "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", @@ -74972,7 +71992,6 @@ "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", @@ -75005,7 +72024,6 @@ "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, @@ -75031,7 +72049,6 @@ "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, @@ -75049,7 +72066,6 @@ "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", @@ -75104,7 +72120,6 @@ "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, @@ -75172,7 +72187,6 @@ "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, @@ -75218,7 +72232,6 @@ "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, @@ -75266,7 +72279,6 @@ "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, @@ -75301,7 +72313,6 @@ "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, @@ -75315,7 +72326,6 @@ "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, @@ -75332,7 +72342,6 @@ "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, @@ -75350,7 +72359,6 @@ "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/", @@ -75383,7 +72391,6 @@ "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, @@ -75416,7 +72423,6 @@ "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, @@ -75439,7 +72445,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2.75e-06, @@ -75454,7 +72459,6 @@ "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/", @@ -75474,7 +72478,6 @@ "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, @@ -75519,7 +72522,6 @@ "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, @@ -75565,7 +72567,6 @@ "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, @@ -75609,7 +72610,6 @@ "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, @@ -75637,7 +72637,6 @@ "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, @@ -75670,7 +72669,6 @@ "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, @@ -75724,7 +72722,6 @@ "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": { @@ -75771,7 +72768,6 @@ "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": true, @@ -75816,7 +72812,6 @@ "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": { @@ -75859,7 +72854,6 @@ "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, @@ -75910,7 +72904,6 @@ "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": { @@ -75957,7 +72950,6 @@ "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": { @@ -75999,7 +72991,6 @@ "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": true, @@ -76041,7 +73032,6 @@ "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": true, @@ -76087,7 +73077,6 @@ "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": { @@ -76139,7 +73128,6 @@ "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": { @@ -76186,7 +73174,6 @@ "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": { @@ -76245,7 +73232,6 @@ "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": true, @@ -76296,7 +73282,6 @@ "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": { @@ -76346,7 +73331,6 @@ "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, @@ -76391,7 +73375,6 @@ "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, @@ -76430,7 +73413,6 @@ "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", @@ -76441,7 +73423,6 @@ "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", @@ -76452,7 +73433,6 @@ "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", @@ -76488,7 +73468,6 @@ "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, @@ -76508,7 +73487,6 @@ "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, @@ -76577,7 +73555,6 @@ "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, @@ -76623,7 +73600,6 @@ "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, @@ -76673,7 +73649,6 @@ "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, @@ -76732,7 +73707,6 @@ "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, @@ -76790,7 +73764,6 @@ "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, @@ -76838,7 +73811,6 @@ "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", @@ -76851,7 +73823,6 @@ "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, @@ -76863,7 +73834,6 @@ "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, @@ -76875,7 +73845,6 @@ "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, @@ -76954,7 +73923,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://api.together.ai/v1/models", @@ -76977,7 +73946,6 @@ "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, @@ -76999,7 +73967,6 @@ "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", @@ -77023,7 +73990,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "prompt_cache_min_tokens": 512.0, @@ -77053,7 +74019,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.25e-06, "source": "https://inference.baseten.co/v1/models", @@ -77071,7 +74036,6 @@ "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", @@ -77087,7 +74051,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, - "max_tokens": 943718, + "max_output_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", @@ -77103,7 +74067,7 @@ "input_cost_per_token": 4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", @@ -77117,7 +74081,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://inference.baseten.co/v1/models", @@ -77131,7 +74094,7 @@ "input_cost_per_token": 2.5e-07, "litellm_provider": "nebius", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/reflection%2Fbeam", @@ -77144,7 +74107,6 @@ "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", @@ -77161,7 +74123,6 @@ "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", @@ -77180,7 +74141,6 @@ "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, @@ -77200,7 +74160,6 @@ "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", @@ -77222,7 +74181,6 @@ "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", @@ -77244,7 +74202,6 @@ "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, @@ -77266,7 +74223,6 @@ "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, @@ -77288,7 +74244,6 @@ "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, @@ -77307,7 +74262,7 @@ "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", @@ -77344,7 +74299,6 @@ "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, @@ -77380,7 +74334,6 @@ "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, @@ -77429,7 +74382,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.2e-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'", @@ -77459,7 +74411,6 @@ "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 5e-07, - "max_tokens": 500000, "max_output_tokens": 500000, "max_input_tokens": 500000, "supports_function_calling": true, @@ -77497,7 +74448,6 @@ "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, "cache_creation_input_token_cost": 1.25e-07, - "max_tokens": 128000, "max_output_tokens": 128000, "max_input_tokens": 922000, "supports_function_calling": true, @@ -77537,7 +74487,6 @@ "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 2e-08, "cache_creation_input_token_cost": 2.5e-07, - "max_tokens": 128000, "max_output_tokens": 128000, "max_input_tokens": 922000, "supports_function_calling": true, @@ -77577,7 +74526,6 @@ "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, "cache_creation_input_token_cost": 1.25e-07, - "max_tokens": 128000, "max_output_tokens": 128000, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77616,7 +74564,6 @@ "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 1e-07, - "max_tokens": 65536, "max_output_tokens": 65536, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77633,7 +74580,6 @@ "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 3e-08, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77650,7 +74596,6 @@ "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77667,7 +74612,6 @@ "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77685,7 +74629,6 @@ "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 2.0000000000000002e-07, "cache_creation_input_token_cost": 2e-06, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77703,7 +74646,6 @@ "output_cost_per_token": 1.5e-05, "cache_read_input_token_cost": 3e-07, "cache_creation_input_token_cost": 3e-06, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77720,7 +74662,6 @@ "input_cost_per_token": 9.499999999999999e-07, "output_cost_per_token": 4e-06, "cache_read_input_token_cost": 1.9e-07, - "max_tokens": 262144, "max_output_tokens": 262144, "max_input_tokens": 262144, "supports_function_calling": true, @@ -77737,7 +74678,6 @@ "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 6e-09, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77754,7 +74694,6 @@ "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 6e-09, - "max_tokens": 384000, "max_output_tokens": 384000, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77771,7 +74710,6 @@ "input_cost_per_token": 1.32e-06, "output_cost_per_token": 3.96e-06, "cache_read_input_token_cost": 4.4e-08, - "max_tokens": 384000, "max_output_tokens": 384000, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77788,7 +74726,6 @@ "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 2.8e-09, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77805,7 +74742,6 @@ "input_cost_per_token": 4.35e-07, "output_cost_per_token": 8.7e-07, "cache_read_input_token_cost": 3.625e-09, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77822,7 +74758,6 @@ "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 2.8e-09, - "max_tokens": 128000, "max_output_tokens": 128000, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77839,7 +74774,6 @@ "input_cost_per_token": 4.35e-07, "output_cost_per_token": 8.7e-07, "cache_read_input_token_cost": 3.625e-09, - "max_tokens": 128000, "max_output_tokens": 128000, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77856,7 +74790,6 @@ "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "cache_read_input_token_cost": 1.5e-08, - "max_tokens": 512000, "max_output_tokens": 512000, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77873,7 +74806,6 @@ "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 6e-08, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77890,7 +74822,6 @@ "input_cost_per_token": 1.0000000000000001e-07, "output_cost_per_token": 2.0000000000000002e-07, "cache_read_input_token_cost": 2e-09, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77907,7 +74838,6 @@ "input_cost_per_token": 1.0000000000000001e-07, "output_cost_per_token": 2.0000000000000002e-07, "cache_read_input_token_cost": 2e-09, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77925,7 +74855,6 @@ "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 2.5e-07, "cache_creation_input_token_cost": 2.5e-06, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77943,7 +74872,6 @@ "output_cost_per_token": 4.6999999999999995e-07, "cache_read_input_token_cost": 1.6e-08, "cache_creation_input_token_cost": 2.0000000000000002e-07, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77961,7 +74889,6 @@ "output_cost_per_token": 1.6000000000000001e-06, "cache_read_input_token_cost": 4e-08, "cache_creation_input_token_cost": 5e-07, - "max_tokens": 65536, "max_output_tokens": 65536, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -78000,7 +74927,6 @@ "input_cost_per_token": 8.34e-07, "output_cost_per_token": 2.501e-06, "cache_read_input_token_cost": 4.2000000000000006e-08, - "max_tokens": 64000, "max_output_tokens": 64000, "max_input_tokens": 1024000, "supports_function_calling": true, @@ -78017,7 +74943,6 @@ "input_cost_per_token": 1.4e-07, "output_cost_per_token": 5.8e-07, "cache_read_input_token_cost": 3.5e-08, - "max_tokens": 128000, "max_output_tokens": 128000, "max_input_tokens": 192000, "supports_function_calling": true, @@ -78034,7 +74959,6 @@ "input_cost_per_token": 0, "output_cost_per_token": 0, "cache_read_input_token_cost": 0, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -78051,7 +74975,6 @@ "input_cost_per_token": 1e-06, "output_cost_per_token": 2.7e-06, "cache_read_input_token_cost": 1.0000000000000001e-07, - "max_tokens": 65536, "max_output_tokens": 65536, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -78068,7 +74991,6 @@ "input_cost_per_token": 0, "output_cost_per_token": 0, "cache_read_input_token_cost": 0, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -78089,7 +75011,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -78134,7 +75055,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -78178,7 +75098,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -78211,7 +75130,6 @@ "litellm_provider": "bedrock", "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, @@ -78261,7 +75179,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -78298,7 +75215,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -78341,7 +75257,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -78385,7 +75300,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -78430,7 +75344,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -78475,7 +75388,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, @@ -78520,7 +75432,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -78555,7 +75466,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -78598,7 +75508,6 @@ "litellm_provider": "bedrock", "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, @@ -78642,7 +75551,6 @@ "litellm_provider": "bedrock", "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, @@ -78712,7 +75620,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "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, @@ -78761,7 +75668,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ @@ -78788,7 +75694,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 922000, "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, @@ -78827,7 +75732,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-06, "output_cost_per_token_above_272k_tokens": 8.25e-06, @@ -78884,7 +75788,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 5e-06, "output_cost_per_token_above_272k_tokens": 7.5e-06, diff --git a/litellm/proxy/_experimental/mcp_server/sampling_handler.py b/litellm/proxy/_experimental/mcp_server/sampling_handler.py index e1469f2fff7..d049ada4dfd 100644 --- a/litellm/proxy/_experimental/mcp_server/sampling_handler.py +++ b/litellm/proxy/_experimental/mcp_server/sampling_handler.py @@ -222,7 +222,7 @@ def _select_model_by_priority( input_cost = info.get("input_cost_per_token") or 0.0 output_cost = info.get("output_cost_per_token") or 0.0 total_cost = input_cost + output_cost - max_output = info.get("max_output_tokens") or info.get("max_tokens") or 0 + max_output = info.get("max_output_tokens") or 0 output_tps = info.get("output_tokens_per_second") or 0.0 scored.append( _ScoredModel( diff --git a/litellm/router.py b/litellm/router.py index d5093384a17..548df8e6721 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -12264,7 +12264,6 @@ class Router: _fallback_entry = litellm.model_cost.get(_azure_fallback_key) _fallback_resolves = _fallback_entry is not None and ( (_fallback_entry.get("max_input_tokens") or 0) > 0 - or (_fallback_entry.get("max_tokens") or 0) > 0 or (_fallback_entry.get("input_cost_per_token") or 0) > 0 ) if _fallback_resolves: diff --git a/litellm/router_utils/pre_call_checks/io_token_rate_limit_check.py b/litellm/router_utils/pre_call_checks/io_token_rate_limit_check.py index 086f5517c29..2e350a2f87b 100644 --- a/litellm/router_utils/pre_call_checks/io_token_rate_limit_check.py +++ b/litellm/router_utils/pre_call_checks/io_token_rate_limit_check.py @@ -148,7 +148,7 @@ def _model_max_output_tokens(model_name: str) -> int | None: # this lookup is a fallback default and must never fail the request. with contextlib.suppress(Exception): info: Final = litellm.get_model_info(model=model_name) - model_max: Final = info.get("max_output_tokens") or info.get("max_tokens") + model_max: Final = info.get("max_output_tokens") if model_max is not None: return max(0, int(model_max)) return None diff --git a/litellm/utils.py b/litellm/utils.py index 1cc7c63e6a5..1aed15ba83e 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -6079,11 +6079,8 @@ def get_max_tokens(model: str) -> int | None: return None try: - if model in litellm.model_cost: - if "max_output_tokens" in litellm.model_cost[model]: - return litellm.model_cost[model]["max_output_tokens"] - elif "max_tokens" in litellm.model_cost[model]: - return litellm.model_cost[model]["max_tokens"] + if model in litellm.model_cost and "max_output_tokens" in litellm.model_cost[model]: + return litellm.model_cost[model]["max_output_tokens"] get_llm_provider: Final = litellm_utils.get_llm_provider model, custom_llm_provider, _, _ = get_llm_provider(model=model) if custom_llm_provider == "huggingface": @@ -6092,8 +6089,6 @@ def get_max_tokens(model: str) -> int | None: if model in litellm.model_cost: # check if extracted model is in model_list if "max_output_tokens" in litellm.model_cost[model]: return litellm.model_cost[model]["max_output_tokens"] - elif "max_tokens" in litellm.model_cost[model]: - return litellm.model_cost[model]["max_tokens"] else: raise Exception() return None @@ -6742,7 +6737,7 @@ def get_model_info_helper( returned_model_info: Final = ModelInfoBase( key=key, - max_tokens=_model_info.get("max_tokens", None), + max_tokens=_model_info.get("max_output_tokens") or _model_info.get("max_input_tokens"), max_input_tokens=_model_info.get("max_input_tokens", None), max_output_tokens=_model_info.get("max_output_tokens", None), input_cost_per_token=_input_cost_per_token, @@ -8242,9 +8237,7 @@ def trim_messages( if max_tokens is None: # Check if model is valid if model in litellm.model_cost: - max_tokens_for_model: Final = litellm.model_cost[model].get( - "max_input_tokens", litellm.model_cost[model]["max_tokens"] - ) + max_tokens_for_model: Final = litellm.model_cost[model]["max_input_tokens"] max_tokens = int(max_tokens_for_model * trim_ratio) else: # if user did not specify max (input) tokens diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index d9df9d97d7b..c913c879ccf 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -9,9 +9,8 @@ "input_cost_per_audio_token": 0.0, "input_cost_per_token": 0.0, "litellm_provider": "one of https://docs.litellm.ai/docs/providers", - "max_input_tokens": "max input tokens, if the provider specifies it. if not default to max_tokens", - "max_output_tokens": "max output tokens, if the provider specifies it. if not default to max_tokens", - "max_tokens": "LEGACY parameter. set to max_output_tokens if provider specifies it. IF not set to max_input_tokens, if provider specifies it.", + "max_input_tokens": "max input tokens, if the provider specifies it", + "max_output_tokens": "max output tokens, if the provider specifies it", "mode": "one of: chat, embedding, completion, image_generation, audio_transcription, audio_speech, image_generation, moderation, rerank, search", "output_cost_per_reasoning_token": 0.0, "output_cost_per_token": 0.0, @@ -49,28 +48,24 @@ "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.018 }, "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.036 }, @@ -79,7 +74,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.25e-05, "source": "https://aws.amazon.com/bedrock/pricing/" @@ -89,7 +83,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8191, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.88e-05, "source": "https://aws.amazon.com/bedrock/pricing/" @@ -100,7 +93,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-large.md" @@ -111,7 +103,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-ai21-labs-jamba-1-5-mini.md" @@ -121,7 +112,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 70000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -298,7 +288,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", @@ -311,7 +300,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", @@ -324,7 +312,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x4.md", @@ -337,7 +324,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-x5.md", @@ -352,7 +338,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, @@ -368,7 +353,6 @@ "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, @@ -389,7 +373,6 @@ "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, @@ -414,7 +397,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -435,7 +417,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.311e-06, "supports_function_calling": true, @@ -455,7 +436,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://aws.amazon.com/nova/pricing/", @@ -474,7 +454,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.597e-06, "supports_function_calling": true, @@ -494,7 +473,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://aws.amazon.com/nova/pricing/", @@ -518,7 +496,6 @@ "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, @@ -544,7 +521,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -562,7 +538,6 @@ "amazon.nova-2-multimodal-embeddings-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 8172, - "max_tokens": 8172, "mode": "embedding", "input_cost_per_token": 1.35e-07, "input_cost_per_image": 6e-05, @@ -583,7 +558,6 @@ "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, @@ -602,7 +576,6 @@ "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, @@ -626,7 +599,6 @@ "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, @@ -646,7 +618,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2.75e-06, @@ -660,7 +631,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -669,7 +639,6 @@ "input_cost_per_token": 8e-07, "litellm_provider": "bedrock", "max_input_tokens": 128, - "max_tokens": 128, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, @@ -684,7 +653,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 @@ -693,7 +661,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 @@ -702,7 +669,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -740,7 +706,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -755,7 +720,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -770,7 +734,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -784,7 +747,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, - "max_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, @@ -798,7 +760,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, - "max_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, @@ -812,7 +773,6 @@ "input_cost_per_image": 0.0001, "litellm_provider": "bedrock", "max_input_tokens": 500, - "max_tokens": 500, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 512, @@ -860,7 +820,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 6e-07 }, @@ -869,7 +828,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 2e-07 }, @@ -878,7 +836,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, @@ -889,7 +846,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -909,7 +865,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", @@ -941,7 +896,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -964,7 +918,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -982,7 +935,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -1001,7 +953,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -1021,7 +972,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -1039,7 +989,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -1054,7 +1003,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true @@ -1067,7 +1015,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -1097,7 +1044,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -1125,7 +1071,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1164,7 +1109,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1204,7 +1148,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1244,7 +1187,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1284,7 +1226,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1324,7 +1265,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1364,7 +1304,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1405,7 +1344,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, @@ -1427,7 +1365,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1470,7 +1407,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1513,7 +1449,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1556,7 +1491,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -1596,7 +1530,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1639,7 +1572,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1678,7 +1610,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1721,7 +1652,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -1760,7 +1690,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1803,7 +1732,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1842,7 +1770,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1880,7 +1807,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "search_context_cost_per_query": { @@ -1922,7 +1848,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -1965,7 +1890,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "search_context_cost_per_query": { @@ -2010,7 +1934,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -2053,7 +1976,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "search_context_cost_per_query": { @@ -2098,7 +2020,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2141,7 +2062,6 @@ "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": { @@ -2186,7 +2106,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2229,7 +2148,6 @@ "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": { @@ -2269,7 +2187,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2312,7 +2229,6 @@ "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": { @@ -2357,7 +2273,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2395,7 +2310,6 @@ "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": { @@ -2435,7 +2349,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -2480,7 +2393,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -2525,7 +2437,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2570,7 +2481,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2615,7 +2525,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2660,7 +2569,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2703,7 +2611,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -2745,7 +2652,6 @@ "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": { @@ -2790,7 +2696,6 @@ "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": { @@ -2835,7 +2740,6 @@ "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": { @@ -2880,7 +2784,6 @@ "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": { @@ -2925,7 +2828,6 @@ "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": { @@ -2970,7 +2872,6 @@ "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": { @@ -3011,7 +2912,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3050,7 +2950,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3089,7 +2988,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -3128,7 +3026,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -3167,7 +3064,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -3206,7 +3102,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -3246,7 +3141,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3286,7 +3180,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3319,7 +3212,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05 }, @@ -3328,7 +3220,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -3338,7 +3229,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07 }, @@ -3347,7 +3237,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -3356,7 +3245,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" @@ -3366,7 +3254,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" @@ -3376,7 +3263,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07 }, @@ -3385,7 +3271,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -3394,7 +3279,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07 }, @@ -3403,7 +3287,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" @@ -3413,7 +3296,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" @@ -3423,7 +3305,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1", @@ -3434,7 +3315,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1", @@ -3445,7 +3325,6 @@ "litellm_provider": "anyscale", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1", @@ -3457,7 +3336,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.52e-07, "supports_function_calling": true, @@ -3473,7 +3351,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.48e-07, "supports_function_calling": true, @@ -3489,7 +3366,6 @@ "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, @@ -3508,7 +3384,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -3543,7 +3418,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -3595,7 +3469,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -3628,7 +3501,6 @@ "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://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -3640,7 +3512,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 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'", @@ -3670,7 +3541,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -3685,7 +3555,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -3709,7 +3578,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": true, @@ -3734,7 +3602,6 @@ "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, @@ -3765,7 +3632,6 @@ "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, @@ -3797,7 +3663,6 @@ "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, @@ -3830,7 +3695,6 @@ "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, @@ -3868,7 +3732,6 @@ "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, @@ -3899,7 +3762,6 @@ "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, @@ -3938,7 +3800,6 @@ "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, @@ -3971,7 +3832,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -3996,7 +3856,6 @@ "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": { @@ -4030,7 +3889,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": false, @@ -4052,7 +3910,6 @@ "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 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'", @@ -4087,7 +3944,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "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, @@ -4105,7 +3961,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4154,7 +4009,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4203,7 +4057,6 @@ "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, @@ -4252,7 +4105,6 @@ "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, @@ -4304,7 +4156,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4345,7 +4196,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", @@ -4395,7 +4245,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", @@ -4439,7 +4288,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4486,7 +4334,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4533,7 +4380,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4581,7 +4427,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "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, @@ -4629,7 +4474,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -4675,7 +4519,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -4717,7 +4560,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_priority": 9e-06, @@ -4759,7 +4601,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_priority": 9e-06, @@ -4801,7 +4642,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_priority": 2.5e-06, @@ -4843,7 +4683,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_priority": 2.5e-06, @@ -4883,7 +4722,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/", "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)" @@ -4895,7 +4733,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/", "comment": "Catalog-name twin of azure_ai/model_router: the flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it" @@ -4908,7 +4745,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -4929,7 +4765,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -4949,7 +4784,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -4968,7 +4802,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -4987,7 +4820,6 @@ "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -5006,7 +4838,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2.2e-05, "output_cost_per_token": 2.64e-06, @@ -5026,7 +4857,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 2.2e-05, @@ -5046,7 +4876,6 @@ "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, @@ -5076,7 +4905,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -5116,7 +4944,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, @@ -5155,7 +4982,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ @@ -5196,7 +5022,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -5228,7 +5053,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-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'", @@ -5261,7 +5085,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, @@ -5298,7 +5121,6 @@ "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, @@ -5317,7 +5139,6 @@ "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, @@ -5335,7 +5156,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -5353,7 +5173,6 @@ "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, @@ -5371,7 +5190,6 @@ "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, @@ -5389,7 +5207,6 @@ "litellm_provider": "azure", "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, @@ -5409,7 +5226,6 @@ "litellm_provider": "azure", "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, @@ -5426,7 +5242,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -5443,7 +5258,6 @@ "litellm_provider": "azure", "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, @@ -5463,7 +5277,6 @@ "litellm_provider": "azure", "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, @@ -5484,7 +5297,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -5525,7 +5337,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 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'", @@ -5557,7 +5368,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-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'", @@ -5587,7 +5397,6 @@ "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -5597,7 +5406,7 @@ "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, - "max_tokens": 4097, + "max_output_tokens": 4097, "mode": "completion", "output_cost_per_token": 2.2e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -5607,7 +5416,6 @@ "litellm_provider": "azure", "max_input_tokens": 4097, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -5619,7 +5427,6 @@ "litellm_provider": "azure", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", @@ -5631,7 +5438,6 @@ "litellm_provider": "azure", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", @@ -5642,7 +5448,7 @@ "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, - "max_tokens": 4097, + "max_output_tokens": 4097, "mode": "completion", "output_cost_per_token": 2.2e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -5651,7 +5457,7 @@ "input_cost_per_token": 1.65e-06, "litellm_provider": "azure_text", "max_input_tokens": 4097, - "max_tokens": 4097, + "max_output_tokens": 4097, "mode": "completion", "output_cost_per_token": 2.2e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -5662,7 +5468,6 @@ "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -5674,7 +5479,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, @@ -5687,7 +5491,6 @@ "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", @@ -5699,7 +5502,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, @@ -5712,7 +5514,6 @@ "litellm_provider": "azure", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00012, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", @@ -5724,7 +5525,6 @@ "litellm_provider": "azure", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.00012, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models", @@ -5735,7 +5535,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", @@ -5748,7 +5547,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", @@ -5762,7 +5560,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.3e-05, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/", @@ -5779,7 +5576,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, @@ -5817,7 +5613,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, @@ -5855,7 +5650,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, @@ -5893,7 +5687,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, @@ -5929,7 +5722,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -5963,7 +5755,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -5997,7 +5788,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 0.00015, "output_cost_per_token_batches": 7.5e-05, @@ -6017,7 +5807,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -6034,7 +5823,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -6053,7 +5841,6 @@ "litellm_provider": "azure", "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, @@ -6073,7 +5860,6 @@ "litellm_provider": "azure", "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, @@ -6092,7 +5878,6 @@ "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, @@ -6125,7 +5910,6 @@ "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, @@ -6157,7 +5941,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -6190,7 +5973,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -6225,7 +6007,6 @@ "litellm_provider": "azure", "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, @@ -6257,7 +6038,6 @@ "litellm_provider": "azure", "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, @@ -6290,7 +6070,6 @@ "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, @@ -6322,7 +6101,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -6340,7 +6118,6 @@ "litellm_provider": "azure", "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, @@ -6358,7 +6135,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 6e-07, @@ -6392,7 +6168,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -6414,7 +6189,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -6449,7 +6223,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -6483,7 +6256,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -6518,7 +6290,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -6552,7 +6323,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, @@ -6587,7 +6357,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -6622,7 +6391,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -6656,7 +6424,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -6720,7 +6487,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 0.0002, "output_cost_per_token": 2e-05, @@ -6739,7 +6505,6 @@ "litellm_provider": "azure", "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, @@ -6793,7 +6558,6 @@ "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": [ @@ -6817,7 +6581,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, @@ -6860,7 +6623,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, @@ -6895,7 +6657,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "output_cost_per_token_priority": 3.6e-06, @@ -6932,7 +6693,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -6971,7 +6731,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -7008,7 +6767,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 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'", @@ -7044,7 +6802,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, @@ -7083,7 +6840,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, @@ -7122,7 +6878,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -7158,7 +6913,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -7194,7 +6948,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, @@ -7228,7 +6981,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -7269,7 +7021,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7294,7 +7045,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7316,7 +7066,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7337,7 +7086,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7358,7 +7106,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7380,7 +7127,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7401,7 +7147,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7422,7 +7167,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7444,7 +7188,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7465,7 +7208,6 @@ "litellm_provider": "azure", "max_input_tokens": 111616, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.54e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7486,7 +7228,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7502,7 +7243,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7518,7 +7258,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7550,7 +7289,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7582,7 +7320,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7618,7 +7355,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, @@ -7658,7 +7394,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_batches": 7e-06, @@ -7696,7 +7431,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -7730,7 +7464,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, @@ -7762,7 +7495,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, @@ -7801,7 +7533,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, @@ -7850,7 +7581,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -7906,7 +7636,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -7956,7 +7685,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -8006,7 +7734,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -8062,7 +7789,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -8112,7 +7838,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -8163,7 +7888,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -8212,7 +7936,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -8266,7 +7989,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -8327,7 +8049,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -8391,7 +8112,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -8455,7 +8175,6 @@ "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, @@ -8519,7 +8238,6 @@ "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, @@ -8583,7 +8301,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, @@ -8647,7 +8364,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, @@ -8699,7 +8415,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -8748,7 +8463,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -8797,7 +8511,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -8846,7 +8559,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -8901,7 +8613,6 @@ "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, @@ -8954,7 +8665,6 @@ "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, @@ -9001,7 +8711,6 @@ "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, @@ -9050,7 +8759,6 @@ "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, @@ -9099,7 +8807,6 @@ "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, @@ -9148,7 +8855,6 @@ "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, @@ -9197,7 +8903,6 @@ "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, @@ -9242,7 +8947,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "reasoning_effort_levels": [ @@ -9279,7 +8983,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "reasoning_effort_levels": [ @@ -9325,7 +9028,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, @@ -9380,7 +9082,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, @@ -9436,7 +9137,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, @@ -9492,7 +9192,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, @@ -9542,7 +9241,6 @@ "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, @@ -9591,7 +9289,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-07, "output_cost_per_token_above_272k_tokens": 8.25e-07, @@ -9646,7 +9343,6 @@ "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, @@ -9689,7 +9385,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.3e-05, "reasoning_effort_levels": [ @@ -9735,7 +9430,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, @@ -9790,7 +9484,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-05, "output_cost_per_token_above_272k_tokens": 3.3e-05, @@ -9846,7 +9539,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, @@ -9902,7 +9594,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, @@ -9961,7 +9652,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -10020,7 +9710,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, @@ -10075,7 +9764,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token_above_272k_tokens_batches": 2.475e-05, "output_cost_per_token_batches": 1.65e-05, @@ -10127,7 +9815,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "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, @@ -10187,7 +9874,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_batches": 1.5e-05, @@ -10246,7 +9932,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -10299,7 +9984,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -10353,7 +10037,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -10406,7 +10089,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -10453,7 +10135,6 @@ "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -10497,7 +10178,6 @@ "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -10539,7 +10219,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { @@ -10590,7 +10269,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "search_context_cost_per_query": { @@ -10642,7 +10320,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "search_context_cost_per_query": { @@ -10690,7 +10367,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "search_context_cost_per_query": { @@ -11066,7 +10742,7 @@ "input_cost_per_token": 8e-06, "litellm_provider": "azure", "max_input_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_function_calling": true @@ -11075,7 +10751,7 @@ "input_cost_per_token": 8e-06, "litellm_provider": "azure", "max_input_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_function_calling": true @@ -11087,7 +10763,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_function_calling": true, @@ -11105,7 +10780,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_batches": 3e-05, @@ -11124,7 +10798,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -11142,7 +10815,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -11160,7 +10832,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "supported_endpoints": [ @@ -11191,7 +10862,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, @@ -11223,7 +10893,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 4e-05, "search_context_cost_per_query": { @@ -11261,7 +10930,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_prompt_caching": true, @@ -11278,7 +10946,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -11295,7 +10962,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, @@ -11326,7 +10992,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, @@ -11357,7 +11022,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supported_endpoints": [ @@ -11388,7 +11052,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -11433,7 +11096,6 @@ "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -11443,7 +11105,6 @@ "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -11453,7 +11114,6 @@ "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/" @@ -11504,7 +11164,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8.8e-06, "output_cost_per_token_batches": 4.4e-06, @@ -11542,7 +11201,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, @@ -11578,7 +11236,6 @@ "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, @@ -11612,7 +11269,6 @@ "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, @@ -11633,7 +11289,6 @@ "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, @@ -11653,7 +11308,6 @@ "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, @@ -11672,7 +11326,6 @@ "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11691,7 +11344,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11710,7 +11362,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2.2e-05, "output_cost_per_token": 2.64e-06, @@ -11730,7 +11381,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 0.00022, "output_cost_per_token": 2.2e-05, @@ -11750,7 +11400,6 @@ "litellm_provider": "azure", "max_input_tokens": 16000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 8.8e-05, "output_cost_per_token": 2.2e-05, @@ -11780,7 +11429,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "output_cost_per_token_batches": 5.5e-06, @@ -11820,7 +11468,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, @@ -11858,7 +11505,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, "output_cost_per_token_batches": 2.2e-07, @@ -11896,7 +11542,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, "supported_endpoints": [ @@ -11937,7 +11582,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -11969,7 +11613,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12002,7 +11645,6 @@ "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, @@ -12021,7 +11663,6 @@ "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, @@ -12039,7 +11680,6 @@ "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, @@ -12057,7 +11697,6 @@ "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, @@ -12090,7 +11729,6 @@ "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, @@ -12123,7 +11761,6 @@ "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, @@ -12141,7 +11778,6 @@ "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, @@ -12159,7 +11795,6 @@ "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, @@ -12180,7 +11815,6 @@ "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, @@ -12204,7 +11838,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -12215,7 +11848,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -12227,7 +11859,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12245,7 +11876,6 @@ "azure_ai/FLUX-1.1-pro": { "litellm_provider": "azure_ai", "max_input_tokens": 5000, - "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", @@ -12256,7 +11886,6 @@ "azure_ai/FLUX.1-Kontext-pro": { "litellm_provider": "azure_ai", "max_input_tokens": 5000, - "max_tokens": 5000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", @@ -12267,7 +11896,6 @@ "azure_ai/flux.2-pro": { "litellm_provider": "azure_ai", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "image_generation", "output_cost_per_image": 0.04, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -12279,7 +11907,6 @@ "input_cost_per_pixel": 5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "image_generation", "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/black-forest-labs/", "supported_endpoints": [ @@ -12301,7 +11928,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12316,7 +11942,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.828e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12332,7 +11957,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.52e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12348,7 +11972,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12363,7 +11986,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12378,7 +12000,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 7.26e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12393,7 +12014,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.46e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12415,7 +12035,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.3e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12438,7 +12057,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12461,7 +12079,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12484,7 +12101,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ @@ -12513,7 +12129,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12528,7 +12143,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12571,7 +12185,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.64e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12637,7 +12250,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12660,7 +12272,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.1e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -12672,7 +12283,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12685,7 +12295,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 10000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", @@ -12699,7 +12308,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 2048, - "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", @@ -12711,7 +12319,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.54e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12723,7 +12330,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12736,7 +12342,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12749,7 +12354,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12762,7 +12366,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12775,7 +12378,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12788,7 +12390,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12801,7 +12402,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12814,7 +12414,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12827,7 +12426,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12840,7 +12438,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12854,7 +12451,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12867,7 +12463,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12881,7 +12476,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12893,7 +12487,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12935,7 +12528,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 8182, - "max_tokens": 8182, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -12975,7 +12567,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -12989,7 +12580,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" @@ -13001,7 +12591,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" @@ -13012,7 +12601,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" @@ -13023,7 +12611,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076" @@ -13033,7 +12620,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -13048,7 +12634,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -13064,7 +12649,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -13076,7 +12660,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -13092,7 +12675,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 5.1e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -13109,7 +12691,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -13122,7 +12703,6 @@ "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": 3072, @@ -13142,7 +12722,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -13159,7 +12738,6 @@ "litellm_provider": "azure_ai", "max_input_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, @@ -13180,7 +12758,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_above_200k_tokens": 1.2e-05, @@ -13200,7 +12777,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -13219,7 +12795,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -13236,7 +12811,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, @@ -13250,7 +12824,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, @@ -13264,7 +12837,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", @@ -13279,7 +12851,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.00971, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models" @@ -13290,7 +12861,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 70000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -13302,7 +12872,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -13319,7 +12888,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -13343,7 +12911,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-08, "source": "https://marketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", @@ -13356,7 +12923,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 32000, "max_output_tokens": 8191, - "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", @@ -13369,7 +12935,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -13381,7 +12946,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -13393,7 +12957,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 8191, - "max_tokens": 8191, "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'", @@ -13407,7 +12970,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "supports_assistant_prefill": true, @@ -13420,7 +12982,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -13432,7 +12993,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/retired-models", @@ -13445,7 +13005,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -13459,7 +13018,6 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -13471,7 +13029,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -13481,7 +13038,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -13491,7 +13047,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -13501,7 +13056,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_tool_choice": true }, @@ -13526,7 +13080,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13536,7 +13089,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { @@ -13545,7 +13097,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13555,7 +13106,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13565,7 +13115,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { @@ -13574,7 +13123,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -13583,7 +13131,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 7.55e-06, "supports_tool_choice": true @@ -13593,7 +13140,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -13603,7 +13149,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -13614,7 +13159,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13634,7 +13178,6 @@ "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, @@ -13652,7 +13195,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -13672,7 +13214,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13686,7 +13227,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13704,7 +13244,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -13723,7 +13262,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13737,7 +13275,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13757,7 +13294,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -13768,7 +13304,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -13779,7 +13314,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13799,7 +13333,6 @@ "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, @@ -13817,7 +13350,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -13837,7 +13369,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13851,7 +13382,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13869,7 +13399,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -13887,7 +13416,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -13906,7 +13434,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13926,7 +13453,6 @@ "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, @@ -13944,7 +13470,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -13963,7 +13488,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -13981,7 +13505,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -13999,7 +13522,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.03e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -14010,7 +13532,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.9e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -14021,7 +13542,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14041,7 +13561,6 @@ "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, @@ -14059,7 +13578,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14078,7 +13596,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14096,7 +13613,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14106,7 +13622,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { @@ -14115,7 +13630,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14125,7 +13639,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14135,7 +13648,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { @@ -14144,7 +13656,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14153,7 +13664,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 8.38e-06, "supports_tool_choice": true @@ -14163,7 +13673,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05 }, @@ -14172,7 +13681,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -14184,7 +13692,6 @@ "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, @@ -14202,7 +13709,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14221,7 +13727,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -14239,7 +13744,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.78e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -14250,7 +13754,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.5e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -14262,7 +13765,6 @@ "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, @@ -14280,7 +13782,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14299,7 +13800,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -14317,7 +13817,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.55e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -14328,7 +13827,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -14340,7 +13838,6 @@ "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, @@ -14358,7 +13855,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14377,7 +13873,6 @@ "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, @@ -14396,7 +13891,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.86e-06, "output_cost_per_token_flex": 9.3e-07, @@ -14414,7 +13908,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -14425,7 +13918,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.56e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", @@ -14437,7 +13929,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -14450,7 +13941,6 @@ "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, @@ -14468,7 +13958,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14487,7 +13976,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -14504,7 +13992,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Anthropic via Invoke route does not currently support pdf input." }, @@ -14523,7 +14010,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.88e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -14534,7 +14020,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.01e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -14545,7 +14030,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14565,7 +14049,6 @@ "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, @@ -14583,7 +14066,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14603,7 +14085,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14617,7 +14098,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14635,7 +14115,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.44e-06, "output_cost_per_token_flex": 7.2e-07, @@ -14653,7 +14132,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14663,7 +14141,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { @@ -14672,7 +14149,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14682,7 +14158,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14692,7 +14167,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { @@ -14701,7 +14175,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -14710,7 +14183,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true @@ -14720,7 +14192,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -14730,7 +14201,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -14741,7 +14211,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -14752,7 +14221,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -14763,7 +14231,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -14774,7 +14241,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", @@ -14786,7 +14252,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -14798,7 +14263,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14818,7 +14282,6 @@ "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, @@ -14838,7 +14301,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -14855,7 +14317,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14869,7 +14330,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14887,7 +14347,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, @@ -14905,7 +14364,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14925,7 +14383,6 @@ "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, @@ -14943,7 +14400,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "supports_function_calling": true, @@ -14963,7 +14419,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14977,7 +14432,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -14995,7 +14449,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, @@ -15013,7 +14466,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.84e-06, "supports_function_calling": true, @@ -15027,7 +14479,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 @@ -15036,7 +14487,6 @@ "input_cost_per_token": 2e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -15046,7 +14496,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.7e-06 }, @@ -15055,7 +14504,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-07 }, @@ -15064,7 +14512,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, @@ -15077,7 +14524,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -15106,7 +14552,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -15127,7 +14572,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.5e-06, "supports_pdf_input": true @@ -15137,7 +14581,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 2.65e-06, "supports_pdf_input": true @@ -15145,7 +14588,6 @@ "bedrock/us-gov-west-1/amazon.nova-2-multimodal-embeddings-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 8172, - "max_tokens": 8172, "mode": "embedding", "input_cost_per_token": 1.62e-07, "input_cost_per_image": 7.2e-05, @@ -15164,7 +14606,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.88e-07, "supports_function_calling": true, @@ -15180,7 +14621,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.68e-07, "supports_function_calling": true, @@ -15194,7 +14634,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.84e-06, "supports_function_calling": true, @@ -15208,7 +14647,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536 @@ -15217,7 +14655,6 @@ "input_cost_per_token": 1.1e-07, "litellm_provider": "bedrock", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -15227,7 +14664,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.6e-06 }, @@ -15236,7 +14672,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-07 }, @@ -15245,7 +14680,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 42000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06 }, @@ -15258,7 +14692,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -15287,7 +14720,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -15308,7 +14740,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 3.5e-06, "supports_pdf_input": true @@ -15318,7 +14749,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 6e-07, "supports_pdf_input": true @@ -15329,7 +14759,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -15340,7 +14769,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -15351,7 +14779,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -15361,7 +14788,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { @@ -15370,7 +14796,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -15380,7 +14805,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -15390,7 +14814,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat" }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { @@ -15399,7 +14822,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "supports_tool_choice": true }, @@ -15408,7 +14830,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-06, "supports_tool_choice": true @@ -15418,7 +14839,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -15428,7 +14848,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 100000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.4e-05, "supports_tool_choice": true @@ -15439,7 +14858,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -15450,7 +14868,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", @@ -15462,7 +14879,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -15474,7 +14890,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -15494,7 +14909,6 @@ "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, @@ -15514,7 +14928,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 196000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -15531,7 +14944,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -15545,7 +14957,6 @@ "litellm_provider": "bedrock", "max_input_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, @@ -15563,7 +14974,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_flex": 6e-07, @@ -15582,7 +14992,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -15672,7 +15081,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -15683,7 +15091,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -15694,7 +15101,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, @@ -15705,7 +15111,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -15716,7 +15121,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -15727,7 +15131,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.5e-07, "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras", @@ -15742,7 +15145,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://inference-docs.cerebras.ai/support/pricing", @@ -15755,7 +15157,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.49e-06, "source": "https://api.cerebras.ai/public/v1/models/qwen-3.8-27b", @@ -15771,7 +15172,6 @@ "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07 }, @@ -15802,7 +15202,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -15829,7 +15228,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -15858,7 +15256,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -15892,7 +15289,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -15928,7 +15324,6 @@ "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, @@ -15972,7 +15367,6 @@ "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, @@ -16019,7 +15413,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -16063,7 +15456,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -16092,7 +15484,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16126,7 +15517,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16163,7 +15553,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16206,7 +15595,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16249,7 +15637,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16293,7 +15680,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16337,7 +15723,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -16382,7 +15767,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -16428,7 +15812,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, @@ -16474,7 +15857,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16522,7 +15904,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -16638,7 +16019,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 3072, "max_output_tokens": 3072, - "max_tokens": 3072, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -16648,7 +16028,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 2048, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -16658,7 +16037,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -16668,7 +16046,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.923e-06, "rpm": 300 @@ -16678,7 +16055,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-07, "rpm": 300, @@ -16690,7 +16066,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -16700,7 +16075,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 80000, "max_output_tokens": 80000, - "max_tokens": 80000, "mode": "chat", "output_cost_per_token": 3.35e-07, "rpm": 300 @@ -16710,7 +16084,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-08, "rpm": 300 @@ -16720,7 +16093,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 15000, "max_output_tokens": 15000, - "max_tokens": 15000, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -16731,7 +16103,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "rpm": 20, @@ -16743,7 +16114,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 80000, "max_output_tokens": 80000, - "max_tokens": 80000, "mode": "chat", "output_cost_per_token": 4.881e-06, "rpm": 300, @@ -16754,7 +16124,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.87e-07, "rpm": 300 @@ -16764,7 +16133,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 60000, "max_output_tokens": 60000, - "max_tokens": 60000, "mode": "chat", "output_cost_per_token": 2.01e-07, "rpm": 300 @@ -16775,7 +16143,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "rpm": 20, @@ -16787,7 +16154,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-07, "rpm": 300, @@ -16799,7 +16165,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -16809,7 +16174,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 24000, "max_output_tokens": 24000, - "max_tokens": 24000, "mode": "chat", "output_cost_per_token": 2.253e-06, "rpm": 300, @@ -16820,7 +16184,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1.12e-07, "rpm": 300, @@ -16831,7 +16194,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-06, "rpm": 300 @@ -16842,7 +16204,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "rpm": 20, @@ -16854,7 +16215,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-06, "rpm": 300, @@ -16866,7 +16226,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.55e-07, "rpm": 300 @@ -16876,7 +16235,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.35e-07, "rpm": 300, @@ -16888,7 +16246,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 3500, "max_output_tokens": 3500, - "max_tokens": 3500, "mode": "chat", "output_cost_per_token": 0.0, "rpm": 300 @@ -16898,7 +16255,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 3e-07, "rpm": 300, @@ -16910,7 +16266,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.55e-07, "rpm": 300, @@ -16921,7 +16276,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.76e-07, "rpm": 300, @@ -16932,7 +16286,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "rpm": 300, @@ -16944,7 +16297,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 8.5e-07, "rpm": 300, @@ -16955,7 +16307,6 @@ "litellm_provider": "cloudflare", "max_input_tokens": 24000, "max_output_tokens": 24000, - "max_tokens": 24000, "mode": "chat", "output_cost_per_token": 1e-06, "rpm": 300, @@ -16966,7 +16317,6 @@ "litellm_provider": "codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/", @@ -16978,7 +16328,6 @@ "litellm_provider": "codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/", @@ -16990,7 +16339,6 @@ "litellm_provider": "bedrock", "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/", @@ -17001,7 +16349,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -17011,7 +16358,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -17021,7 +16367,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "bedrock", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -17031,7 +16376,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -17042,7 +16386,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -17053,7 +16396,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "bedrock", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -17064,7 +16406,6 @@ "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": 1536, @@ -17076,7 +16417,6 @@ "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, @@ -17087,7 +16427,6 @@ "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, @@ -17109,7 +16448,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-cohere-rerank-3-5.md" @@ -17119,7 +16457,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -17131,7 +16468,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "source": "https://docs.cohere.com/docs/models" }, @@ -17140,7 +16476,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.cohere.com/docs/command-a-plus", @@ -17155,7 +16490,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06 }, @@ -17164,7 +16498,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -17175,7 +16508,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -17186,7 +16518,6 @@ "litellm_provider": "cohere_chat", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://docs.cohere.com/v2/docs/command-r7b", @@ -17199,7 +16530,7 @@ "input_cost_per_token": 1.12e-06, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.coralbricks.ai/pricing", @@ -17222,7 +16553,7 @@ "input_cost_per_token": 1.12e-06, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.coralbricks.ai/pricing", @@ -17245,7 +16576,7 @@ "input_cost_per_token": 1.12e-06, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.coralbricks.ai/pricing", @@ -17268,7 +16599,7 @@ "input_cost_per_token": 1e-08, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.coralbricks.ai/pricing", @@ -17291,7 +16622,7 @@ "input_cost_per_token": 1e-08, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.coralbricks.ai/pricing", @@ -17314,7 +16645,7 @@ "input_cost_per_token": 1e-08, "litellm_provider": "coralbricks", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.coralbricks.ai/pricing", @@ -17337,7 +16668,6 @@ "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": [ @@ -17367,7 +16697,6 @@ "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": [ @@ -17398,7 +16727,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -17420,7 +16748,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -17442,7 +16769,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17458,7 +16784,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17474,7 +16799,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17490,7 +16814,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 202745, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17506,7 +16829,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17522,7 +16844,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 229376, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17538,7 +16859,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17550,7 +16870,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17579,7 +16898,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17609,7 +16927,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 30720, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17622,7 +16939,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17635,7 +16951,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17648,7 +16963,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -17662,7 +16976,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -17675,7 +16988,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17706,7 +17018,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17737,7 +17048,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17769,7 +17079,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -17783,7 +17092,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -17796,7 +17104,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -17810,7 +17117,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -17823,7 +17129,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17834,7 +17139,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17883,7 +17187,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17928,7 +17231,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -17977,7 +17279,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18022,7 +17323,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18059,7 +17359,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18096,7 +17395,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18134,7 +17432,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18146,7 +17443,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18159,7 +17455,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18172,7 +17467,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18186,7 +17480,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18199,7 +17492,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -18212,7 +17504,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 260096, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18250,7 +17541,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18284,7 +17574,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18298,7 +17587,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -18334,7 +17622,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18352,7 +17639,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -18371,7 +17657,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -18390,7 +17675,6 @@ "litellm_provider": "dashscope", "max_input_tokens": 98304, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -18711,7 +17995,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.qwencloud.com/models", @@ -18727,7 +18010,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.qwencloud.com/models", @@ -18743,7 +18025,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.qwencloud.com/models", @@ -18759,7 +18040,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 202745, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.qwencloud.com/models", @@ -18775,7 +18055,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.qwencloud.com/models", @@ -18791,7 +18070,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 229376, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.qwencloud.com/models", @@ -18807,7 +18085,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.qwencloud.com/models", @@ -18819,7 +18096,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18848,7 +18124,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18878,7 +18153,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 30720, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.qwencloud.com/models", @@ -18891,7 +18165,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -18904,7 +18177,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -18917,7 +18189,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -18931,7 +18202,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -18944,7 +18214,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -18975,7 +18244,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19006,7 +18274,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19038,7 +18305,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -19052,7 +18318,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.qwencloud.com/models", @@ -19065,7 +18330,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -19079,7 +18343,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -19092,7 +18355,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19103,7 +18365,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19152,7 +18413,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19197,7 +18457,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19246,7 +18505,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19291,7 +18549,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19328,7 +18585,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19365,7 +18621,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19403,7 +18658,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -19415,7 +18669,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.qwencloud.com/models", @@ -19428,7 +18681,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.qwencloud.com/models", @@ -19441,7 +18693,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.qwencloud.com/models", @@ -19455,7 +18706,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.qwencloud.com/models", @@ -19468,7 +18718,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.qwencloud.com/models", @@ -19481,7 +18730,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 260096, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19519,7 +18767,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19553,7 +18800,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.qwencloud.com/models", @@ -19567,7 +18813,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.qwencloud.com/models", "supports_function_calling": true, @@ -19603,7 +18848,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.qwencloud.com/models", @@ -19619,7 +18863,6 @@ "litellm_provider": "qwencloud", "max_input_tokens": 98304, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.qwencloud.com/models", @@ -19940,7 +19183,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19956,7 +19198,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19972,7 +19213,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 4.8e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -19988,7 +19228,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 202745, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20004,7 +19243,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20020,7 +19258,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 229376, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20036,7 +19273,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20048,7 +19284,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20077,7 +19312,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20107,7 +19341,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 30720, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20120,7 +19353,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20133,7 +19365,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20146,7 +19377,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -20160,7 +19390,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 4e-06, "output_cost_per_token": 1.2e-06, @@ -20173,7 +19402,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20204,7 +19432,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20235,7 +19462,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20267,7 +19493,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -20281,7 +19506,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20294,7 +19518,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -20308,7 +19531,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_reasoning_token": 5e-07, "output_cost_per_token": 2e-07, @@ -20321,7 +19543,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 129024, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20332,7 +19553,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20381,7 +19601,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20426,7 +19645,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20475,7 +19693,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 997952, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20520,7 +19737,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20557,7 +19773,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20594,7 +19809,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 258048, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20632,7 +19846,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -20644,7 +19857,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -20657,7 +19869,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -20670,7 +19881,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -20684,7 +19894,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.4e-07, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -20697,7 +19906,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.87e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", @@ -20710,7 +19918,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 260096, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20748,7 +19955,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20782,7 +19988,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20796,7 +20001,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_function_calling": true, @@ -20832,7 +20036,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -20850,7 +20053,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -20869,7 +20071,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 991808, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", @@ -20888,7 +20089,6 @@ "litellm_provider": "qwen_ai_platform", "max_input_tokens": 98304, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://www.alibabacloud.com/help/en/model-studio/models", @@ -21210,7 +20410,6 @@ "input_dbu_cost_per_token": 1.429e-06, "litellm_provider": "databricks", "max_input_tokens": 512, - "max_tokens": 512, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21228,7 +20427,6 @@ "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." }, @@ -21257,7 +20455,6 @@ "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." }, @@ -21287,7 +20484,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21311,7 +20507,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21335,7 +20530,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21359,7 +20553,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21384,7 +20577,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21409,7 +20601,6 @@ "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." }, @@ -21436,7 +20627,6 @@ "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." }, @@ -21464,7 +20654,6 @@ "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." }, @@ -21493,7 +20682,6 @@ "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." }, @@ -21528,7 +20716,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21552,7 +20739,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21575,7 +20761,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21599,7 +20784,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21624,7 +20808,6 @@ "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. Introductory launch rates of 28.571 input / 142.857 output / 35.714 cache write / 2.857 cache read DBU run through 2026-08-31; the standard rates are listed here because entries carry no expiry date." }, @@ -21653,7 +20836,6 @@ "token_count_framing": 97, "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." }, @@ -21686,7 +20868,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." }, @@ -21715,7 +20896,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21749,7 +20929,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21784,7 +20963,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21812,7 +20990,6 @@ "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "metadata": { "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." }, @@ -21833,7 +21010,6 @@ "litellm_provider": "databricks", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "metadata": { "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." }, @@ -21858,7 +21034,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21891,7 +21066,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21923,7 +21097,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -21939,7 +21112,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." }, @@ -21964,7 +21136,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "metadata": { "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." }, @@ -21993,7 +21164,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "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." }, @@ -22025,7 +21195,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "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." }, @@ -22056,7 +21225,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "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." }, @@ -22089,7 +21257,6 @@ "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22106,7 +21273,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." }, @@ -22134,7 +21300,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "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." }, @@ -22165,7 +21330,6 @@ "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "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." }, @@ -22195,7 +21359,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22215,7 +21378,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22235,7 +21397,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22255,7 +21416,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22275,7 +21435,6 @@ "litellm_provider": "databricks", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22304,7 +21463,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22333,7 +21491,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22362,7 +21519,6 @@ "litellm_provider": "databricks", "max_input_tokens": 922000, "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. Rates reflect OpenAI's promotional pricing in effect through November 21, 2026; afterwards input, cache and Batch rates are 25% higher and output rates 50% higher." }, @@ -22391,7 +21547,6 @@ "litellm_provider": "databricks", "max_input_tokens": 922000, "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." }, @@ -22420,7 +21575,6 @@ "litellm_provider": "databricks", "max_input_tokens": 922000, "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." }, @@ -22449,7 +21603,6 @@ "litellm_provider": "databricks", "max_input_tokens": 922000, "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." }, @@ -22478,7 +21631,6 @@ "litellm_provider": "databricks", "max_input_tokens": 922000, "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." }, @@ -22507,7 +21659,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22527,7 +21678,6 @@ "litellm_provider": "databricks", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22547,7 +21697,6 @@ "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22564,7 +21713,6 @@ "litellm_provider": "databricks", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22606,7 +21754,6 @@ "input_dbu_cost_per_token": 1.857e-06, "litellm_provider": "databricks", "max_input_tokens": 8192, - "max_tokens": 8192, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22653,7 +21800,6 @@ "token_count_framing": 100, "max_input_tokens": 1000000, "max_output_tokens": 1048576, - "max_tokens": 1048576, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." }, @@ -22687,7 +21833,6 @@ "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." }, @@ -22705,7 +21850,6 @@ "litellm_provider": "databricks", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22722,7 +21866,6 @@ "litellm_provider": "databricks", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, @@ -22740,7 +21883,6 @@ "litellm_provider": "databricks", "max_input_tokens": 262144, "max_output_tokens": 25000, - "max_tokens": 25000, "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." }, @@ -22790,7 +21932,6 @@ "input_dbu_cost_per_token": 2.86e-07, "litellm_provider": "databricks", "max_input_tokens": 32768, - "max_tokens": 32768, "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." }, @@ -22836,7 +21977,6 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, @@ -23431,7 +22571,6 @@ ] }, "deepinfra/Gryphe/MythoMax-L2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 4e-07, @@ -23443,7 +22582,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-06, @@ -23454,7 +22592,6 @@ "supports_function_calling": true }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 7e-07, @@ -23465,7 +22602,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/QwQ-32B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, @@ -23476,7 +22612,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen2.5-72B-Instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 3.6e-07, @@ -23488,7 +22623,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen2.5-7B-Instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 4e-08, @@ -23498,7 +22632,6 @@ "supports_tool_choice": false }, "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -23510,7 +22643,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-14B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.2e-07, @@ -23522,7 +22654,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.8e-07, @@ -23533,7 +22664,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-08, @@ -23545,7 +22675,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, @@ -23556,7 +22685,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-30B-A3B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1.2e-07, @@ -23568,7 +22696,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-32B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 8e-08, @@ -23580,7 +22707,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 4e-07, @@ -23591,7 +22717,6 @@ "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, @@ -23605,7 +22730,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-08, @@ -23617,7 +22741,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.4e-07, @@ -23628,7 +22751,6 @@ "supports_function_calling": true }, "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, @@ -23638,7 +22760,6 @@ "supports_tool_choice": false }, "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 8.5e-07, @@ -23649,7 +22770,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6.5e-07, @@ -23659,7 +22779,6 @@ "supports_tool_choice": false }, "deepinfra/allenai/olmOCR-7B-0725-FP8": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2.7e-07, @@ -23669,7 +22788,6 @@ "supports_tool_choice": false }, "deepinfra/anthropic/claude-3-7-sonnet-latest": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 3.3e-06, @@ -23681,7 +22799,6 @@ "supports_function_calling": true }, "deepinfra/anthropic/claude-4-opus": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 1.65e-05, @@ -23692,7 +22809,6 @@ "supports_function_calling": true }, "deepinfra/anthropic/claude-4-sonnet": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 3.3e-06, @@ -23703,7 +22819,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 7e-07, @@ -23714,7 +22829,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -23726,7 +22840,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-06, @@ -23737,7 +22850,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -23747,7 +22859,6 @@ "supports_tool_choice": false }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.7e-07, @@ -23758,7 +22869,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-06, @@ -23769,7 +22879,6 @@ "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-V3": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 3.2e-07, @@ -23781,7 +22890,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.4e-07, @@ -23795,7 +22903,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.5e-07, @@ -23809,7 +22916,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 2.7e-07, @@ -23821,7 +22927,6 @@ "supports_function_calling": true }, "deepinfra/google/gemini-2.5-flash": { - "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "input_cost_per_token": 3e-07, @@ -23837,7 +22942,6 @@ "supports_audio_input": true }, "deepinfra/google/gemini-2.5-pro": { - "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "input_cost_per_token": 1.25e-06, @@ -23852,7 +22956,6 @@ "supports_audio_input": true }, "deepinfra/google/gemma-3-12b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-08, @@ -23864,7 +22967,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-27b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 8e-08, @@ -23876,7 +22978,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-4b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-08, @@ -23888,7 +22989,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4.9e-08, @@ -23898,7 +22998,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, @@ -23909,7 +23008,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.3e-07, @@ -23920,7 +23018,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -23932,7 +23029,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 2e-07, @@ -23944,7 +23040,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "max_tokens": 327680, "max_input_tokens": 327680, "max_output_tokens": 327680, "input_cost_per_token": 1e-07, @@ -23956,7 +23051,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-Guard-3-8B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5.5e-08, @@ -23966,7 +23060,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Llama-Guard-4-12B": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.8e-07, @@ -23976,7 +23069,6 @@ "supports_tool_choice": false }, "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, @@ -23987,7 +23079,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, @@ -23998,7 +23089,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, @@ -24010,7 +23100,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -24021,7 +23110,6 @@ "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, @@ -24033,7 +23121,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/microsoft/WizardLM-2-8x22B": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 4.8e-07, @@ -24043,7 +23130,6 @@ "supports_tool_choice": false }, "deepinfra/microsoft/phi-4": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 7e-08, @@ -24054,7 +23140,6 @@ "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.9e-08, @@ -24066,7 +23151,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-08, @@ -24077,7 +23161,6 @@ "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 7.5e-08, @@ -24088,7 +23171,6 @@ "supports_function_calling": true }, "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 4e-07, @@ -24099,7 +23181,6 @@ "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-07, @@ -24110,7 +23191,6 @@ "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct-0905": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-07, @@ -24122,7 +23202,6 @@ "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6e-07, @@ -24133,7 +23212,6 @@ "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -24157,7 +23235,6 @@ "supports_prompt_caching": true }, "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-08, @@ -24168,7 +23245,6 @@ "supports_function_calling": true }, "deepinfra/openai/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3.7e-08, @@ -24180,7 +23256,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/openai/gpt-oss-20b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -24192,7 +23267,6 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.5": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 4e-07, @@ -24211,7 +23285,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -24234,7 +23307,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07, "supports_assistant_prefill": true, @@ -24249,7 +23321,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.19e-06, "supports_assistant_prefill": true, @@ -24266,7 +23337,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", @@ -24291,7 +23361,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.1e-06, "supports_assistant_prefill": true, @@ -24306,7 +23375,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 4e-07, "supports_assistant_prefill": true, @@ -24321,7 +23389,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html", @@ -24338,7 +23405,6 @@ "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, @@ -24358,7 +23424,6 @@ "litellm_provider": "nlp_cloud", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "completion", "output_cost_per_token": 5e-07 }, @@ -24367,7 +23432,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 98304, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, @@ -24381,7 +23445,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, @@ -24395,7 +23458,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 229376, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_assistant_prefill": true, @@ -24408,7 +23470,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" }, @@ -24420,7 +23481,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" }, @@ -24432,7 +23492,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240915 version with 4096 dimensions" }, @@ -24444,7 +23503,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-250515 version with 2048 dimensions" }, @@ -24456,7 +23514,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "volcengine", "max_input_tokens": 4096, - "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions" }, @@ -24569,7 +23626,6 @@ "mode": "search" }, "sail/moonshotai/Kimi-K3": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 2.5e-06, @@ -24591,7 +23647,6 @@ "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, @@ -24613,7 +23668,6 @@ "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, @@ -24635,7 +23689,6 @@ "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, @@ -24657,7 +23710,6 @@ "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, @@ -24679,7 +23731,6 @@ "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, @@ -24701,7 +23752,6 @@ "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, @@ -24724,7 +23774,6 @@ "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, @@ -24747,7 +23796,6 @@ "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, @@ -24770,7 +23818,6 @@ "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, @@ -24792,7 +23839,6 @@ "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, @@ -24808,7 +23854,6 @@ "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, @@ -25047,7 +24092,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -25056,7 +24100,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, @@ -25069,7 +24112,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true @@ -25078,7 +24120,6 @@ "input_cost_per_token": 0.0001, "litellm_provider": "cohere", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true @@ -25089,7 +24130,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.12e-07, "supports_function_calling": true, @@ -25105,7 +24145,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.84e-07, "supports_function_calling": true, @@ -25121,7 +24160,6 @@ "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, @@ -25138,7 +24176,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -25161,7 +24198,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -25189,7 +24225,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -25205,7 +24240,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -25224,7 +24258,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -25244,7 +24277,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -25261,7 +24293,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -25292,7 +24323,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -25323,7 +24353,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -25363,7 +24392,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -25397,7 +24425,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -25410,7 +24437,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -25422,7 +24448,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "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", @@ -27688,14 +26713,12 @@ "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat" }, "featherless_ai/featherless-ai/Qwerky-QwQ-32B": { "litellm_provider": "featherless_ai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat" }, "fireworks-ai-4.1b-to-16b": { @@ -27743,7 +26766,6 @@ "input_cost_per_token": 1.6e-08, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -27753,7 +26775,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/pricing", @@ -27766,7 +26787,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 20480, - "max_tokens": 20480, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://fireworks.ai/pricing", @@ -27778,7 +26798,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 160000, - "max_tokens": 160000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://fireworks.ai/pricing", @@ -27790,7 +26809,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 20480, - "max_tokens": 20480, "mode": "chat", "output_cost_per_token": 2.19e-06, "source": "https://fireworks.ai/pricing", @@ -27802,7 +26820,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -27814,7 +26831,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", @@ -27826,7 +26842,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/pricing", @@ -27839,7 +26854,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/pricing", @@ -27852,7 +26866,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, "source": "https://fireworks.ai/models/fireworks/deepseek-v3p2", @@ -27867,7 +26880,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -27886,7 +26898,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.96e-06, "output_cost_per_token_priority": 4.95e-06, @@ -27906,7 +26917,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.96e-06, "output_cost_per_token_priority": 4.95e-06, @@ -27922,7 +26932,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -27935,7 +26944,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 96000, - "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 2.19e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p5", @@ -27949,7 +26957,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 96000, - "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://artificialanalysis.ai/models/glm-4-5-air", @@ -27964,7 +26971,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "source": "https://fireworks.ai/pricing", "supports_function_calling": true, @@ -27978,7 +26984,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p7", @@ -27993,7 +26998,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28012,7 +27016,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, @@ -28032,7 +27035,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, @@ -28049,7 +27051,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28064,7 +27065,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct", @@ -28077,7 +27077,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://app.fireworks.ai/models/fireworks/kimi-k2-instruct-0905", @@ -28090,7 +27089,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://fireworks.ai/pricing", @@ -28105,7 +27103,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -28122,7 +27119,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -28142,7 +27138,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -28158,7 +27153,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -28171,7 +27165,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", @@ -28184,7 +27177,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://fireworks.ai/pricing", @@ -28198,7 +27190,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", @@ -28211,7 +27202,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://fireworks.ai/pricing", @@ -28224,7 +27214,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -28237,7 +27226,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://fireworks.ai/pricing", @@ -28249,7 +27237,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://fireworks.ai/pricing", @@ -28262,7 +27249,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 196608, "max_output_tokens": 204800, - "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", @@ -28278,7 +27264,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.8e-06, @@ -28294,7 +27279,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/pricing", @@ -28307,7 +27291,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -28320,7 +27303,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://fireworks.ai/pricing", @@ -28333,7 +27315,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -28347,7 +27328,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28363,7 +27343,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://fireworks.ai/models/fireworks/glm-4p7", @@ -28378,7 +27357,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202752, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28394,7 +27372,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28413,7 +27390,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, @@ -28433,7 +27409,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_priority": 7.2e-07, @@ -28450,7 +27425,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28466,7 +27440,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://fireworks.ai/pricing", @@ -28483,7 +27456,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -28501,7 +27473,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28520,7 +27491,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-06, "output_cost_per_token_priority": 6e-06, @@ -28538,7 +27508,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -28554,7 +27523,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 196608, "max_output_tokens": 204800, - "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", @@ -28570,7 +27538,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.8e-06, @@ -28587,7 +27554,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -28601,7 +27567,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -28610,7 +27575,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -28619,7 +27583,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -28628,7 +27591,6 @@ "input_cost_per_token": 1.6e-08, "litellm_provider": "fireworks_ai-embedding-models", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "source": "https://fireworks.ai/pricing" @@ -28637,7 +27599,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 3e-08, @@ -28665,7 +27626,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "input_cost_per_token": 1.26e-06, "output_cost_per_token": 3.96e-06, "cache_read_input_token_cost": 2.34e-07, @@ -28693,7 +27653,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 4e-07, "supports_prompt_caching": false, @@ -28716,7 +27675,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, @@ -28743,7 +27701,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "input_cost_per_token": 5e-07, "output_cost_per_token": 1.5e-06, "cache_read_input_token_cost": 2.5e-07, @@ -28767,7 +27724,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 196608, "max_output_tokens": 196608, - "max_tokens": 196608, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 6e-08, @@ -28791,7 +27747,6 @@ "litellm_provider": "friendliai", "max_input_tokens": 202752, "max_output_tokens": 202752, - "max_tokens": 202752, "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, @@ -28818,7 +27773,6 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 9e-07, @@ -28831,7 +27785,6 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, @@ -28844,7 +27797,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "output_cost_per_token_batches": 3e-06, @@ -28858,7 +27810,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "supports_system_messages": true, @@ -28870,7 +27821,6 @@ "litellm_provider": "openai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "supports_system_messages": true, @@ -28882,7 +27832,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-06, "supports_system_messages": true, @@ -28894,7 +27843,6 @@ "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", @@ -28911,7 +27859,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -28932,7 +27879,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -28952,7 +27898,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_batches": 6e-07, @@ -28974,7 +27919,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, @@ -28995,7 +27939,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.2e-06, "output_cost_per_token_batches": 1.6e-06, @@ -29016,7 +27959,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, "output_cost_per_token_batches": 4e-07, @@ -29037,7 +27979,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 1.6e-05, "output_cost_per_token_batches": 8e-06, @@ -29060,7 +28001,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -29117,7 +28057,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, @@ -29175,7 +28114,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -29229,7 +28167,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -29281,7 +28218,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, @@ -29327,7 +28263,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, @@ -29376,7 +28311,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, @@ -29416,7 +28350,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -29475,7 +28408,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -29535,7 +28467,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -29591,7 +28522,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -29629,7 +28559,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, @@ -29684,7 +28613,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, @@ -29731,7 +28659,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -29778,7 +28705,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -29824,7 +28750,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -29868,7 +28793,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -29920,7 +28844,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -29982,7 +28905,6 @@ "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, @@ -30035,7 +28957,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -30088,7 +29009,6 @@ "litellm_provider": "vertex_ai", "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, @@ -30149,7 +29069,6 @@ "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, @@ -30196,7 +29115,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -30259,7 +29177,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -30320,7 +29237,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -30384,7 +29300,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -30440,7 +29355,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, @@ -30488,7 +29402,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -30531,7 +29444,6 @@ "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, @@ -30584,7 +29496,6 @@ "litellm_provider": "vertex_ai", "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, @@ -30641,7 +29552,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, @@ -30674,7 +29584,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_reasoning_token": 2.5e-06, @@ -30712,7 +29621,6 @@ "litellm_provider": "gemini", "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, @@ -30759,7 +29667,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -30783,7 +29690,6 @@ "input_cost_per_token_batches": 1.2e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30800,7 +29706,6 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30818,7 +29723,6 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30837,7 +29741,6 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30856,7 +29759,6 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "vertex_ai", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30870,7 +29772,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1000000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30882,7 +29783,6 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "gemini", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30901,7 +29801,6 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "gemini", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -30922,7 +29821,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -30968,7 +29866,6 @@ "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 6e-05, @@ -31020,7 +29917,6 @@ "litellm_provider": "gemini", "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, @@ -31080,7 +29976,6 @@ "input_cost_per_video_token_batches": 6e-06, "litellm_provider": "gemini", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -31097,7 +29992,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "rpm": 1000, @@ -31134,7 +30028,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "rpm": 1000, @@ -31180,7 +30073,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -31243,7 +30135,6 @@ "supports_reasoning": false, "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, @@ -31295,7 +30186,6 @@ "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, @@ -31344,7 +30234,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -31387,7 +30276,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.045, "output_cost_per_image_token": 6e-05, @@ -31429,7 +30317,6 @@ "litellm_provider": "gemini", "max_input_tokens": 65536, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, @@ -31468,7 +30355,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, @@ -31513,7 +30399,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, @@ -31570,7 +30455,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -31629,7 +30513,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -31688,7 +30571,6 @@ "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, @@ -31718,7 +30600,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -31772,7 +30653,6 @@ "litellm_provider": "gemini", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, @@ -31815,7 +30695,6 @@ "litellm_provider": "gemini", "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, @@ -31877,7 +30756,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -31940,7 +30818,6 @@ "litellm_provider": "gemini", "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, @@ -32002,7 +30879,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -32067,7 +30943,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -32129,7 +31004,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -32192,7 +31066,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -32250,7 +31123,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -32288,7 +31160,6 @@ "litellm_provider": "gemini", "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, @@ -32352,7 +31223,6 @@ "litellm_provider": "gemini", "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, @@ -32421,7 +31291,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 3e-06, @@ -32466,7 +31335,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -32501,7 +31369,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -32564,7 +31431,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -32625,7 +31491,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -32689,7 +31554,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -32745,7 +31609,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, @@ -32792,7 +31655,6 @@ "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, @@ -32827,7 +31689,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "metadata": { "notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true @@ -32850,7 +31711,6 @@ "litellm_provider": "gemini", "max_input_tokens": 2097152, "max_output_tokens": 8192, - "max_tokens": 8192, "metadata": { "notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true @@ -32871,7 +31731,7 @@ "input_cost_per_token": 3.5e-07, "litellm_provider": "gemini", "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", @@ -32885,7 +31745,7 @@ "input_cost_per_token": 3.5e-07, "litellm_provider": "gemini", "max_output_tokens": 8192, - "max_tokens": 8192, + "max_input_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", @@ -32909,7 +31769,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, @@ -32929,7 +31788,6 @@ "litellm_provider": "gemini", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, @@ -32945,7 +31803,6 @@ "litellm_provider": "gemini", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, @@ -32981,7 +31838,6 @@ "litellm_provider": "gemini", "max_input_tokens": 32767, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, @@ -33000,7 +31856,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_image": 0.04, "output_cost_per_token": 0, @@ -33025,7 +31880,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -33049,7 +31903,6 @@ "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -33066,7 +31919,6 @@ "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, @@ -33082,7 +31934,6 @@ "deprecation_date": "2026-10-22", "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08, @@ -33097,7 +31948,6 @@ "gemini/veo-3.1-fast-generate-001": { "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -33113,7 +31963,6 @@ "gemini/veo-3.1-generate-001": { "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, @@ -33132,7 +31981,6 @@ "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", @@ -33155,7 +32003,6 @@ "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", @@ -33178,7 +32025,6 @@ "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": [ @@ -33199,7 +32045,6 @@ "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, @@ -33224,7 +32069,6 @@ "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", @@ -33247,7 +32091,6 @@ "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", @@ -33270,7 +32113,6 @@ "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", @@ -33292,7 +32134,6 @@ "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", @@ -33315,7 +32156,6 @@ "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", @@ -33337,7 +32177,6 @@ "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", @@ -33360,7 +32199,6 @@ "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", @@ -33379,7 +32217,6 @@ "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", @@ -33396,7 +32233,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -33404,7 +32240,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -33412,7 +32247,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -33420,7 +32254,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true }, @@ -33428,7 +32261,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -33438,7 +32270,6 @@ "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, @@ -33451,7 +32282,6 @@ "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, @@ -33467,7 +32297,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -33477,7 +32306,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -33487,7 +32315,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -33496,7 +32323,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, @@ -33506,7 +32332,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -33515,7 +32340,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 64000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -33527,7 +32351,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://github.blog/changelog/2026-10-19-github-copilot-models-deprecated-on-october-19-2026", @@ -33542,7 +32365,6 @@ "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": [ @@ -33563,7 +32385,6 @@ "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, @@ -33585,7 +32406,6 @@ "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", @@ -33607,7 +32427,6 @@ "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, @@ -33631,7 +32450,6 @@ "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, @@ -33655,7 +32473,6 @@ "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, @@ -33680,7 +32497,6 @@ "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, @@ -33704,7 +32520,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 922000, "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, @@ -33728,7 +32543,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 922000, "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, @@ -33752,7 +32566,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 922000, "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, @@ -33776,7 +32589,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 922000, "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, @@ -33796,7 +32608,6 @@ "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", @@ -33814,7 +32625,6 @@ "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", @@ -33829,19 +32639,16 @@ "github_copilot/text-embedding-3-small": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding" }, "github_copilot/text-embedding-3-small-inference": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding" }, "github_copilot/text-embedding-ada-002": { "litellm_provider": "github_copilot", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding" }, "chatgpt/gpt-6-sol": { @@ -33853,7 +32660,6 @@ ], "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, @@ -33874,7 +32680,6 @@ ], "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, @@ -33895,7 +32700,6 @@ ], "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, @@ -33916,7 +32720,6 @@ ], "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, @@ -33933,7 +32736,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.5", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -33953,7 +32755,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.6-luna", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -33973,7 +32774,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.6-sol", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -33993,7 +32793,6 @@ "source": "https://platform.openai.com/docs/models/gpt-5.6-terra", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -34012,7 +32811,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -34032,7 +32830,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -34050,7 +32847,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -34068,7 +32864,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -34082,7 +32877,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -34097,7 +32891,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -34113,7 +32906,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -34128,7 +32920,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/chat/completions", @@ -34148,7 +32939,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -34163,7 +32953,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "responses", "supported_endpoints": [ "/v1/responses" @@ -34179,7 +32968,6 @@ "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, @@ -34190,7 +32978,6 @@ "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, @@ -34202,7 +32989,6 @@ "litellm_provider": "gigachat", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true, @@ -34213,7 +32999,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -34222,7 +33007,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024 @@ -34231,7 +33015,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 4096, - "max_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560 @@ -34240,7 +33023,6 @@ "input_cost_per_token": 0.0, "litellm_provider": "gigachat", "max_input_tokens": 4096, - "max_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2048 @@ -34250,7 +33032,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_function_calling": true, @@ -34262,7 +33043,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -34273,7 +33053,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -34284,7 +33063,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -34295,7 +33073,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.4e-05, "supports_function_calling": true @@ -34305,7 +33082,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true @@ -34315,7 +33091,6 @@ "litellm_provider": "gmi", "max_input_tokens": 409600, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true @@ -34325,7 +33100,6 @@ "litellm_provider": "gmi", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -34336,7 +33110,6 @@ "litellm_provider": "gmi", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -34347,7 +33120,6 @@ "litellm_provider": "gmi", "max_input_tokens": 163840, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true @@ -34357,7 +33129,6 @@ "litellm_provider": "gmi", "max_input_tokens": 163840, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 8.8e-07, "supports_function_calling": true @@ -34367,7 +33138,6 @@ "litellm_provider": "gmi", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, @@ -34379,7 +33149,6 @@ "litellm_provider": "gmi", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, @@ -34388,7 +33157,6 @@ "litellm_provider": "gmi", "max_input_tokens": 196608, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, @@ -34420,7 +33188,6 @@ "litellm_provider": "baseten", "max_input_tokens": 200000, "max_output_tokens": 200000, - "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://inference.baseten.co/v1/models", @@ -34465,7 +33232,6 @@ "litellm_provider": "baseten", "max_input_tokens": 128072, "max_output_tokens": 128072, - "max_tokens": 128072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inference.baseten.co/v1/models", @@ -34495,7 +33261,6 @@ "litellm_provider": "gmi", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-06, "supports_vision": true @@ -34505,7 +33270,6 @@ "litellm_provider": "gmi", "max_input_tokens": 202752, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2e-06 }, @@ -34518,7 +33282,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.9e-07, "output_cost_per_token_batches": 1.5e-07, @@ -34540,7 +33303,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 3.8e-07, "output_cost_per_token_batches": 1.9e-07, @@ -34562,7 +33324,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-08, "output_cost_per_token_batches": 4e-08, @@ -34594,7 +33355,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -34634,7 +33394,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -34668,7 +33427,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -34700,7 +33458,6 @@ "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, @@ -34721,7 +33478,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://developers.openai.com/api/docs/pricing", @@ -34737,7 +33493,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, @@ -34755,7 +33510,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 2e-06, @@ -34772,7 +33526,6 @@ "litellm_provider": "openai", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 4e-06, "supports_prompt_caching": true, @@ -34785,7 +33538,6 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 2e-06, "source": "https://developers.openai.com/api/docs/pricing" @@ -34795,7 +33547,6 @@ "litellm_provider": "text-completion-openai", "max_input_tokens": 8192, "max_output_tokens": 4097, - "max_tokens": 4097, "mode": "completion", "output_cost_per_token": 2e-06 }, @@ -34805,7 +33556,6 @@ "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, "supports_function_calling": true, @@ -34820,7 +33570,6 @@ "litellm_provider": "openai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_batches": 3e-05, @@ -34836,7 +33585,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, @@ -34851,7 +33599,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_function_calling": true, @@ -34869,7 +33616,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_batches": 1.5e-05, @@ -34891,7 +33637,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, @@ -34935,7 +33680,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_priority": 1.4e-05, @@ -34978,7 +33722,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, @@ -35022,7 +33765,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_priority": 2.8e-06, @@ -35066,7 +33808,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -35104,7 +33845,6 @@ "litellm_provider": "openai", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_priority": 8e-07, @@ -35141,7 +33881,6 @@ "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, @@ -35164,7 +33903,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -35188,7 +33926,6 @@ "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_priority": 1.7e-05, @@ -35213,7 +33950,6 @@ "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_priority": 1.7e-05, @@ -35235,7 +33971,6 @@ "litellm_provider": "openai", "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, @@ -35253,7 +33988,6 @@ "litellm_provider": "openai", "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, @@ -35271,7 +34005,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -35308,7 +34041,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -35343,7 +34075,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1e-05, @@ -35381,7 +34112,6 @@ "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, @@ -35419,7 +34149,6 @@ "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, @@ -35456,7 +34185,6 @@ "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, @@ -35497,7 +34225,6 @@ "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, @@ -35527,7 +34254,6 @@ "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_priority": 1e-06, @@ -35554,7 +34280,6 @@ "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": 6e-07, @@ -35574,7 +34299,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -35592,7 +34316,6 @@ "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, @@ -35619,7 +34342,6 @@ "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, @@ -35700,7 +34422,6 @@ "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, @@ -35727,7 +34448,6 @@ "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, @@ -36281,7 +35001,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -36327,7 +35046,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5-codex", @@ -36362,7 +35080,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, @@ -36412,7 +35129,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini", @@ -36443,7 +35159,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-max", @@ -36475,7 +35190,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex", @@ -36507,7 +35221,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-chat-latest", @@ -36542,7 +35255,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, @@ -36594,7 +35306,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, @@ -36645,7 +35356,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-codex", @@ -36677,7 +35387,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-chat-latest", @@ -36712,7 +35421,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, @@ -36762,7 +35470,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, @@ -36804,7 +35511,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, "output_cost_per_token_batches": 8.4e-05, @@ -36884,7 +35590,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "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, @@ -36971,7 +35676,6 @@ "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, @@ -37062,7 +35766,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_decisions": 0.0, @@ -37148,7 +35851,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -37230,7 +35932,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -37314,7 +36015,6 @@ "litellm_provider": "openai", "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, @@ -37397,7 +36097,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, @@ -37455,7 +36154,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-05, "output_cost_per_token_above_272k_tokens": 0.0001125, @@ -37494,7 +36192,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-05, "output_cost_per_token_above_272k_tokens": 0.0001125, @@ -37533,7 +36230,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 7.5e-05, "output_cost_per_token_above_272k_tokens": 0.0001125, @@ -37571,7 +36267,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -37610,7 +36305,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-05, "output_cost_per_token_above_272k_tokens": 3e-05, @@ -37644,7 +36338,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "reasoning_effort_levels": [ @@ -37690,7 +36383,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "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, @@ -37753,7 +36445,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "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, @@ -37809,7 +36500,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -37861,7 +36551,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -37920,7 +36609,6 @@ "litellm_provider": "openai", "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, @@ -37978,7 +36666,6 @@ "litellm_provider": "openai", "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, @@ -38029,7 +36716,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -38082,7 +36768,6 @@ "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, @@ -38138,7 +36823,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_flex": 2.25e-06, @@ -38193,7 +36877,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "output_cost_per_token_flex": 2.25e-06, @@ -38246,7 +36929,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, @@ -38298,7 +36980,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "output_cost_per_token_flex": 6.25e-07, @@ -38345,7 +37026,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 272000, - "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, @@ -38388,7 +37068,6 @@ "litellm_provider": "openai", "max_input_tokens": 400000, "max_output_tokens": 272000, - "max_tokens": 272000, "mode": "responses", "output_cost_per_token": 0.00012, "output_cost_per_token_batches": 6e-05, @@ -38437,7 +37116,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_batches": 5e-06, @@ -38483,7 +37161,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supported_endpoints": [ @@ -38519,7 +37196,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5-chat-latest", @@ -38552,7 +37228,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, @@ -38596,7 +37271,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://developers.openai.com/api/docs/models/gpt-5.3-chat-latest", @@ -38633,7 +37307,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, @@ -38685,7 +37358,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_batches": 1e-06, @@ -38735,7 +37407,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -38785,7 +37456,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -38871,7 +37541,6 @@ "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -38906,7 +37575,6 @@ "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -38941,7 +37609,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, @@ -38976,7 +37643,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, @@ -39013,7 +37679,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -39051,7 +37716,6 @@ "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -39087,7 +37751,6 @@ "litellm_provider": "openai", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 1.6e-05, @@ -39113,7 +37776,6 @@ }, "gradient_ai/alibaba-qwen3-32b": { "litellm_provider": "gradient_ai", - "max_tokens": 40960, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" @@ -39128,7 +37790,6 @@ "gradient_ai/anthropic-claude-3-opus": { "input_cost_per_token": 1.5e-05, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 7.5e-05, "supported_endpoints": [ @@ -39144,7 +37805,6 @@ "gradient_ai/anthropic-claude-3.5-haiku": { "input_cost_per_token": 8e-07, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 4e-06, "supported_endpoints": [ @@ -39160,7 +37820,6 @@ "gradient_ai/anthropic-claude-3.5-sonnet": { "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.5e-05, "supported_endpoints": [ @@ -39176,7 +37835,6 @@ "gradient_ai/anthropic-claude-3.7-sonnet": { "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.5e-05, "supported_endpoints": [ @@ -39192,7 +37850,6 @@ "gradient_ai/deepseek-r1-distill-llama-70b": { "input_cost_per_token": 9.9e-07, "litellm_provider": "gradient_ai", - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 9.9e-07, "supported_endpoints": [ @@ -39208,7 +37865,6 @@ "gradient_ai/llama3-8b-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "gradient_ai", - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 2e-07, "supported_endpoints": [ @@ -39224,7 +37880,6 @@ "gradient_ai/llama3.3-70b-instruct": { "input_cost_per_token": 6.5e-07, "litellm_provider": "gradient_ai", - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 6.5e-07, "supported_endpoints": [ @@ -39240,7 +37895,6 @@ "gradient_ai/mistral-nemo-instruct-2407": { "input_cost_per_token": 3e-07, "litellm_provider": "gradient_ai", - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 3e-07, "supported_endpoints": [ @@ -39255,7 +37909,6 @@ }, "gradient_ai/openai-gpt-4o": { "litellm_provider": "gradient_ai", - "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" @@ -39269,7 +37922,6 @@ }, "gradient_ai/openai-gpt-4o-mini": { "litellm_provider": "gradient_ai", - "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions" @@ -39284,7 +37936,6 @@ "gradient_ai/openai-o3": { "input_cost_per_token": 2e-06, "litellm_provider": "gradient_ai", - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "supported_endpoints": [ @@ -39300,7 +37951,6 @@ "gradient_ai/openai-o3-mini": { "input_cost_per_token": 1.1e-06, "litellm_provider": "gradient_ai", - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supported_endpoints": [ @@ -39316,7 +37966,6 @@ "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", @@ -39328,7 +37977,6 @@ "lemonade/gpt-oss-20b-mxfp4-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", @@ -39340,7 +37988,6 @@ "lemonade/gpt-oss-120b-mxfp-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 131072, "max_output_tokens": 32768, "mode": "chat", @@ -39352,7 +37999,6 @@ "lemonade/Gemma-3-4b-it-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "mode": "chat", @@ -39364,7 +38010,6 @@ "lemonade/Qwen3-4B-Instruct-2507-GGUF": { "input_cost_per_token": 0, "litellm_provider": "lemonade", - "max_tokens": 32768, "max_input_tokens": 262144, "max_output_tokens": 32768, "mode": "chat", @@ -39378,7 +38023,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 128000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.4e-07, "supports_function_calling": true, @@ -39390,7 +38034,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 2.4e-07, "supports_function_calling": true, @@ -39404,7 +38047,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 1000000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 1.25e-05, "supports_function_calling": true, @@ -39418,7 +38060,6 @@ "litellm_provider": "amazon_nova", "max_input_tokens": 300000, "max_output_tokens": 10000, - "max_tokens": 10000, "mode": "chat", "output_cost_per_token": 3.2e-06, "supports_function_calling": true, @@ -39432,7 +38073,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "groq", "max_input_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://console.groq.com/docs/model/llama-guard-3-8b" @@ -39442,7 +38083,6 @@ "litellm_provider": "groq", "max_input_tokens": 512, "max_output_tokens": 512, - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://console.groq.com/docs/models" @@ -39452,7 +38092,6 @@ "litellm_provider": "groq", "max_input_tokens": 512, "max_output_tokens": 512, - "max_tokens": 512, "mode": "chat", "output_cost_per_token": 4e-08, "source": "https://console.groq.com/docs/model/meta-llama/llama-prompt-guard-2-86m" @@ -39463,7 +38102,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-07, "search_context_cost_per_query": { @@ -39484,7 +38122,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "search_context_cost_per_query": { @@ -39505,7 +38142,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "search_context_cost_per_query": { @@ -39524,7 +38160,6 @@ "litellm_provider": "groq", "max_input_tokens": 4000, "max_output_tokens": 50000, - "max_tokens": 50000, "mode": "audio_speech", "source": "https://console.groq.com/docs/model/canopylabs/orpheus-v1-english" }, @@ -39533,7 +38168,6 @@ "litellm_provider": "groq", "max_input_tokens": 4000, "max_output_tokens": 50000, - "max_tokens": 50000, "mode": "audio_speech", "source": "https://console.groq.com/docs/models" }, @@ -39551,7 +38185,6 @@ }, "heroku/claude-3-5-haiku": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -39561,7 +38194,6 @@ }, "heroku/claude-3-5-sonnet-latest": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -39571,7 +38203,6 @@ }, "heroku/claude-3-7-sonnet": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -39581,7 +38212,6 @@ }, "heroku/claude-4-sonnet": { "litellm_provider": "heroku", - "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, @@ -39627,7 +38257,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39640,7 +38269,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -39653,7 +38281,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39666,7 +38293,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39679,7 +38305,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "supports_function_calling": true, @@ -39692,7 +38317,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true, @@ -39705,7 +38329,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_function_calling": true, @@ -39718,7 +38341,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -39731,7 +38353,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_function_calling": true, @@ -39744,7 +38365,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39757,7 +38377,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39770,7 +38389,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39783,7 +38401,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39796,7 +38413,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39809,7 +38425,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -39822,7 +38437,6 @@ "litellm_provider": "hyperbolic", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "supports_function_calling": true, @@ -39835,7 +38449,6 @@ "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 3e-06 }, @@ -39844,7 +38457,6 @@ "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 1e-05 }, @@ -39853,7 +38465,6 @@ "litellm_provider": "ai21", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 1.5e-05 }, @@ -39862,7 +38473,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -39872,7 +38482,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -39882,7 +38491,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -39892,7 +38500,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -39902,7 +38509,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -39912,7 +38518,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -39922,7 +38527,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -39932,7 +38536,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -39942,7 +38545,6 @@ "litellm_provider": "ai21", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -39952,7 +38554,6 @@ "litellm_provider": "jina_ai", "max_input_tokens": 1024, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://api.jina.ai/v1/models" @@ -39972,7 +38573,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -40009,7 +38609,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -40037,7 +38636,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 7e-06, "supports_function_calling": false, @@ -40050,7 +38648,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -40063,7 +38660,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -40077,7 +38673,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -40090,7 +38685,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-06, "supports_function_calling": false, @@ -40103,7 +38697,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -40116,7 +38709,6 @@ "litellm_provider": "crusoe", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, @@ -40130,7 +38722,6 @@ "litellm_provider": "inception", "max_input_tokens": 128000, "max_output_tokens": 50000, - "max_tokens": 50000, "mode": "chat", "output_cost_per_token": 7.5e-07, "supports_function_calling": true, @@ -40145,7 +38736,6 @@ "litellm_provider": "inception", "max_input_tokens": 260000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.5e-07, "source": "https://docs.inceptionlabs.ai/get-started/models", @@ -40160,7 +38750,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40181,7 +38771,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40202,7 +38792,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40223,7 +38813,7 @@ "input_cost_per_token": 1.72e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5.15e-06, "source": "https://inferenceapis.com/pricing", @@ -40244,7 +38834,7 @@ "input_cost_per_token": 1.72e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5.15e-06, "source": "https://inferenceapis.com/pricing", @@ -40265,7 +38855,7 @@ "input_cost_per_token": 4e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://inferenceapis.com/pricing", @@ -40286,7 +38876,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40307,7 +38897,7 @@ "input_cost_per_token": 4e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://inferenceapis.com/pricing", @@ -40328,7 +38918,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40349,7 +38939,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40370,7 +38960,7 @@ "input_cost_per_token": 1.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.8e-07, "source": "https://inferenceapis.com/pricing", @@ -40391,7 +38981,7 @@ "input_cost_per_token": 1.72e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5.15e-06, "source": "https://inferenceapis.com/pricing", @@ -40412,7 +39002,7 @@ "input_cost_per_token": 4e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://inferenceapis.com/pricing", @@ -40433,7 +39023,7 @@ "input_cost_per_token": 1.82e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048575, - "max_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", "output_cost_per_token": 5.72e-06, "source": "https://inferenceapis.com/pricing", @@ -40454,7 +39044,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048575, - "max_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://inferenceapis.com/pricing", @@ -40474,7 +39064,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://inferenceapis.com/pricing", @@ -40493,7 +39083,7 @@ "input_cost_per_token": 4e-08, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.9e-07, "source": "https://inferenceapis.com/pricing", @@ -40513,7 +39103,7 @@ "input_cost_per_token": 8.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.42e-06, "source": "https://inferenceapis.com/pricing", @@ -40533,7 +39123,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40552,7 +39142,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40571,7 +39161,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40590,7 +39180,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40609,7 +39199,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40628,7 +39218,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40648,7 +39238,7 @@ "input_cost_per_token": 3.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 524288, - "max_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://inferenceapis.com/pricing", @@ -40669,7 +39259,7 @@ "input_cost_per_token": 3.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 524288, - "max_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://inferenceapis.com/pricing", @@ -40690,7 +39280,7 @@ "input_cost_per_token": 8.9e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.42e-06, "source": "https://inferenceapis.com/pricing", @@ -40710,7 +39300,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://inferenceapis.com/pricing", @@ -40729,7 +39319,7 @@ "input_cost_per_token": 4e-08, "litellm_provider": "inferenceapis", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.9e-07, "source": "https://inferenceapis.com/pricing", @@ -40748,7 +39338,7 @@ "input_cost_per_token": 2.6e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://inferenceapis.com/pricing", @@ -40768,7 +39358,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40788,7 +39378,7 @@ "input_cost_per_token": 2.6e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://inferenceapis.com/pricing", @@ -40807,7 +39397,7 @@ "input_cost_per_token": 2.6e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://inferenceapis.com/pricing", @@ -40827,7 +39417,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inferenceapis.com/pricing", @@ -40848,7 +39438,7 @@ "input_cost_per_token": 1.82e-06, "litellm_provider": "inferenceapis", "max_input_tokens": 1048575, - "max_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", "output_cost_per_token": 5.72e-06, "source": "https://inferenceapis.com/pricing", @@ -40869,7 +39459,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "inferenceapis", "max_input_tokens": 1048575, - "max_tokens": 1048575, + "max_output_tokens": 1048575, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://inferenceapis.com/pricing", @@ -40891,7 +39481,6 @@ "litellm_provider": "text-completion-inception", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 7.5e-07 }, @@ -40900,7 +39489,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -40914,7 +39502,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -40928,7 +39515,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -40942,7 +39528,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -40955,7 +39540,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -40968,7 +39552,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -40981,7 +39564,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, @@ -40994,7 +39576,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "supports_function_calling": true, @@ -41007,7 +39588,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, @@ -41020,7 +39600,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -41033,7 +39612,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 16384, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -41046,7 +39624,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -41059,7 +39636,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -41072,7 +39648,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, @@ -41085,7 +39660,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -41098,7 +39672,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-08, "supports_function_calling": true, @@ -41112,7 +39685,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-08, "supports_function_calling": true, @@ -41125,7 +39697,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -41138,7 +39709,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -41151,7 +39721,6 @@ "litellm_provider": "lambda_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "supports_function_calling": true, @@ -41196,14 +39765,12 @@ "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.036 }, "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.072 }, @@ -41299,7 +39866,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "chat", "output_cost_per_character": 1.5e-05, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", @@ -41310,7 +39876,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_character": 1e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", @@ -41321,7 +39886,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://aws.amazon.com/bedrock/pricing/" @@ -41331,7 +39895,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.56e-06, "source": "https://aws.amazon.com/bedrock/pricing/" @@ -41342,7 +39905,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -41356,7 +39918,6 @@ "litellm_provider": "bedrock", "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, @@ -41371,7 +39932,6 @@ "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, @@ -41385,7 +39945,6 @@ "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", @@ -41399,7 +39958,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -41412,7 +39970,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -41425,7 +39982,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -41440,7 +39996,6 @@ "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, @@ -41454,7 +40009,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.5e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-70b-instruct.md" @@ -41465,7 +40019,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-8b-instruct.md" @@ -41477,7 +40030,6 @@ "litellm_provider": "bedrock_converse", "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, @@ -41500,7 +40052,6 @@ "litellm_provider": "bedrock_converse", "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, @@ -41522,7 +40073,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.25e-06, "search_context_cost_per_query": { @@ -41563,7 +40113,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.25e-06, "search_context_cost_per_query": { @@ -41604,7 +40153,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "search_context_cost_per_query": { @@ -41645,7 +40193,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.25e-06, "search_context_cost_per_query": { @@ -41686,7 +40233,6 @@ "litellm_provider": "meta", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "search_context_cost_per_query": { @@ -41743,7 +40289,6 @@ "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": { @@ -41784,7 +40329,6 @@ "litellm_provider": "meta_llama", "max_input_tokens": 128000, "max_output_tokens": 4028, - "max_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ @@ -41800,7 +40344,6 @@ "litellm_provider": "meta_llama", "max_input_tokens": 128000, "max_output_tokens": 4028, - "max_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ @@ -41816,7 +40359,6 @@ "litellm_provider": "meta_llama", "max_input_tokens": 1000000, "max_output_tokens": 4028, - "max_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ @@ -41833,7 +40375,6 @@ "litellm_provider": "meta_llama", "max_input_tokens": 10000000, "max_output_tokens": 4028, - "max_tokens": 4028, "mode": "chat", "source": "https://ai.developer.meta.com/docs/models", "supported_modalities": [ @@ -41855,7 +40396,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_batches": 6e-07, @@ -41878,7 +40418,6 @@ "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, @@ -41902,7 +40441,6 @@ "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, @@ -42100,7 +40638,6 @@ "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, @@ -42122,7 +40659,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 40000, - "max_tokens": 40000, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, @@ -42144,7 +40680,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_batches": 1e-07, @@ -42166,7 +40701,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-07, "output_cost_per_token_batches": 5e-08, @@ -42188,7 +40722,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-07, "output_cost_per_token_batches": 7e-08, @@ -42208,7 +40741,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -42219,7 +40751,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large.md", @@ -42230,7 +40761,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -42245,7 +40775,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-06, "output_cost_per_token_batches": 7.5e-07, @@ -42265,7 +40794,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-06, "output_cost_per_token_batches": 1.5e-06, @@ -42278,7 +40806,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 32000, "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", @@ -42293,7 +40820,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-08, "output_cost_per_token_batches": 2e-08, @@ -42313,7 +40839,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-07, "output_cost_per_token_batches": 1.5e-07, @@ -42330,7 +40855,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", @@ -42345,7 +40869,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", @@ -42360,7 +40883,6 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://mistral.ai/technology/", @@ -42373,7 +40895,6 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", @@ -42388,7 +40909,6 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://mistral.ai/news/devstral-2-vibe-cli", @@ -42403,7 +40923,6 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://mistral.ai/news/devstral-2-vibe-cli", @@ -42417,7 +40936,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", @@ -42433,7 +40951,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", @@ -42449,7 +40966,6 @@ "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", @@ -42465,7 +40981,6 @@ "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", @@ -42480,7 +40995,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "source": "https://docs.mistral.ai/models/mistral-embed-23-12" }, @@ -42490,7 +41004,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -42671,7 +41184,6 @@ "litellm_provider": "mistral", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://docs.mistral.ai/models/voxtral-small-25-07", @@ -42686,7 +41198,6 @@ "litellm_provider": "mistral", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://docs.mistral.ai/models/voxtral-small-25-07", @@ -42702,7 +41213,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -42728,7 +41238,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -42750,7 +41259,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "reasoning_effort_levels": [ @@ -42773,7 +41281,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -42795,7 +41302,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -42817,7 +41323,6 @@ "litellm_provider": "mistral", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "reasoning_effort_levels": [ @@ -42896,7 +41401,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", @@ -42913,7 +41417,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", @@ -42928,7 +41431,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding" }, "mistral/codestral-embed": { @@ -42936,7 +41438,6 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding" }, "mistral/codestral-embed-2505": { @@ -42944,7 +41445,6 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "mistral", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding" }, "mistral/mistral-large-4": { @@ -42952,7 +41452,7 @@ "input_cost_per_token": 6.8e-07, "litellm_provider": "mistral", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.09e-06, "reasoning_effort_levels": [ @@ -42973,7 +41473,7 @@ "input_cost_per_token": 6.8e-07, "litellm_provider": "mistral", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.09e-06, "reasoning_effort_levels": [ @@ -42995,7 +41495,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", @@ -43011,7 +41510,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", @@ -43027,7 +41525,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", @@ -43043,7 +41540,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -43064,7 +41560,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -43085,7 +41580,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -43106,7 +41600,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -43127,7 +41620,6 @@ "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-07, "supports_assistant_prefill": true, @@ -43141,7 +41633,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ @@ -43162,7 +41653,6 @@ "litellm_provider": "mistral", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://mistral.ai/pricing", @@ -43178,7 +41668,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://mistral.ai/pricing", @@ -43194,7 +41683,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://mistral.ai/pricing", @@ -43210,7 +41698,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://mistral.ai/pricing", @@ -43226,7 +41713,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://mistral.ai/pricing", @@ -43242,7 +41728,6 @@ "litellm_provider": "mistral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_assistant_prefill": true, @@ -43255,7 +41740,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://mistral.ai/technology/", @@ -43269,7 +41753,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_assistant_prefill": true, @@ -43286,7 +41769,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_batches": 1.25e-06, @@ -43308,7 +41790,6 @@ "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, @@ -43328,7 +41809,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://platform.kimi.ai/docs/pricing/chat-k27-code", @@ -43346,7 +41826,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", @@ -43363,7 +41842,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://platform.kimi.ai/docs/pricing/chat-k26", @@ -43380,7 +41858,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ @@ -43401,7 +41878,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43414,7 +41890,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43428,7 +41903,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43441,7 +41915,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43455,7 +41928,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43468,7 +41940,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43482,7 +41953,6 @@ "litellm_provider": "moonshot", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://platform.moonshot.ai/docs/pricing", @@ -43495,7 +41965,6 @@ "litellm_provider": "morph", "max_input_tokens": 16000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": false, @@ -43509,7 +41978,6 @@ "litellm_provider": "morph", "max_input_tokens": 16000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 1.9e-06, "supports_function_calling": false, @@ -43527,7 +41995,6 @@ "input_cost_per_video_per_second_above_8s_interval": 0.001, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -43551,7 +42018,6 @@ "input_cost_per_video_per_second_above_8s_interval": 0.001, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -43711,7 +42177,6 @@ ] }, "nebius/deepseek-ai/DeepSeek-R1": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 8e-07, @@ -43723,7 +42188,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 164000, "max_input_tokens": 164000, "max_output_tokens": 164000, "input_cost_per_token": 8e-07, @@ -43735,7 +42199,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2.5e-07, @@ -43746,7 +42209,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V3": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 5e-07, @@ -43757,7 +42219,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 5e-07, @@ -43768,7 +42229,6 @@ "source": "https://nebius.com/prices" }, "nebius/google/gemma-3-27b-it": { - "max_tokens": 110000, "max_input_tokens": 110000, "max_output_tokens": 110000, "input_cost_per_token": 1e-07, @@ -43780,7 +42240,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/google%2Fgemma-3-27b-it" }, "nebius/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, @@ -43791,7 +42250,6 @@ "source": "https://nebius.com/prices" }, "nebius/meta-llama/Llama-Guard-3-8B": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-08, @@ -43801,7 +42259,6 @@ "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-08, @@ -43812,7 +42269,6 @@ "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.3e-07, @@ -43823,7 +42279,6 @@ "source": "https://nebius.com/prices" }, "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-06, @@ -43834,7 +42289,6 @@ "source": "https://nebius.com/prices" }, "nebius/mistralai/Mistral-Nemo-Instruct-2407": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 4e-08, @@ -43845,7 +42299,6 @@ "source": "https://nebius.com/prices" }, "nebius/NousResearch/Hermes-3-Llama-3.1-405B": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-06, @@ -43856,7 +42309,6 @@ "source": "https://nebius.com/prices" }, "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 6e-07, @@ -43867,7 +42319,6 @@ "source": "https://nebius.com/prices" }, "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -43878,7 +42329,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-235B-A22B": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-07, @@ -43889,7 +42339,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-32B": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, @@ -43900,7 +42349,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-32B" }, "nebius/Qwen/Qwen3-30B-A3B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -43911,7 +42359,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-14B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 8e-08, @@ -43922,7 +42369,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-4B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 8e-08, @@ -43933,7 +42379,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/QwQ-32B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.5e-07, @@ -43945,7 +42390,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-72B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.3e-07, @@ -43956,7 +42400,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-32B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 6e-08, @@ -43967,7 +42410,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-Coder-7B": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-08, @@ -43978,7 +42420,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2.5-VL-72B-Instruct": { - "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 2.5e-07, @@ -43990,7 +42431,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/image2text/Qwen%2FQwen2.5-VL-72B-Instruct" }, "nebius/Qwen/Qwen2-VL-72B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, @@ -44002,7 +42442,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen2-VL-7B-Instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, @@ -44013,7 +42452,6 @@ "source": "https://nebius.com/prices" }, "nebius/deepseek-ai/DeepSeek-V4-Flash": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.4e-07, @@ -44025,7 +42463,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash" }, "nebius/deepseek-ai/DeepSeek-V4-Flash-0731": { - "max_tokens": 1024000, "max_input_tokens": 1024000, "max_output_tokens": 1024000, "input_cost_per_token": 1.4e-07, @@ -44037,7 +42474,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash-0731" }, "nebius/deepseek-ai/DeepSeek-V4-Pro": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.75e-06, @@ -44063,7 +42499,6 @@ "litellm_provider": "nebius", "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", @@ -44072,7 +42507,6 @@ "supports_vision": true }, "nebius/MiniMaxAI/MiniMax-M2.5": { - "max_tokens": 196608, "max_input_tokens": 196608, "max_output_tokens": 196608, "input_cost_per_token": 3e-07, @@ -44084,7 +42518,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M2.5" }, "nebius/MiniMaxAI/MiniMax-M3": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 3e-07, @@ -44097,7 +42530,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M3" }, "nebius/moonshotai/Kimi-K2.6": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9.5e-07, @@ -44110,7 +42542,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K2.6" }, "nebius/moonshotai/Kimi-K2.7-Code": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9.5e-07, @@ -44123,7 +42554,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/moonshotai%2FKimi-K2.7-Code" }, "nebius/moonshotai/Kimi-K3": { - "max_tokens": 1024000, "max_input_tokens": 1024000, "max_output_tokens": 1024000, "input_cost_per_token": 3e-06, @@ -44136,7 +42566,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K3" }, "nebius/NousResearch/Hermes-4-405B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-06, @@ -44148,7 +42577,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-405B" }, "nebius/NousResearch/Hermes-4-70B": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.3e-07, @@ -44160,7 +42588,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-70B" }, "nebius/nvidia/Cosmos3-Super-Reasoner": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-07, @@ -44173,7 +42600,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/image2text/nvidia%2FCosmos3-Super-Reasoner" }, "nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6e-07, @@ -44184,7 +42610,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FLlama-3_1-Nemotron-Ultra-253B-v1" }, "nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 6e-08, @@ -44196,7 +42621,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNVIDIA-Nemotron-3-Nano-30B-A3B" }, "nebius/nvidia/Nemotron-3-Nano-Omni": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 6e-08, @@ -44209,7 +42633,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Nano-Omni" }, "nebius/nvidia/nemotron-3-super-120b-a12b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 3e-07, @@ -44221,7 +42644,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2Fnemotron-3-super-120b-a12b" }, "nebius/nvidia/Nemotron-3-Ultra-550b-a55b": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1e-06, @@ -44233,7 +42655,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Ultra-550b-a55b" }, "nebius/nvidia/Nemotron-3_5-Lightning": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 6e-08, @@ -44245,7 +42666,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3_5-Lightning" }, "nebius/openai/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, @@ -44257,7 +42677,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/openai%2Fgpt-oss-120b" }, "nebius/openbmb/MiniCPM-V-4_5": { - "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 6.58e-07, @@ -44268,7 +42687,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/image2text/openbmb%2FMiniCPM-V-4_5" }, "nebius/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-07, @@ -44279,7 +42697,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-235B-A22B-Instruct-2507" }, "nebius/Qwen/Qwen3-30B-A3B-Instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-07, @@ -44290,7 +42707,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-30B-A3B-Instruct-2507" }, "nebius/Qwen/Qwen3-Next-80B-A3B-Thinking": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.5e-07, @@ -44302,7 +42718,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-Next-80B-A3B-Thinking" }, "nebius/Qwen/Qwen3.5-397B-A17B": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 6e-07, @@ -44324,7 +42739,6 @@ "supports_reasoning": true }, "nebius/zai-org/GLM-5.1": { - "max_tokens": 202752, "max_input_tokens": 202752, "max_output_tokens": 202752, "input_cost_per_token": 1.4e-06, @@ -44336,7 +42750,6 @@ "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.1" }, "nebius/zai-org/GLM-5.2": { - "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "input_cost_per_token": 1.4e-06, @@ -44351,7 +42764,7 @@ "input_cost_per_token": 1.4e-06, "litellm_provider": "nebius", "max_input_tokens": 1024000, - "max_tokens": 1024000, + "max_output_tokens": 1024000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", @@ -44359,7 +42772,6 @@ "supports_reasoning": true }, "nebius/zai-org/GLM-5.3-Flash": { - "max_tokens": 1024000, "max_input_tokens": 1024000, "max_output_tokens": 1024000, "input_cost_per_token": 1.5e-07, @@ -44372,7 +42784,6 @@ "supports_vision": true }, "nebius/BAAI/bge-en-icl": { - "max_tokens": 32768, "max_input_tokens": 32768, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -44381,7 +42792,6 @@ "source": "https://nebius.com/prices" }, "nebius/BAAI/bge-multilingual-gemma2": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -44390,7 +42800,6 @@ "source": "https://nebius.com/prices" }, "nebius/intfloat/e5-mistral-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -44399,7 +42808,6 @@ "source": "https://nebius.com/prices" }, "nebius/Qwen/Qwen3-Embedding-8B": { - "max_tokens": 40960, "max_input_tokens": 40960, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -44416,7 +42824,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, @@ -44438,7 +42845,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.3e-07, "output_cost_per_token_batches": 1.2e-07, @@ -44459,7 +42865,6 @@ "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, @@ -44482,7 +42887,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.5e-07, "output_cost_per_token_batches": 3.25e-07, @@ -44505,7 +42909,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_batches": 3e-05, @@ -44528,7 +42931,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_batches": 3e-05, @@ -44550,7 +42952,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.0006, "output_cost_per_token_batches": 0.0003, @@ -44584,7 +42985,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 0.0006, "output_cost_per_token_batches": 0.0003, @@ -44622,7 +43022,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, @@ -44663,7 +43062,6 @@ "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", @@ -44696,7 +43094,6 @@ "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", @@ -44733,7 +43130,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, @@ -44776,7 +43172,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -44797,7 +43192,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -44816,7 +43210,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, @@ -44854,7 +43247,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, @@ -44897,7 +43289,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -44925,7 +43316,6 @@ "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", @@ -44958,7 +43348,6 @@ "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", @@ -44995,7 +43384,6 @@ "litellm_provider": "openai", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_batches": 2.2e-06, @@ -45022,7 +43410,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45035,7 +43422,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45048,7 +43434,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.068e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45061,7 +43446,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45075,7 +43459,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45088,7 +43471,6 @@ "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45102,7 +43484,6 @@ "litellm_provider": "oci", "max_input_tokens": 10485760, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45115,7 +43496,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45128,7 +43508,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45141,7 +43520,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45154,7 +43532,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45167,7 +43544,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45180,7 +43556,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -45193,7 +43568,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -45206,7 +43580,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -45219,7 +43592,6 @@ "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45239,7 +43611,6 @@ "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45258,7 +43629,6 @@ "litellm_provider": "oci", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45278,7 +43648,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -45292,7 +43661,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/enterprise-ai/cost-estimator/", @@ -45314,7 +43682,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45326,7 +43693,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45339,7 +43705,6 @@ "litellm_provider": "oci", "max_input_tokens": 256000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 9e-08, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45351,7 +43716,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45363,7 +43727,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.56e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45375,7 +43738,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45388,7 +43750,6 @@ "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45400,7 +43761,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45412,7 +43772,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45424,7 +43783,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [], @@ -45437,7 +43795,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45452,7 +43809,6 @@ "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, @@ -45468,7 +43824,6 @@ "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, @@ -45485,7 +43840,6 @@ "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, @@ -45501,7 +43855,6 @@ "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, @@ -45515,7 +43868,6 @@ "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45527,7 +43879,6 @@ "litellm_provider": "oci", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45542,7 +43893,6 @@ "litellm_provider": "oci", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45557,7 +43907,6 @@ "litellm_provider": "oci", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", @@ -45572,7 +43921,6 @@ "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", @@ -45585,7 +43933,6 @@ "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", @@ -45597,7 +43944,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -45607,7 +43953,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, @@ -45617,7 +43962,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -45627,7 +43971,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, @@ -45637,7 +43980,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -45648,7 +43990,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, @@ -45659,7 +44000,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "oci", "max_input_tokens": 512, - "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 384, @@ -45670,7 +44010,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "oci", "max_input_tokens": 128000, - "max_tokens": 128000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -45682,7 +44021,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": false @@ -45692,7 +44030,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -45701,7 +44038,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -45710,7 +44046,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45720,7 +44055,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45730,7 +44064,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45740,7 +44073,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45750,7 +44082,6 @@ "litellm_provider": "ollama", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45760,7 +44091,6 @@ "litellm_provider": "ollama", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45770,7 +44100,6 @@ "litellm_provider": "ollama", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45780,7 +44109,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45790,7 +44118,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45799,7 +44126,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -45808,7 +44134,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45817,7 +44142,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45826,7 +44150,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45835,7 +44158,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45844,7 +44166,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45854,7 +44175,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45863,7 +44183,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -45872,7 +44191,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "completion", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45882,7 +44200,6 @@ "litellm_provider": "ollama", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45892,7 +44209,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45902,7 +44218,6 @@ "litellm_provider": "ollama", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45912,7 +44227,6 @@ "litellm_provider": "ollama", "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45922,7 +44236,6 @@ "litellm_provider": "ollama", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45932,7 +44245,6 @@ "litellm_provider": "ollama", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -45941,7 +44253,6 @@ "litellm_provider": "ollama", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0, "supports_function_calling": true @@ -45951,7 +44262,6 @@ "litellm_provider": "ollama", "max_input_tokens": 2048, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -45960,7 +44270,6 @@ "litellm_provider": "openai", "max_input_tokens": 32768, "max_output_tokens": 0, - "max_tokens": 0, "mode": "moderation", "output_cost_per_token": 0.0 }, @@ -45969,7 +44278,6 @@ "litellm_provider": "openai", "max_input_tokens": 32768, "max_output_tokens": 0, - "max_tokens": 0, "mode": "moderation", "output_cost_per_token": 0.0 }, @@ -45987,7 +44295,6 @@ "litellm_provider": "bedrock_converse", "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, @@ -46013,7 +44320,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07, "output_cost_per_token_batches": 1.5e-07, @@ -46033,7 +44339,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, @@ -46055,7 +44360,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_batches": 1e-07, @@ -46074,7 +44378,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46088,7 +44391,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46101,7 +44403,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46114,7 +44415,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 6.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46127,7 +44427,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 127000, "max_output_tokens": 127000, - "max_tokens": 127000, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46140,7 +44439,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 118000, "max_output_tokens": 118000, - "max_tokens": 118000, "mode": "chat", "output_cost_per_token": 1.3e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46153,7 +44451,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46167,7 +44464,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 6.3e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46180,7 +44476,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 8.7e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46193,7 +44488,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 9.1e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46207,7 +44501,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.3e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46221,7 +44514,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46235,7 +44527,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 131000, "max_output_tokens": 131000, - "max_tokens": 131000, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46249,7 +44540,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2.9e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46263,7 +44553,6 @@ "litellm_provider": "ovhcloud", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.9e-07, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", @@ -46296,7 +44585,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.4e-06 }, @@ -46305,7 +44593,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -46314,7 +44601,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -46323,7 +44609,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -46332,7 +44617,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07 }, @@ -46341,7 +44625,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -46350,7 +44633,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -46359,7 +44641,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -46369,7 +44650,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-06 }, @@ -46378,7 +44658,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -46388,7 +44667,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -46444,7 +44722,7 @@ "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-06, "search_context_cost_per_query": { @@ -46459,7 +44737,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_reasoning_token": 3e-06, "output_cost_per_token": 8e-06, @@ -46476,7 +44754,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.8e-06 }, @@ -46486,7 +44763,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 12000, "max_output_tokens": 12000, - "max_tokens": 12000, "mode": "chat", "output_cost_per_token": 1.8e-06 }, @@ -46495,7 +44771,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 200000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -46509,7 +44784,7 @@ "input_cost_per_token": 1e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-06, "search_context_cost_per_query": { @@ -46524,7 +44799,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "perplexity", "max_input_tokens": 128000, - "max_tokens": 128000, + "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 8e-06, "search_context_cost_per_query": { @@ -46540,7 +44815,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -46550,7 +44824,6 @@ "litellm_provider": "perplexity", "max_input_tokens": 12000, "max_output_tokens": 12000, - "max_tokens": 12000, "mode": "chat", "output_cost_per_token": 2.8e-07 }, @@ -46559,7 +44832,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46571,7 +44843,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46583,7 +44854,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46595,7 +44865,6 @@ "litellm_provider": "publicai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46607,7 +44876,6 @@ "litellm_provider": "publicai", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46619,7 +44887,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46859,7 +45126,6 @@ "input_cost_per_token": 4e-09, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -46869,7 +45135,6 @@ "input_cost_per_token": 3e-08, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560, @@ -46880,7 +45145,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46892,7 +45156,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46905,7 +45168,6 @@ "litellm_provider": "publicai", "max_input_tokens": 32768, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", @@ -46919,7 +45181,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.8e-06, "supports_function_calling": true, @@ -46934,7 +45195,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8.8e-07, "output_cost_per_token_flex": 4.4e-07, @@ -46954,7 +45214,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_batches": 3e-07, @@ -46973,7 +45232,6 @@ "litellm_provider": "bedrock_converse", "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, @@ -46990,7 +45248,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -47006,7 +45263,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", @@ -47022,7 +45278,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", @@ -47038,7 +45293,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.236e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", @@ -47054,7 +45308,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.41e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", @@ -47070,7 +45323,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.86e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", @@ -47086,7 +45338,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.45e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", @@ -47104,7 +45355,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 2.66e-06, "output_cost_per_token_batches": 1.33e-06, @@ -47125,7 +45375,6 @@ "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, @@ -47180,7 +45429,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, "supports_tool_choice": true @@ -47190,7 +45438,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, "supports_tool_choice": true @@ -47200,7 +45447,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true @@ -47210,7 +45456,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true @@ -47220,7 +45465,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -47230,7 +45474,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -47240,7 +45483,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true @@ -47250,7 +45492,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.75e-06, "supports_tool_choice": true @@ -47260,7 +45501,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8086, "max_output_tokens": 8086, - "max_tokens": 8086, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -47270,7 +45510,6 @@ "litellm_provider": "replicate", "max_input_tokens": 8086, "max_output_tokens": 8086, - "max_tokens": 8086, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -47280,7 +45519,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -47290,7 +45528,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.5e-07, "supports_tool_choice": true @@ -47300,7 +45537,6 @@ "litellm_provider": "replicate", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-06, "supports_tool_choice": true @@ -47429,7 +45665,6 @@ "mode": "chat", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_system_messages": true }, @@ -47584,7 +45819,6 @@ "mode": "chat", "max_input_tokens": 163840, "max_output_tokens": 163840, - "max_tokens": 163840, "supports_function_calling": true, "supports_reasoning": true, "supports_system_messages": true @@ -47605,7 +45839,6 @@ "mode": "chat", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_reasoning": true, "supports_system_messages": true }, @@ -47615,7 +45848,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -47625,7 +45857,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -47635,7 +45866,6 @@ "litellm_provider": "cohere", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -47645,7 +45875,6 @@ "litellm_provider": "cohere", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cohere.com/pricing" @@ -47656,7 +45885,6 @@ "litellm_provider": "cohere", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://cohere.com/pricing" @@ -47687,7 +45915,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -47696,7 +45923,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -47705,7 +45931,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -47714,7 +45939,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -47723,7 +45947,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "completion", "output_cost_per_token": 0.0 }, @@ -47732,7 +45955,6 @@ "litellm_provider": "sagemaker", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -47741,7 +45963,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 196608, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://cloud.sambanova.ai/plans/pricing", @@ -47754,7 +45975,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7e-06, "source": "https://cloud.sambanova.ai/plans/pricing" @@ -47764,7 +45984,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "metadata": { "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" }, @@ -47781,7 +46000,6 @@ "litellm_provider": "sambanova", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.sambanova.ai/plans/pricing", @@ -47790,7 +46008,6 @@ "supports_tool_choice": true }, "sambanova/DeepSeek-V3.1": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-06, @@ -47803,7 +46020,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.2e-07, @@ -47816,7 +46032,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/DeepSeek-V3.2": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 3e-06, @@ -47828,7 +46043,6 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/gemma-4-31B-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3.8e-07, @@ -47844,7 +46058,6 @@ "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", @@ -47859,7 +46072,6 @@ "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", @@ -47875,7 +46087,6 @@ "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", @@ -47891,7 +46102,6 @@ "litellm_provider": "scx-ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.98e-06, "source": "https://scx.ai/pricing", @@ -47908,7 +46118,6 @@ "litellm_provider": "scx-ai", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.99e-06, "source": "https://scx.ai/pricing", @@ -47923,7 +46132,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 200000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, @@ -47939,7 +46147,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 1.35e-06, "output_cost_per_token": 5.4e-06, @@ -47950,56 +46157,48 @@ "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/jamba-1.5-large": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/jamba-1.5-mini": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/jamba-instruct": { "litellm_provider": "snowflake", "max_input_tokens": 256000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama2-70b-chat": { "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3-70b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3-8b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3.1-405b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 1.2e-06, "output_cost_per_token": 1.2e-06, @@ -48010,7 +46209,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 7.2e-07, "output_cost_per_token": 7.2e-07, @@ -48021,7 +46219,6 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 2.4e-07, "output_cost_per_token": 2.4e-07, @@ -48031,18 +46228,15 @@ "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3.2-3b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/llama3.3-70b": { - "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 7.2e-07, @@ -48056,21 +46250,18 @@ "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/mistral-large": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/mistral-large2": { "litellm_provider": "snowflake", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, @@ -48082,39 +46273,33 @@ "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/reka-core": { "litellm_provider": "snowflake", "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/reka-flash": { "litellm_provider": "snowflake", "max_input_tokens": 100000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-arctic": { "litellm_provider": "snowflake", "max_input_tokens": 4096, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-llama-3.1-405b": { "litellm_provider": "snowflake", "max_input_tokens": 8000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat" }, "snowflake/snowflake-llama-3.3-70b": { - "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 7.2e-07, @@ -48311,21 +46496,18 @@ "stability.sd3-5-large-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "stability.sd3-large-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.08 }, "stability.stable-image-core-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, @@ -48501,21 +46683,18 @@ "stability.stable-image-core-v1:1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.04 }, "stability.stable-image-ultra-v1:0": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.14 }, "stability.stable-image-ultra-v1:1": { "litellm_provider": "bedrock", "max_input_tokens": 77, - "max_tokens": 77, "mode": "image_generation", "output_cost_per_image": 0.14 }, @@ -48549,7 +46728,6 @@ "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "completion", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/" @@ -48559,7 +46737,6 @@ "litellm_provider": "text-completion-codestral", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "completion", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/capabilities/code_generation/" @@ -48570,7 +46747,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -48582,7 +46758,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -48593,7 +46768,6 @@ "input_cost_per_token_batches": 6.5e-08, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0, @@ -48605,7 +46779,6 @@ "input_cost_per_token_batches": 1e-08, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0, @@ -48616,7 +46789,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1536, @@ -48627,7 +46799,6 @@ "input_cost_per_token_batches": 5e-08, "litellm_provider": "openai", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0, "output_cost_per_token_batches": 0.0 @@ -48637,7 +46808,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 8192, - "max_tokens": 8192, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 3072, @@ -48647,7 +46817,6 @@ "input_cost_per_token": 6.25e-09, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 3072, - "max_tokens": 3072, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -48659,7 +46828,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-embedding-models", "max_input_tokens": 2048, - "max_tokens": 2048, "mode": "embedding", "output_cost_per_token": 0, "output_vector_size": 768, @@ -48670,7 +46838,6 @@ "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 2.8e-05, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -48680,7 +46847,6 @@ "litellm_provider": "vertex_ai-text-models", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "completion", "output_cost_per_token": 2.8e-05, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -48706,7 +46872,8 @@ "together-ai-8.1b-21b": { "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", - "max_tokens": 1000, + "max_output_tokens": 1000, + "max_input_tokens": 1000, "mode": "chat", "output_cost_per_token": 3e-07 }, @@ -48759,7 +46926,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 65536, "max_output_tokens": 8192, - "max_tokens": 8192, "metadata": { "successor": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" }, @@ -48775,7 +46941,7 @@ "input_cost_per_token": 1.04e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.04e-06, "source": "https://api.together.ai/v1/models", @@ -48802,7 +46968,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.together.ai/v1/models", @@ -48823,7 +46989,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 202752, - "max_tokens": 202752, + "max_output_tokens": 202752, "metadata": { "successor": "together_ai/zai-org/GLM-5.2" }, @@ -48840,7 +47006,7 @@ "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 524288, - "max_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", @@ -48857,7 +47023,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://www.together.ai/pricing", @@ -48867,7 +47033,7 @@ "input_cost_per_token": 0.0, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.together.ai/docs/serverless-models" @@ -48876,7 +47042,7 @@ "input_cost_per_token": 1.7e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://api.together.ai/v1/models", @@ -48891,7 +47057,7 @@ "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://api.together.ai/v1/models", @@ -48902,7 +47068,7 @@ "input_cost_per_token": 1.5e-06, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://www.together.ai/pricing", @@ -48912,7 +47078,7 @@ "input_cost_per_token": 3.2e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.28e-06, "source": "https://api.together.ai/v1/models" @@ -48922,7 +47088,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 1010000, - "max_tokens": 1010000, + "max_output_tokens": 1010000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://api.together.ai/v1/models", @@ -48932,7 +47098,7 @@ "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://api.together.ai/v1/models" @@ -48943,7 +47109,7 @@ "input_cost_per_token": 1.4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://api.together.ai/v1/models", @@ -48958,7 +47124,7 @@ "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", @@ -48972,7 +47138,7 @@ "input_cost_per_token": 1.32e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://api.together.ai/v1/models", @@ -48987,7 +47153,7 @@ "input_cost_per_token": 3.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models", @@ -48998,7 +47164,7 @@ "input_cost_per_token": 1.25e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.25e-06, "source": "https://docs.together.ai/docs/serverless-models", @@ -49011,7 +47177,7 @@ "input_cost_per_token": 3e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ @@ -49033,7 +47199,7 @@ "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 524288, - "max_tokens": 524288, + "max_output_tokens": 524288, "mode": "chat", "output_cost_per_token": 4.05e-06, "source": "https://api.together.ai/v1/models", @@ -49049,7 +47215,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models", @@ -49066,7 +47231,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models", @@ -49083,7 +47247,6 @@ "litellm_provider": "together_ai", "max_input_tokens": 1048575, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://api.together.ai/v1/models", @@ -49168,7 +47331,6 @@ "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, @@ -49187,7 +47349,6 @@ "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, @@ -49208,7 +47369,6 @@ "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, @@ -49229,7 +47389,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_assistant_prefill": true, @@ -49249,7 +47408,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -49277,7 +47435,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -49295,7 +47452,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -49314,7 +47470,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -49332,7 +47487,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -49350,7 +47504,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -49389,7 +47542,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { @@ -49431,7 +47583,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.8e-05, "supports_assistant_prefill": true, @@ -49463,7 +47614,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, @@ -49503,7 +47653,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, @@ -49542,7 +47691,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, @@ -49580,7 +47728,6 @@ "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, @@ -49618,7 +47765,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, @@ -49654,7 +47800,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -49672,7 +47817,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "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", @@ -49688,7 +47832,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "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", @@ -49703,7 +47846,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -49721,7 +47863,6 @@ "litellm_provider": "bedrock_converse", "max_input_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", @@ -49741,7 +47882,6 @@ "litellm_provider": "bedrock_converse", "max_input_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", @@ -49768,7 +47908,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "supports_function_calling": true, "supports_prompt_caching": false, @@ -49785,7 +47924,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "supports_assistant_prefill": true, @@ -49815,7 +47953,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "search_context_cost_per_query": { @@ -49843,7 +47980,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -49880,7 +48016,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "search_context_cost_per_query": { @@ -49917,7 +48052,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.75e-05, "search_context_cost_per_query": { @@ -49957,7 +48091,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "search_context_cost_per_query": { @@ -49988,7 +48121,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", @@ -50004,7 +48136,6 @@ "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, @@ -50025,7 +48156,6 @@ "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, @@ -50043,7 +48173,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -50057,7 +48186,6 @@ "litellm_provider": "bedrock", "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, @@ -50072,7 +48200,6 @@ "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, @@ -50086,7 +48213,6 @@ "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", @@ -50100,7 +48226,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -50113,7 +48238,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "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", @@ -50126,7 +48250,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.2e-07, "source": "https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/bedrock/USD/current/bedrock.json", @@ -50141,7 +48264,6 @@ "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, @@ -50156,7 +48278,6 @@ "litellm_provider": "bedrock_converse", "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, @@ -50179,7 +48300,6 @@ "litellm_provider": "bedrock_converse", "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, @@ -50200,7 +48320,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "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", @@ -50212,7 +48331,6 @@ "litellm_provider": "v0", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -50226,7 +48344,6 @@ "litellm_provider": "v0", "max_input_tokens": 512000, "max_output_tokens": 512000, - "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_function_calling": true, @@ -50240,7 +48357,6 @@ "litellm_provider": "v0", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -50254,7 +48370,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.4e-07 }, @@ -50263,7 +48378,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07 }, @@ -50272,7 +48386,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07 }, @@ -50281,7 +48394,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 40960, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -50292,7 +48404,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 262144, "max_output_tokens": 66536, - "max_tokens": 66536, "mode": "chat", "output_cost_per_token": 1.6e-06, "supports_function_calling": true, @@ -50303,7 +48414,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.4e-07, "supports_vision": true, @@ -50315,7 +48425,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.4e-07, "supports_function_calling": true, @@ -50326,7 +48435,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 300000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3.2e-06, "supports_vision": true, @@ -50338,7 +48446,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -50349,7 +48456,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_vision": true, @@ -50364,7 +48470,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_vision": true, @@ -50379,7 +48484,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4e-06, "supports_vision": true, @@ -50394,7 +48498,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -50409,7 +48512,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -50424,7 +48526,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_vision": true, @@ -50439,7 +48540,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -50452,7 +48552,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -50470,7 +48569,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -50488,7 +48586,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -50507,7 +48604,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -50527,7 +48623,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, @@ -50547,7 +48642,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, @@ -50567,7 +48661,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": true, @@ -50590,7 +48683,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_assistant_prefill": false, @@ -50611,7 +48703,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -50631,7 +48722,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -50648,7 +48738,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -50660,7 +48749,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -50671,7 +48759,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -50682,7 +48769,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -50691,7 +48777,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.19e-06, "supports_tool_choice": true @@ -50701,7 +48786,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 9.9e-07, "supports_function_calling": true, @@ -50713,7 +48797,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 9e-07, "supports_tool_choice": true @@ -50723,7 +48806,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1000000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.5e-06, "supports_vision": true, @@ -50742,7 +48824,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, @@ -50763,7 +48844,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50772,7 +48852,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "supports_vision": true, @@ -50784,7 +48863,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50793,7 +48871,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -50802,7 +48879,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -50811,7 +48887,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.9e-07, "supports_tool_choice": true @@ -50821,7 +48896,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 8e-08, "supports_tool_choice": true @@ -50831,7 +48905,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_tool_choice": true @@ -50841,7 +48914,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8e-08, "supports_function_calling": true, @@ -50852,7 +48924,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.6e-07, "supports_vision": true, @@ -50864,7 +48935,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1e-07 }, @@ -50873,7 +48943,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_function_calling": true, @@ -50884,7 +48953,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_vision": true, @@ -50896,7 +48964,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "supports_function_calling": true, @@ -50907,7 +48974,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 6e-07, "supports_tool_choice": true @@ -50917,7 +48983,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-07, "supports_vision": true, @@ -50929,7 +48994,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 9e-07, "supports_function_calling": true, @@ -50940,7 +49004,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -50949,7 +49012,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.8e-07, "supports_function_calling": true, @@ -50961,7 +49023,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "supports_function_calling": true, @@ -50973,7 +49034,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true @@ -50983,7 +49043,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 4e-08, "supports_function_calling": true, @@ -50994,7 +49053,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1e-07, "supports_vision": true, @@ -51006,7 +49064,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "chat", "output_cost_per_token": 0.0 }, @@ -51015,7 +49072,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -51026,7 +49082,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.9e-07 }, @@ -51035,7 +49090,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -51047,7 +49101,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 65536, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true @@ -51057,7 +49110,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_vision": true, @@ -51070,7 +49122,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 6e-06, "supports_vision": true, @@ -51083,7 +49134,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.2e-06, "supports_function_calling": true, @@ -51094,7 +49144,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.2e-06 }, @@ -51103,7 +49152,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.9e-06 }, @@ -51112,7 +49160,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 16385, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -51123,7 +49170,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 8192, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-06 }, @@ -51132,7 +49178,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-05, "supports_vision": true, @@ -51146,7 +49191,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "supports_vision": true, @@ -51161,7 +49205,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.6e-06, "supports_vision": true, @@ -51176,7 +49219,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1047576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4e-07, "supports_vision": true, @@ -51191,7 +49233,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, @@ -51206,7 +49247,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-07, "supports_vision": true, @@ -51221,7 +49261,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_vision": true, @@ -51236,7 +49275,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_vision": true, @@ -51251,7 +49289,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_function_calling": true, @@ -51265,7 +49302,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, "supports_vision": true, @@ -51278,7 +49314,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51287,7 +49322,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51296,7 +49330,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 0, "max_output_tokens": 0, - "max_tokens": 0, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -51305,7 +49338,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1e-06 }, @@ -51314,7 +49346,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 200000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 1.5e-05 }, @@ -51323,7 +49354,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 5e-06 }, @@ -51332,7 +49362,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 127000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8e-06 }, @@ -51341,7 +49370,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -51353,7 +49381,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_vision": true, @@ -51365,7 +49392,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 4000, - "max_tokens": 4000, "mode": "chat", "output_cost_per_token": 1e-05, "supports_function_calling": true, @@ -51376,7 +49402,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1e-05, "supports_vision": true, @@ -51388,7 +49413,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -51399,7 +49423,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.5e-05, "supports_function_calling": true @@ -51409,7 +49432,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "supports_function_calling": true, @@ -51420,7 +49442,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "supports_function_calling": true, @@ -51431,7 +49452,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_function_calling": true, @@ -51442,7 +49462,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-06, "supports_function_calling": true, @@ -51453,7 +49472,6 @@ "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 128000, "max_output_tokens": 96000, - "max_tokens": 96000, "mode": "chat", "output_cost_per_token": 1.1e-06, "supports_function_calling": true, @@ -51465,7 +49483,6 @@ "input_cost_per_token": 4.5e-07, "max_input_tokens": 200000, "max_output_tokens": 200000, - "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 1.8e-06, "source": "https://vercel.com/ai-gateway/models/glm-4.6", @@ -51516,7 +49533,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -51530,7 +49546,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5e-06, "supports_assistant_prefill": true, @@ -51550,7 +49565,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -51579,7 +49593,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -51602,7 +49615,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -51618,7 +49630,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -51633,7 +49644,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_assistant_prefill": true, @@ -51647,7 +49657,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.25e-06, "supports_assistant_prefill": true, @@ -51661,7 +49670,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, @@ -51675,7 +49683,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 7.5e-05, "supports_assistant_prefill": true, @@ -51688,7 +49695,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -51701,7 +49707,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, "supports_assistant_prefill": true, @@ -51721,7 +49726,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -51756,7 +49760,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -51795,7 +49798,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -51833,7 +49835,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -51870,7 +49871,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -51908,7 +49908,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -51946,7 +49945,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -51984,7 +49982,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -52028,7 +50025,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -52066,7 +50062,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "search_context_cost_per_query": { @@ -52111,7 +50106,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -52150,7 +50144,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -52187,7 +50180,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1.25e-05, @@ -52228,7 +50220,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1.25e-05, @@ -52271,7 +50262,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -52310,7 +50300,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -52350,7 +50339,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -52380,7 +50368,6 @@ "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, @@ -52419,7 +50406,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -52458,7 +50444,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -52482,7 +50467,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -52494,7 +50478,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -52506,7 +50489,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -52518,7 +50500,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -52530,7 +50511,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -52541,7 +50521,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -52552,7 +50531,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true, @@ -52566,7 +50544,6 @@ "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.7e-06, "output_cost_per_token_batches": 8.5e-07, @@ -52588,7 +50565,6 @@ "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.68e-06, "output_cost_per_token_batches": 8.4e-07, @@ -52609,7 +50585,6 @@ "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 65336, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "output_cost_per_token_batches": 2.7e-06, @@ -52632,7 +50607,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_image_token": 3e-05, @@ -52691,7 +50665,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -52726,7 +50699,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -52759,7 +50731,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, @@ -52787,7 +50758,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.0672, "output_cost_per_image_token": 6e-05, @@ -52817,7 +50787,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "image_generation", "output_cost_per_image": 0.0336, "output_cost_per_image_token": 3e-05, @@ -52857,7 +50826,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -52916,7 +50884,6 @@ "litellm_provider": "vertex_ai-language-models", "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, @@ -52977,7 +50944,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -53034,7 +51000,6 @@ "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 65536, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, @@ -53048,7 +51013,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -53059,7 +51023,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -53070,7 +51033,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 8e-06, "supports_tool_choice": true @@ -53081,7 +51043,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -53092,7 +51053,6 @@ "litellm_provider": "vertex_ai-ai21_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4e-07, "supports_tool_choice": true @@ -53122,7 +51082,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "audio_speech", "output_cost_per_image": 0.04, "output_cost_per_token": 0, @@ -53158,7 +51117,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "audio_speech", "output_cost_per_image": 0.08, "output_cost_per_token": 0, @@ -53195,7 +51153,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 1.6e-05, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", @@ -53208,7 +51165,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", @@ -53221,7 +51177,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." }, @@ -53237,7 +51192,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 2048, - "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." }, @@ -53254,7 +51208,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.15e-06, "output_cost_per_token_batches": 5.75e-07, @@ -53276,7 +51229,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.15e-06, "output_cost_per_token_batches": 5.75e-07, @@ -53298,7 +51250,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, - "max_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-07, "output_cost_per_token_batches": 3.5e-07, @@ -53320,7 +51271,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, - "max_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-07, "output_cost_per_token_batches": 3.5e-07, @@ -53341,7 +51291,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", @@ -53352,7 +51301,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", @@ -53363,7 +51311,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", @@ -53376,7 +51323,6 @@ "litellm_provider": "vertex_ai-minimax_models", "max_input_tokens": 196608, "max_output_tokens": 196608, - "max_tokens": 196608, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53390,7 +51336,6 @@ "litellm_provider": "vertex_ai-moonshot_models", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53405,7 +51350,6 @@ "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53423,7 +51367,6 @@ "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53440,7 +51383,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53452,7 +51394,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53464,7 +51405,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53476,7 +51416,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53488,7 +51427,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -53499,7 +51437,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -53510,7 +51447,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -53521,7 +51457,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 6e-06, "supports_function_calling": true, @@ -53532,7 +51467,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-06, "supports_function_calling": true, @@ -53543,7 +51477,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-07, "supports_function_calling": true, @@ -53554,7 +51487,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -53567,7 +51499,6 @@ "litellm_provider": "vertex_ai-mistral_models", "max_input_tokens": 32000, "max_output_tokens": 8191, - "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 3e-07, "supports_function_calling": true, @@ -53601,7 +51532,6 @@ "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 262144, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/maas/google/gemma-4-26b-a4b-it", @@ -53618,7 +51548,6 @@ "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.6e-07, "output_cost_per_token_batches": 1.8e-07, @@ -53631,7 +51560,6 @@ "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53646,7 +51574,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53663,7 +51590,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53683,7 +51609,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, - "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -53703,7 +51628,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 2000000, "max_output_tokens": 2000000, - "max_tokens": 2000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -53724,7 +51648,6 @@ "litellm_provider": "vertex_ai", "max_input_tokens": 200000, "max_output_tokens": 200000, - "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.5e-06, "output_cost_per_token_above_200k_tokens": 5e-06, @@ -53744,7 +51667,6 @@ "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, @@ -53763,7 +51685,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 8.8e-07, "output_cost_per_token_batches": 4.4e-07, @@ -53783,7 +51704,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-06, "output_cost_per_token_batches": 9e-07, @@ -53800,7 +51720,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53816,7 +51735,6 @@ "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -53829,7 +51747,6 @@ "vertex_ai/veo-3.1-generate-preview": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, @@ -53844,7 +51761,6 @@ "vertex_ai/veo-3.1-fast-generate-preview": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -53861,7 +51777,6 @@ "deprecation_date": "2026-11-17", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, @@ -53877,7 +51792,6 @@ "deprecation_date": "2026-11-17", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -53893,7 +51807,6 @@ "vertex_ai/veo-3.1-lite-generate-001": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08, @@ -53911,7 +51824,6 @@ "litellm_provider": "voyage", "max_input_tokens": 16000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -53920,7 +51832,6 @@ "litellm_provider": "voyage", "max_input_tokens": 8000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -53929,7 +51840,6 @@ "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" @@ -53939,7 +51849,6 @@ "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" @@ -53949,7 +51858,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -53958,7 +51866,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0 }, @@ -53967,7 +51874,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" @@ -53977,7 +51883,6 @@ "litellm_provider": "voyage", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "rerank", "output_cost_per_token": 0.0, "source": "https://docs.voyageai.com/docs/pricing" @@ -53986,7 +51891,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4000, - "max_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -53994,7 +51898,6 @@ "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54002,7 +51905,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -54012,7 +51914,6 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54020,7 +51921,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54028,7 +51928,6 @@ "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54036,7 +51935,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54044,7 +51942,6 @@ "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 }, @@ -54052,7 +51949,6 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54060,7 +51956,6 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "voyage", "max_input_tokens": 120000, - "max_tokens": 120000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54068,7 +51963,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54076,7 +51970,6 @@ "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 }, @@ -54084,7 +51977,6 @@ "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, @@ -54094,7 +51986,6 @@ "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 }, @@ -54102,7 +51993,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4096, - "max_tokens": 4096, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54110,7 +52000,6 @@ "input_cost_per_token": 1e-07, "litellm_provider": "voyage", "max_input_tokens": 4000, - "max_tokens": 4000, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -54118,13 +52007,11 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0 }, "wandb/openai/gpt-oss-120b": { "supports_reasoning": true, - "max_tokens": 131072, "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -54135,7 +52022,6 @@ }, "wandb/openai/gpt-oss-20b": { "supports_reasoning": true, - "max_tokens": 131072, "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, @@ -54145,7 +52031,6 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/moonshotai/Kimi-K2.5": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "cache_read_input_token_cost": 1e-07, @@ -54160,7 +52045,6 @@ "supports_vision": true }, "wandb/meta-llama/Llama-3.1-8B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 131000, "max_output_tokens": 128000, "input_cost_per_token": 2.2e-07, @@ -54171,7 +52055,6 @@ }, "wandb/deepseek-ai/DeepSeek-V3.1": { "supports_reasoning": true, - "max_tokens": 128000, "max_input_tokens": 161000, "max_output_tokens": 128000, "input_cost_per_token": 5.5e-07, @@ -54181,7 +52064,6 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 7.1e-07, @@ -54195,7 +52077,6 @@ "litellm_provider": "watsonx", "max_input_tokens": 8192, "max_output_tokens": 1024, - "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 2e-07, "supports_audio_input": false, @@ -54213,7 +52094,6 @@ "litellm_provider": "watsonx", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, "supports_audio_input": false, @@ -54227,7 +52107,6 @@ "supports_vision": false }, "watsonx/bigscience/mt0-xxl-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.908e-06, @@ -54240,7 +52119,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/bigscience/mt0-xxl": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.908e-06, @@ -54253,7 +52131,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/core42/jais-13b-chat": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 0.0005, @@ -54265,7 +52142,6 @@ "supports_vision": false }, "watsonx/google/flan-t5-xl-3b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, @@ -54277,7 +52153,6 @@ "supports_vision": false }, "watsonx/ibm/granite-13b-chat-v2": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, @@ -54289,7 +52164,6 @@ "supports_vision": false }, "watsonx/ibm/granite-13b-instruct-v2": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 6e-07, @@ -54301,7 +52175,6 @@ "supports_vision": false }, "watsonx/ibm/granite-3-3-8b-instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -54313,7 +52186,6 @@ "supports_vision": false }, "watsonx/ibm/granite-4-h-small": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 6.36e-08, @@ -54326,7 +52198,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/ibm/granite-guardian-3-2-2b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -54338,7 +52209,6 @@ "supports_vision": false }, "watsonx/ibm/granite-guardian-3-3-8b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -54350,7 +52220,6 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-1024-96-r2": { - "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, @@ -54362,7 +52231,6 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-1536-96-r2": { - "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, @@ -54374,7 +52242,6 @@ "supports_vision": false }, "watsonx/ibm/granite-ttm-512-96-r2": { - "max_tokens": 512, "max_input_tokens": 512, "max_output_tokens": 512, "input_cost_per_token": 3.8e-07, @@ -54386,7 +52253,6 @@ "supports_vision": false }, "watsonx/ibm/granite-vision-3-2-2b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -54398,7 +52264,6 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-2-11b-vision-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, @@ -54410,7 +52275,6 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-2-1b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1e-07, @@ -54422,7 +52286,6 @@ "supports_vision": false }, "watsonx/meta-llama/llama-3-2-3b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.5e-07, @@ -54434,7 +52297,6 @@ "supports_vision": false }, "watsonx/meta-llama/llama-3-2-90b-vision-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-06, @@ -54446,7 +52308,6 @@ "supports_vision": true }, "watsonx/meta-llama/llama-3-3-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 7.526e-07, @@ -54459,7 +52320,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, @@ -54472,7 +52332,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3.71e-07, @@ -54485,7 +52344,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/meta-llama/llama-guard-3-11b-vision": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, @@ -54497,7 +52355,6 @@ "supports_vision": true }, "watsonx/mistralai/mistral-medium-2505": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3e-06, @@ -54509,7 +52366,6 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-2503": { - "max_tokens": 32000, "max_input_tokens": 32000, "max_output_tokens": 32000, "input_cost_per_token": 1e-07, @@ -54521,7 +52377,6 @@ "supports_vision": false }, "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { - "max_tokens": 16384, "max_input_tokens": 131072, "max_output_tokens": 16384, "input_cost_per_token": 1.06e-07, @@ -54534,7 +52389,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/mistralai/pixtral-12b-2409": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 3.5e-07, @@ -54546,7 +52400,6 @@ "supports_vision": true }, "watsonx/openai/gpt-oss-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.59e-07, @@ -54559,7 +52412,6 @@ "source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx" }, "watsonx/sdaia/allam-1-13b-instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1.8e-06, @@ -54596,7 +52448,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -54621,7 +52472,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -54645,7 +52495,6 @@ "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, @@ -54671,7 +52520,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -54699,7 +52547,6 @@ "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_above_200k_tokens": 5e-06, @@ -54727,7 +52574,6 @@ "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_above_200k_tokens": 5e-06, @@ -54751,7 +52597,6 @@ "litellm_provider": "xai", "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, @@ -54773,7 +52618,6 @@ "litellm_provider": "xai", "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, @@ -54795,7 +52639,6 @@ "litellm_provider": "xai", "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, @@ -54817,7 +52660,6 @@ "litellm_provider": "xai", "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, @@ -54839,7 +52681,6 @@ "litellm_provider": "xai", "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, @@ -54861,7 +52702,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, "output_cost_per_token_batches": 1.1e-06, @@ -54884,7 +52724,6 @@ "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, @@ -54907,7 +52746,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 203000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, @@ -55505,7 +53343,6 @@ } }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 4.5e-07, @@ -55515,7 +53352,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/flux-kontext-pro": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 4e-08, @@ -55524,7 +53360,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/SSD-1B": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -55533,7 +53368,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -55542,7 +53376,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -55551,7 +53384,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -55560,7 +53392,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-13b-python": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -55569,7 +53400,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -55578,7 +53408,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -55587,7 +53416,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-34b-python": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -55596,7 +53424,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -55605,7 +53432,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -55614,7 +53440,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-70b-python": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -55623,7 +53448,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -55632,7 +53456,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -55641,7 +53464,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-llama-7b-python": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -55650,7 +53472,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 2e-07, @@ -55659,7 +53480,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/codegemma-2b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -55668,7 +53488,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/codegemma-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -55677,7 +53496,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-671b-v2-p1": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.2e-06, @@ -55686,7 +53504,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -55695,7 +53512,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55704,7 +53520,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55713,7 +53528,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55722,7 +53536,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55731,7 +53544,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-kontext-max": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 8e-08, @@ -55740,7 +53552,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/dbrx-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.2e-06, @@ -55749,7 +53560,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-1b-base": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, @@ -55758,7 +53568,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-33b-instruct": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -55767,7 +53576,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -55776,7 +53584,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-base-v1p5": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -55785,7 +53592,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -55794,7 +53600,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-base": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -55803,7 +53608,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-lite-instruct": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -55812,7 +53616,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-prover-v2": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1.2e-06, @@ -55821,7 +53624,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55830,7 +53632,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55839,7 +53640,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55848,7 +53648,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55857,7 +53656,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -55866,7 +53664,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55875,7 +53672,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55884,7 +53680,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-v2-lite-chat": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 5e-07, @@ -55893,7 +53688,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/deepseek-v2p5": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1.2e-06, @@ -55902,7 +53696,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/devstral-small-2505": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55911,7 +53704,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -55920,7 +53712,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55929,7 +53720,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dolphin-2-9-2-qwen2-72b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55938,7 +53728,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/dolphin-2p6-mixtral-8x7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -55947,7 +53736,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-21b-a3b-pt": { - "max_tokens": 4096, "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -55956,7 +53744,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ernie-4p5-300b-a47b-pt": { - "max_tokens": 4096, "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -55965,7 +53752,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/fare-20b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -55974,7 +53760,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firefunction-v1": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -55983,7 +53768,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firellava-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -55992,7 +53776,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/firesearch-ocr-v6": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56001,7 +53784,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/fireworks-asr-large": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0.0, @@ -56010,7 +53792,6 @@ "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/fireworks-asr-v2": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0.0, @@ -56019,7 +53800,6 @@ "mode": "audio_transcription" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56028,7 +53808,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev-controlnet-union": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-09, @@ -56037,7 +53816,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-dev-fp8": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 5e-10, @@ -56046,7 +53824,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/flux-1-schnell": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56055,7 +53832,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/flux-1-schnell-fp8": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 3.5e-10, @@ -56064,7 +53840,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/gemma-2b-it": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -56073,7 +53848,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-3-27b-it": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56082,7 +53856,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56091,7 +53864,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma-7b-it": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56100,7 +53872,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gemma2-9b-it": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56109,7 +53880,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/glm-4p5v": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.2e-06, @@ -56119,7 +53889,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-120b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.2e-06, @@ -56128,7 +53897,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-07, @@ -56137,7 +53905,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56146,7 +53913,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-38b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -56155,7 +53921,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-78b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -56164,7 +53929,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/internvl3-8b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -56173,7 +53937,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/japanese-stable-diffusion-xl": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -56182,7 +53945,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/kat-coder": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-07, @@ -56191,7 +53953,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/kat-dev-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56200,7 +53961,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/kat-dev-72b-exp": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56209,7 +53969,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-2-8b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56218,7 +53977,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-3-1b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -56227,7 +53985,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-guard-3-8b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -56236,7 +53993,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56245,7 +54001,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56254,7 +54009,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-70b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56263,7 +54017,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat": { - "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 9e-07, @@ -56272,7 +54025,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-7b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56281,7 +54033,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56290,7 +54041,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 9e-07, @@ -56299,7 +54049,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 9e-07, @@ -56308,7 +54057,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-8b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56317,7 +54065,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56326,7 +54073,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct-long": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56335,7 +54081,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56344,7 +54089,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56353,7 +54097,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56362,7 +54105,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -56371,7 +54113,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -56380,7 +54121,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56389,7 +54129,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llamaguard-7b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56398,7 +54137,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/llava-yi-34b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -56407,7 +54145,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/minimax-m1-80k": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56416,7 +54153,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/minimax-m2": { - "max_tokens": 4096, "max_input_tokens": 196608, "max_output_tokens": 4096, "input_cost_per_token": 3e-07, @@ -56425,7 +54161,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 2e-07, @@ -56434,7 +54169,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-3b-instruct-2512": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 1e-07, @@ -56443,7 +54177,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/ministral-3-8b-instruct-2512": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 2e-07, @@ -56452,7 +54185,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56461,7 +54193,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56470,7 +54201,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56479,7 +54209,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v3": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56488,7 +54217,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56497,7 +54225,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8": { - "max_tokens": 256000, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token": 1.2e-06, @@ -56506,7 +54233,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-nemo-base-2407": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -56515,7 +54241,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -56524,7 +54249,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56533,7 +54257,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 1.2e-06, @@ -56542,7 +54265,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 1.2e-06, @@ -56551,7 +54273,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -56560,7 +54281,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -56569,7 +54289,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -56578,7 +54297,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/mythomax-l2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56587,7 +54305,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl": { - "max_tokens": 4096, "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -56596,7 +54313,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-capybara-7b-v1p9": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56605,7 +54321,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 5e-07, @@ -56614,7 +54329,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-2-yi-34b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -56623,7 +54337,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56632,7 +54345,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -56641,7 +54353,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -56650,7 +54361,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2": { - "max_tokens": 131072, "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -56659,7 +54369,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2": { - "max_tokens": 131072, "max_input_tokens": 128000, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -56668,7 +54377,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openchat-3p5-0106-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -56677,7 +54385,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56686,7 +54393,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56695,7 +54401,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/openorca-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56704,7 +54409,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-2-3b": { - "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 1e-07, @@ -56713,7 +54417,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-3-mini-128k-instruct": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -56722,7 +54425,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct": { - "max_tokens": 32064, "max_input_tokens": 32064, "max_output_tokens": 32064, "input_cost_per_token": 2e-07, @@ -56731,7 +54433,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-python-v1": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -56740,7 +54441,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v1": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -56749,7 +54449,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/phind-code-llama-34b-v2": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 9e-07, @@ -56758,7 +54457,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/playground-v2-1024px-aesthetic": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -56767,7 +54465,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/playground-v2-5-1024px-aesthetic": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -56776,7 +54473,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/pythia-12b": { - "max_tokens": 2048, "max_input_tokens": 2048, "max_output_tokens": 2048, "input_cost_per_token": 2e-07, @@ -56785,7 +54481,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56794,7 +54489,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56803,7 +54497,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen-v2p5-7b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -56812,7 +54505,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen1p5-72b-chat": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56821,7 +54513,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56830,7 +54521,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-2b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56839,7 +54529,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-72b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56848,7 +54537,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2-vl-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56857,7 +54545,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-0p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56866,7 +54553,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-14b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-07, @@ -56875,7 +54561,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-1p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56884,7 +54569,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56893,7 +54577,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56902,7 +54585,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-72b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -56911,7 +54593,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56920,7 +54601,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56929,7 +54609,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56938,7 +54617,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-0p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56947,7 +54625,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56956,7 +54633,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-14b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -56965,7 +54641,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56974,7 +54649,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-1p5b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -56983,7 +54657,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -56992,7 +54665,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -57001,7 +54673,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 9e-07, @@ -57010,7 +54681,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k": { - "max_tokens": 65536, "max_input_tokens": 65536, "max_output_tokens": 65536, "input_cost_per_token": 9e-07, @@ -57019,7 +54689,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -57028,7 +54697,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 1e-07, @@ -57037,7 +54705,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -57046,7 +54713,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -57055,7 +54721,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-math-72b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57064,7 +54729,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 9e-07, @@ -57073,7 +54737,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-3b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -57082,7 +54745,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 9e-07, @@ -57091,7 +54753,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen2p5-vl-7b-instruct": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -57100,7 +54761,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-0p6b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, @@ -57109,7 +54769,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-14b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -57118,7 +54777,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -57127,7 +54785,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1e-07, @@ -57136,7 +54793,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-131072": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1e-07, @@ -57145,7 +54801,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft-40960": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 1e-07, @@ -57154,7 +54809,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2.2e-07, @@ -57163,7 +54817,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -57172,7 +54825,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -57181,7 +54833,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.5e-07, @@ -57190,7 +54841,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 5e-07, @@ -57199,7 +54849,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-07, @@ -57208,7 +54857,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -57218,7 +54866,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/qwen3-4b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -57227,7 +54874,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2e-07, @@ -57236,7 +54882,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-8b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -57246,7 +54891,6 @@ "supports_reasoning": true }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-30b-a3b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -57255,7 +54899,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16": { - "max_tokens": 4096, "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57264,7 +54907,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 0.0, @@ -57273,7 +54915,6 @@ "mode": "embedding" }, "fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, @@ -57282,7 +54923,6 @@ "mode": "embedding" }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57291,7 +54931,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57300,7 +54939,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-0p6b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, @@ -57309,7 +54947,6 @@ "mode": "rerank" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-4b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 0.0, @@ -57318,7 +54955,6 @@ "mode": "rerank" }, "fireworks_ai/accounts/fireworks/models/qwen3-reranker-8b": { - "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, "input_cost_per_token": 2e-07, @@ -57328,7 +54964,6 @@ "source": "https://api.fireworks.ai/v1/serverless/models" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -57337,7 +54972,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.2e-07, @@ -57346,7 +54980,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -57355,7 +54988,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -57364,7 +54996,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-32b-instruct": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57373,7 +55004,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/qwen3-vl-8b-instruct": { - "max_tokens": 4096, "max_input_tokens": 262144, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -57387,7 +55017,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -57398,7 +55027,6 @@ "supports_vision": true }, "fireworks_ai/accounts/fireworks/models/qwq-32b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-07, @@ -57407,7 +55035,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/rolm-ocr": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 2e-07, @@ -57416,7 +55043,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -57425,7 +55051,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/stable-diffusion-xl-1024-v1-0": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1.3e-10, @@ -57434,7 +55059,6 @@ "mode": "image_generation" }, "fireworks_ai/accounts/fireworks/models/stablecode-3b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 1e-07, @@ -57443,7 +55067,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder-16b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -57452,7 +55075,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder-7b": { - "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_token": 2e-07, @@ -57461,7 +55083,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-15b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -57470,7 +55091,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-3b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, @@ -57479,7 +55099,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/starcoder2-7b": { - "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, "input_cost_per_token": 2e-07, @@ -57488,7 +55107,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/toppy-m-7b": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -57497,7 +55115,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57506,7 +55123,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b-200k-capybara": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 9e-07, @@ -57515,7 +55131,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-34b-chat": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 9e-07, @@ -57524,7 +55139,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/yi-6b": { - "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 2e-07, @@ -57533,7 +55147,6 @@ "mode": "chat" }, "fireworks_ai/accounts/fireworks/models/zephyr-7b-beta": { - "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_token": 2e-07, @@ -57547,7 +55160,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -57564,7 +55176,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -57581,7 +55192,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -57596,7 +55206,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 3.6e-06, "supports_function_calling": true, @@ -57608,7 +55217,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.5e-06, "supports_function_calling": true, @@ -57620,7 +55228,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 2.25e-06, "supports_function_calling": true @@ -57636,7 +55243,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, "supports_function_calling": true, @@ -57647,7 +55253,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "supports_function_calling": true @@ -57663,7 +55268,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 5e-07, "supports_function_calling": true, @@ -57675,7 +55279,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 7.5e-06, "supports_reasoning": true, @@ -57688,7 +55291,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.5e-07, "supports_function_calling": true, @@ -57699,7 +55301,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 2e-07, "supports_vision": true, @@ -57717,7 +55318,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 9e-07, "supports_function_calling": true @@ -57729,7 +55329,6 @@ "output_cost_per_token": 4e-07, "max_input_tokens": 163840, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57746,7 +55345,6 @@ "output_cost_per_token": 1.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57762,7 +55360,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57779,7 +55376,6 @@ "output_cost_per_token": 3.3e-07, "max_input_tokens": 262144, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57796,7 +55392,6 @@ "output_cost_per_token": 1.38e-07, "max_input_tokens": 65536, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_vision": true, "supports_system_messages": true }, @@ -57807,7 +55402,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, "max_output_tokens": 100352, - "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57824,7 +55418,6 @@ "output_cost_per_token": 1.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57841,7 +55434,6 @@ "output_cost_per_token": 2e-08, "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_vision": true, "supports_system_messages": true }, @@ -57852,7 +55444,6 @@ "output_cost_per_token": 4.1e-07, "max_input_tokens": 163840, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57867,7 +55458,6 @@ "output_cost_per_token": 3.95e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true, @@ -57881,7 +55471,6 @@ "output_cost_per_token": 9e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57899,7 +55488,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57916,7 +55504,6 @@ "output_cost_per_token": 1.2e-06, "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57932,7 +55519,6 @@ "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57947,7 +55533,6 @@ "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57962,7 +55547,6 @@ "output_cost_per_token": 3e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, @@ -57975,7 +55559,6 @@ "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -57992,7 +55575,6 @@ "output_cost_per_token": 1.5e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58007,7 +55589,6 @@ "output_cost_per_token": 8.45e-06, "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58021,7 +55602,6 @@ "output_cost_per_token": 6e-07, "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, @@ -58034,7 +55614,6 @@ "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58051,7 +55630,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, "max_output_tokens": 100352, - "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58065,7 +55643,6 @@ "output_cost_per_token": 1.55e-06, "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58079,7 +55656,6 @@ "output_cost_per_token": 2.7e-07, "max_input_tokens": 160000, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58093,7 +55669,6 @@ "output_cost_per_token": 2.5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58109,7 +55684,6 @@ "output_cost_per_token": 2.3e-06, "max_input_tokens": 131072, "max_output_tokens": 100352, - "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58123,7 +55697,6 @@ "output_cost_per_token": 1.12e-06, "max_input_tokens": 163840, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58139,7 +55712,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 131072, "max_output_tokens": 98304, - "max_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58155,7 +55727,6 @@ "output_cost_per_token": 3e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58169,7 +55740,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 16384, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_system_messages": true, "supports_response_schema": true }, @@ -58180,7 +55750,6 @@ "output_cost_per_token": 1e-07, "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_vision": true, "supports_system_messages": true, @@ -58193,7 +55762,6 @@ "output_cost_per_token": 1.8e-06, "max_input_tokens": 65536, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58211,7 +55779,6 @@ "output_cost_per_token": 1.5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_tool_choice": true, "supports_vision": false, "supports_system_messages": true, @@ -58225,7 +55792,6 @@ "output_cost_per_token": 5.8e-07, "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58239,7 +55805,6 @@ "output_cost_per_token": 1.5e-07, "max_input_tokens": 32768, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, @@ -58252,7 +55817,6 @@ "output_cost_per_token": 4e-07, "max_input_tokens": 12288, "max_output_tokens": 12288, - "max_tokens": 12288, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58266,7 +55830,6 @@ "output_cost_per_token": 4e-07, "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58280,7 +55843,6 @@ "output_cost_per_token": 1.7e-07, "max_input_tokens": 60288, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -58292,7 +55854,6 @@ "output_cost_per_token": 2.2e-06, "max_input_tokens": 1000000, "max_output_tokens": 40000, - "max_tokens": 40000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58307,7 +55868,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 163840, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58324,7 +55884,6 @@ "output_cost_per_token": 3e-07, "max_input_tokens": 64000, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, @@ -58337,7 +55896,6 @@ "output_cost_per_token": 4e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_system_messages": true, "supports_response_schema": true }, @@ -58348,7 +55906,6 @@ "output_cost_per_token": 6.2e-07, "max_input_tokens": 65535, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_system_messages": true, "supports_response_schema": true }, @@ -58359,7 +55916,6 @@ "output_cost_per_token": 9e-08, "max_input_tokens": 128000, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_system_messages": true, "supports_reasoning": true }, @@ -58370,7 +55926,6 @@ "output_cost_per_token": 8e-07, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, @@ -58383,7 +55938,6 @@ "output_cost_per_token": 7.4e-07, "max_input_tokens": 8192, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -58395,7 +55949,6 @@ "output_cost_per_token": 8e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "supports_response_schema": true @@ -58407,7 +55960,6 @@ "output_cost_per_token": 8.5e-07, "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true @@ -58419,7 +55971,6 @@ "output_cost_per_token": 5.9e-07, "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_vision": true, "supports_system_messages": true }, @@ -58430,7 +55981,6 @@ "output_cost_per_token": 1.4e-07, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -58442,7 +55992,6 @@ "output_cost_per_token": 8e-07, "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_vision": true, "supports_system_messages": true }, @@ -58453,7 +56002,6 @@ "output_cost_per_token": 1.48e-06, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58466,7 +56014,6 @@ "output_cost_per_token": 2.8e-07, "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_system_messages": true, "supports_reasoning": true }, @@ -58477,7 +56024,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -58489,7 +56035,6 @@ "output_cost_per_token": 7e-08, "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-424b-a47b": { @@ -58499,7 +56044,6 @@ "output_cost_per_token": 1.25e-06, "max_input_tokens": 123000, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_vision": true, "supports_system_messages": true, "supports_reasoning": true @@ -58511,7 +56055,6 @@ "output_cost_per_token": 1.1e-06, "max_input_tokens": 123000, "max_output_tokens": 12000, - "max_tokens": 12000, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true @@ -58523,7 +56066,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 160000, "max_output_tokens": 160000, - "max_tokens": 160000, "supports_system_messages": true }, "novita/qwen/qwen3-32b-fp8": { @@ -58533,7 +56075,6 @@ "output_cost_per_token": 4.5e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true }, @@ -58544,7 +56085,6 @@ "output_cost_per_token": 4.5e-07, "max_input_tokens": 40960, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "supports_function_calling": true, @@ -58557,7 +56097,6 @@ "output_cost_per_token": 2e-07, "max_input_tokens": 98304, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_vision": true, "supports_system_messages": true }, @@ -58568,7 +56107,6 @@ "output_cost_per_token": 1.3e-06, "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58581,7 +56119,6 @@ "output_cost_per_token": 2.5e-06, "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58596,7 +56133,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 8192, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58609,7 +56145,6 @@ "output_cost_per_token": 9e-08, "max_input_tokens": 4096, "max_output_tokens": 3200, - "max_tokens": 3200, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-28b-a3b-thinking": { @@ -58619,7 +56154,6 @@ "output_cost_per_token": 3.9e-07, "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58635,7 +56169,6 @@ "output_cost_per_token": 5e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58650,7 +56183,6 @@ "output_cost_per_token": 8.5e-07, "max_input_tokens": 131072, "max_output_tokens": 98304, - "max_tokens": 98304, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58666,7 +56198,6 @@ "output_cost_per_token": 7e-07, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58681,7 +56212,6 @@ "output_cost_per_token": 1e-06, "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58696,7 +56226,6 @@ "output_cost_per_token": 9.7e-07, "max_input_tokens": 65536, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58713,7 +56242,6 @@ "output_cost_per_token": 9.7e-07, "max_input_tokens": 65536, "max_output_tokens": 16384, - "max_tokens": 16384, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58730,7 +56258,6 @@ "output_cost_per_token": 7.5e-07, "max_input_tokens": 16384, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_system_messages": true }, "novita/baidu/ernie-4.5-vl-28b-a3b": { @@ -58740,7 +56267,6 @@ "output_cost_per_token": 5.6e-07, "max_input_tokens": 30000, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58755,7 +56281,6 @@ "output_cost_per_token": 2.8e-07, "max_input_tokens": 120000, "max_output_tokens": 8000, - "max_tokens": 8000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58768,7 +56293,6 @@ "output_cost_per_token": 1.38e-07, "max_input_tokens": 128000, "max_output_tokens": 20000, - "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true }, @@ -58779,7 +56303,6 @@ "output_cost_per_token": 3e-08, "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_system_messages": true, "supports_reasoning": true, "supports_function_calling": true, @@ -58792,7 +56315,6 @@ "output_cost_per_token": 7e-08, "max_input_tokens": 32000, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58806,7 +56328,6 @@ "output_cost_per_token": 5e-08, "max_input_tokens": 32768, "max_output_tokens": 32000, - "max_tokens": 32000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58819,7 +56340,6 @@ "output_cost_per_token": 1.48e-06, "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -58831,8 +56351,7 @@ "input_cost_per_token": 7e-08, "output_cost_per_token": 0, "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768 + "max_output_tokens": 32768 }, "novita/qwen/qwen3-embedding-8b": { "litellm_provider": "novita", @@ -58840,8 +56359,7 @@ "input_cost_per_token": 7e-08, "output_cost_per_token": 0, "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096 + "max_output_tokens": 4096 }, "novita/baai/bge-m3": { "litellm_provider": "novita", @@ -58849,8 +56367,7 @@ "input_cost_per_token": 1e-08, "output_cost_per_token": 1e-08, "max_input_tokens": 8192, - "max_output_tokens": 96000, - "max_tokens": 96000 + "max_output_tokens": 96000 }, "novita/qwen/qwen3-reranker-8b": { "litellm_provider": "novita", @@ -58858,8 +56375,7 @@ "input_cost_per_token": 5e-08, "output_cost_per_token": 5e-08, "max_input_tokens": 32768, - "max_output_tokens": 4096, - "max_tokens": 4096 + "max_output_tokens": 4096 }, "novita/baai/bge-reranker-v2-m3": { "litellm_provider": "novita", @@ -58867,11 +56383,9 @@ "input_cost_per_token": 1e-08, "output_cost_per_token": 1e-08, "max_input_tokens": 8000, - "max_output_tokens": 8000, - "max_tokens": 8000 + "max_output_tokens": 8000 }, "llamagate/llama-3.1-8b": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, @@ -58882,7 +56396,6 @@ "supports_response_schema": true }, "llamagate/llama-3.2-3b": { - "max_tokens": 8192, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, @@ -58893,7 +56406,6 @@ "supports_response_schema": true }, "llamagate/mistral-7b-v0.3": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 1e-07, @@ -58904,7 +56416,6 @@ "supports_response_schema": true }, "llamagate/qwen3-8b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 4e-08, @@ -58915,7 +56426,6 @@ "supports_response_schema": true }, "llamagate/dolphin3-8b": { - "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 8e-08, @@ -58926,7 +56436,6 @@ "supports_response_schema": true }, "llamagate/deepseek-r1-8b": { - "max_tokens": 16384, "max_input_tokens": 65536, "max_output_tokens": 16384, "input_cost_per_token": 1e-07, @@ -58938,7 +56447,6 @@ "supports_reasoning": true }, "llamagate/deepseek-r1-7b-qwen": { - "max_tokens": 16384, "max_input_tokens": 131072, "max_output_tokens": 16384, "input_cost_per_token": 8e-08, @@ -58950,7 +56458,6 @@ "supports_reasoning": true }, "llamagate/openthinker-7b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 8e-08, @@ -58962,7 +56469,6 @@ "supports_reasoning": true }, "llamagate/qwen2.5-coder-7b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 6e-08, @@ -58973,7 +56479,6 @@ "supports_response_schema": true }, "llamagate/deepseek-coder-6.7b": { - "max_tokens": 4096, "max_input_tokens": 16384, "max_output_tokens": 4096, "input_cost_per_token": 6e-08, @@ -58984,7 +56489,6 @@ "supports_response_schema": true }, "llamagate/codellama-7b": { - "max_tokens": 4096, "max_input_tokens": 16384, "max_output_tokens": 4096, "input_cost_per_token": 6e-08, @@ -58995,7 +56499,6 @@ "supports_response_schema": true }, "llamagate/qwen3-vl-8b": { - "max_tokens": 8192, "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_token": 1.5e-07, @@ -59007,7 +56510,6 @@ "supports_vision": true }, "llamagate/llava-7b": { - "max_tokens": 2048, "max_input_tokens": 4096, "max_output_tokens": 2048, "input_cost_per_token": 1e-07, @@ -59018,7 +56520,6 @@ "supports_vision": true }, "llamagate/gemma3-4b": { - "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, "input_cost_per_token": 3e-08, @@ -59030,7 +56531,6 @@ "supports_vision": true }, "llamagate/nomic-embed-text": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 2e-08, "output_cost_per_token": 0, @@ -59038,7 +56538,6 @@ "mode": "embedding" }, "llamagate/qwen3-embedding-8b": { - "max_tokens": 40960, "max_input_tokens": 40960, "input_cost_per_token": 2e-08, "output_cost_per_token": 0, @@ -59046,7 +56545,6 @@ "mode": "embedding" }, "libertai/hermes-3-8b-tee": { - "max_tokens": 16000, "max_input_tokens": 16000, "max_output_tokens": 16000, "input_cost_per_token": 1.5e-07, @@ -59060,7 +56558,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/gemma-4-31b-it": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -59074,7 +56571,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/gemma-4-31b-it-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -59089,7 +56585,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-27b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -59103,7 +56598,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-27b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -59118,7 +56612,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-35b-a3b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -59132,7 +56625,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.6-35b-a3b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 1.5e-07, @@ -59147,7 +56639,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.5-122b-a10b": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.5e-07, @@ -59161,7 +56652,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/qwen3.5-122b-a10b-thinking": { - "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 2.5e-07, @@ -59176,7 +56666,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/deepseek-v4-flash": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 2.5e-07, @@ -59190,7 +56679,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/deepseek-v4-flash-thinking": { - "max_tokens": 200000, "max_input_tokens": 200000, "max_output_tokens": 200000, "input_cost_per_token": 2.5e-07, @@ -59205,7 +56693,6 @@ "source": "https://docs.libertai.io/apis/text/" }, "libertai/bge-m3": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 1e-08, "output_cost_per_token": 0.0, @@ -59221,7 +56708,6 @@ "litellm_provider": "sarvam", "max_input_tokens": 8192, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 0, "supports_reasoning": true @@ -59297,7 +56783,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { @@ -59325,7 +56810,6 @@ "litellm_provider": "openai", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "search_context_cost_per_query": { @@ -59357,7 +56841,6 @@ "litellm_provider": "openai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2.4e-06, @@ -59467,7 +56950,6 @@ "litellm_provider": "gemini", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_token": 0.0, @@ -59488,7 +56970,6 @@ "litellm_provider": "gemini", "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "image_generation", "output_cost_per_image": 0.039, "output_cost_per_token": 0.0, @@ -59511,7 +56992,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -59537,7 +57017,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -59564,7 +57043,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -59599,7 +57077,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -59634,7 +57111,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -59668,7 +57144,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -59701,7 +57176,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -59729,7 +57203,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -59758,7 +57231,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, @@ -59796,7 +57268,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -59833,7 +57304,6 @@ "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 2e-05, "output_cost_per_token": 2e-05, @@ -59860,7 +57330,6 @@ "litellm_provider": "gemini", "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, @@ -59885,7 +57354,6 @@ "litellm_provider": "gemini", "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, @@ -59905,7 +57373,6 @@ "litellm_provider": "gemini", "max_input_tokens": 8192, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "audio_speech", "output_cost_per_audio_token": 1e-05, "output_cost_per_token": 1e-05, @@ -59925,7 +57392,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 3.75e-06, "output_cost_per_token": 3.75e-06, @@ -59984,7 +57450,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -60044,7 +57509,6 @@ "litellm_provider": "gemini", "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, @@ -60106,7 +57570,6 @@ "litellm_provider": "gemini", "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, @@ -60167,7 +57630,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65535, - "max_tokens": 65535, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -60218,7 +57680,6 @@ "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, @@ -60257,7 +57718,6 @@ "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -60299,7 +57759,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token_batches": 3e-07, "output_cost_per_token_priority": 1.05e-06, @@ -60325,7 +57784,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "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, @@ -60351,7 +57809,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token_batches": 3e-07, "output_cost_per_token_priority": 1.05e-06, @@ -60375,7 +57832,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token_batches": 1e-07, "output_cost_per_token_priority": 3.5e-07, @@ -60405,7 +57861,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -60449,7 +57904,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -60484,7 +57938,6 @@ "litellm_provider": "bedrock_mantle", "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, @@ -60520,7 +57973,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -60560,7 +58012,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -60601,7 +58052,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ @@ -60638,7 +58088,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "supported_modalities": [ @@ -60675,7 +58124,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ @@ -60712,7 +58160,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "supported_modalities": [ @@ -60749,7 +58196,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ @@ -60783,7 +58229,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "supported_modalities": [ @@ -60815,7 +58260,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "supported_modalities": [ @@ -60847,7 +58291,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", "supported_modalities": [ @@ -60879,7 +58322,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", "supported_modalities": [ @@ -60914,7 +58356,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "supported_modalities": [ @@ -60955,7 +58396,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "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, @@ -60996,7 +58436,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -61035,7 +58474,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -61082,7 +58520,6 @@ "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, @@ -61123,7 +58560,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -61162,7 +58598,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -61207,7 +58642,6 @@ "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, @@ -61247,7 +58681,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -61282,7 +58715,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -61320,7 +58752,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -61355,7 +58786,6 @@ "supports_bedrock_converse_tool_result_images": false, "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supported_modalities": [ "text", @@ -61395,7 +58825,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -61435,7 +58864,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -61470,7 +58898,6 @@ "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, @@ -61496,7 +58923,6 @@ "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, @@ -61522,7 +58948,6 @@ "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, @@ -61552,7 +58977,6 @@ "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, @@ -61580,7 +59004,6 @@ "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, @@ -61605,7 +59028,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -61636,7 +59058,6 @@ "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": { @@ -61674,7 +59095,6 @@ "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": { @@ -61722,7 +59142,6 @@ "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, @@ -61750,7 +59169,6 @@ "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, @@ -61765,7 +59183,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -61805,7 +59222,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 4.3125e-06, "source": "https://www.volcengine.com/docs/82379/1544106", @@ -61821,7 +59237,6 @@ "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", @@ -61839,7 +59254,6 @@ "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", @@ -61856,7 +59270,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.15625e-06, "source": "https://www.volcengine.com/docs/82379/1544106", @@ -61870,7 +59283,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -61908,7 +59320,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -61946,7 +59357,6 @@ "litellm_provider": "volcengine", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_function_calling": true, @@ -62041,7 +59451,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, @@ -62059,7 +59468,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_function_calling": true, "supports_reasoning": true, @@ -62080,7 +59488,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -62110,7 +59517,6 @@ "supports_tool_search": true, "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", @@ -62132,7 +59538,6 @@ } }, "snowflake/claude-sonnet-4-5": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -62150,7 +59555,6 @@ "snowflake/claude-sonnet-4-6": { "supports_adaptive_thinking": true, "supports_legacy_thinking": true, - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -62166,7 +59570,6 @@ "prompt_cache_min_tokens": 1024 }, "snowflake/claude-4-sonnet": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -62182,7 +59585,6 @@ "prompt_cache_min_tokens": 1024 }, "snowflake/claude-4-opus": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 5e-06, @@ -62199,7 +59601,6 @@ "prompt_cache_min_tokens": 1024 }, "snowflake/claude-haiku-4-5": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 1e-06, @@ -62215,7 +59616,6 @@ "prompt_cache_min_tokens": 4096 }, "snowflake/claude-3-7-sonnet": { - "max_tokens": 16384, "max_input_tokens": 200000, "max_output_tokens": 16384, "input_cost_per_token": 3e-06, @@ -62231,7 +59631,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-4.1": { - "max_tokens": 16384, "max_input_tokens": 300000, "max_output_tokens": 16384, "input_cost_per_token": 2e-06, @@ -62246,7 +59645,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-5": { - "max_tokens": 16384, "max_input_tokens": 300000, "max_output_tokens": 16384, "input_cost_per_token": 1.25e-06, @@ -62262,7 +59660,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-5-mini": { - "max_tokens": 16384, "max_input_tokens": 1000000, "max_output_tokens": 16384, "input_cost_per_token": 3e-07, @@ -62274,7 +59671,6 @@ "supports_response_schema": true }, "snowflake/openai-gpt-5-nano": { - "max_tokens": 16384, "max_input_tokens": 5000000, "max_output_tokens": 16384, "input_cost_per_token": 1.5e-07, @@ -62286,7 +59682,6 @@ "supports_response_schema": true }, "snowflake/llama4-maverick": { - "max_tokens": 16384, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token": 2.4e-07, @@ -62297,7 +59692,6 @@ "supports_system_messages": true }, "snowflake/snowflake-arctic-embed-l-v2.0": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 7e-08, "output_cost_per_token": 0.0, @@ -62305,7 +59699,6 @@ "mode": "embedding" }, "snowflake/snowflake-arctic-embed-m-v2.0": { - "max_tokens": 8192, "max_input_tokens": 8192, "input_cost_per_token": 7e-08, "output_cost_per_token": 0.0, @@ -62315,7 +59708,7 @@ "soniox/stt-async-v4": { "litellm_provider": "soniox", "max_output_tokens": 8000, - "max_tokens": 8000, + "max_input_tokens": 8000, "input_cost_per_second": 0.0, "output_cost_per_second": 2.77778e-05, "mode": "audio_transcription", @@ -62328,7 +59721,7 @@ "soniox/stt-async-v5": { "litellm_provider": "soniox", "max_output_tokens": 8000, - "max_tokens": 8000, + "max_input_tokens": 8000, "input_cost_per_second": 0.0, "output_cost_per_second": 2.77778e-05, "mode": "audio_transcription", @@ -62505,7 +59898,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -62559,7 +59951,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -62613,7 +60004,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -62667,7 +60057,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 2.2e-08, @@ -62721,7 +60110,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -62775,7 +60163,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -62829,7 +60216,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 3e-09, @@ -62883,7 +60269,6 @@ "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "off_peak_pricing": { "cache_read_input_token_cost": 2.2e-08, @@ -62937,7 +60322,6 @@ "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, "source": "https://www.tencentcloud.com/document/product/1300/78937", @@ -62963,7 +60347,6 @@ "litellm_provider": "tencent", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://www.tencentcloud.com/document/product/1300/78937", @@ -62989,7 +60372,6 @@ "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, @@ -63044,7 +60426,6 @@ "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, @@ -63099,7 +60480,6 @@ "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", @@ -63124,7 +60504,6 @@ "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", @@ -63149,7 +60528,6 @@ "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", @@ -63173,7 +60551,6 @@ "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", @@ -63197,7 +60574,6 @@ "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", @@ -63221,7 +60597,6 @@ "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", @@ -63245,7 +60620,6 @@ "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", @@ -63269,7 +60643,6 @@ "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", @@ -63336,7 +60709,6 @@ "source": "https://docs.devin.ai/desktop/models" }, "pinstripes/ps/glm-4.5-air": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_cost_per_token": 1.25e-07, @@ -63349,7 +60721,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3.6-35b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 1.4e-07, @@ -63362,7 +60733,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3-30b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 9e-08, @@ -63375,7 +60745,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/qwen3-coder-30b-a3b": { - "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 3e-07, @@ -63388,7 +60757,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/deepseek-v4-flash": { - "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token": 1e-07, @@ -63401,7 +60769,6 @@ "source": "https://pinstripes.io/" }, "pinstripes/ps/minimax-m2.7": { - "max_tokens": 1000192, "max_input_tokens": 1000192, "max_output_tokens": 1000192, "input_cost_per_token": 2.55e-07, @@ -63418,7 +60785,6 @@ "litellm_provider": "darkbloom", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.65e-07, "source": "https://www.darkbloom.dev/", @@ -63435,7 +60801,6 @@ "litellm_provider": "darkbloom", "max_input_tokens": 131072, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7e-08, "source": "https://www.darkbloom.dev/", @@ -63455,7 +60820,6 @@ "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, @@ -63482,7 +60846,6 @@ "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, @@ -63511,7 +60874,6 @@ "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.x.ai/v1/language-models", @@ -63584,7 +60946,6 @@ "litellm_provider": "openai", "max_input_tokens": 16000, "max_output_tokens": 2000, - "max_tokens": 2000, "mode": "realtime", "source": "https://developers.openai.com/api/docs/pricing", "supported_modalities": [ @@ -63609,7 +60970,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -63653,7 +61013,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -63696,7 +61055,6 @@ "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "prompt_cache_min_tokens": 512, @@ -63732,7 +61090,6 @@ "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": { @@ -63767,7 +61124,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ @@ -63788,7 +61144,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5", @@ -63878,7 +61233,6 @@ "mode": "chat", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, @@ -63977,7 +61331,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 2.1e-05, "output_cost_per_token": 2.1e-05, @@ -64006,7 +61359,6 @@ "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", @@ -64031,7 +61383,6 @@ "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", @@ -64112,7 +61463,6 @@ "input_cost_per_token": 8e-09, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64122,7 +61472,6 @@ "input_cost_per_token": 5e-08, "litellm_provider": "perplexity", "max_input_tokens": 32768, - "max_tokens": 32768, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 2560, @@ -64132,7 +61481,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64142,7 +61490,6 @@ "input_cost_per_token": 6e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64152,7 +61499,6 @@ "input_cost_per_token": 2e-08, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64162,7 +61508,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64172,7 +61517,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 120000, - "max_tokens": 120000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64182,7 +61526,6 @@ "input_cost_per_token": 1.2e-07, "litellm_provider": "voyage", "max_input_tokens": 32000, - "max_tokens": 32000, "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 1024, @@ -64198,7 +61541,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -64217,7 +61559,6 @@ "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, @@ -64237,7 +61578,6 @@ "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, @@ -64257,7 +61597,7 @@ "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -64275,7 +61615,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_priority": 1.875e-05, @@ -64300,7 +61639,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -64319,7 +61657,6 @@ "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, @@ -64339,7 +61676,6 @@ "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, @@ -64359,7 +61695,7 @@ "input_cost_per_token_priority": 2.75e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-07, "output_cost_per_token_priority": 8.25e-07, @@ -64376,7 +61712,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -64393,7 +61728,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -64411,7 +61745,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_priority": 1.875e-05, @@ -64433,7 +61766,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "reasoning_effort_levels": [ @@ -64456,7 +61788,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "output_cost_per_token_priority": 2.8125e-05, @@ -64498,7 +61829,6 @@ "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, @@ -64518,7 +61848,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_priority": 2.5e-07, @@ -64538,7 +61867,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, "output_cost_per_token_priority": 3e-06, @@ -64558,7 +61886,6 @@ "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, @@ -64593,7 +61920,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "output_cost_per_token_priority": 2.5e-07, @@ -64613,7 +61939,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.4e-06, "output_cost_per_token_priority": 3e-06, @@ -64648,7 +61973,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -64665,7 +61989,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -64681,7 +62004,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "reasoning_effort_levels": [ @@ -64704,7 +62026,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.25e-05, "output_cost_per_token_priority": 2.8125e-05, @@ -64726,7 +62047,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -64743,7 +62063,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://novita.ai/pricing", @@ -64760,7 +62079,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://novita.ai/pricing", @@ -64777,7 +62095,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 5.8e-07, "source": "https://novita.ai/pricing", @@ -64794,7 +62111,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://novita.ai/pricing", @@ -64811,7 +62127,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://novita.ai/pricing", @@ -64828,7 +62143,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -64845,7 +62159,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 1.32e-06, "source": "https://novita.ai/pricing", @@ -64862,7 +62175,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://novita.ai/pricing", @@ -64878,7 +62190,6 @@ "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", @@ -64895,7 +62206,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://novita.ai/pricing", @@ -64912,7 +62222,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 393216, - "max_tokens": 393216, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", @@ -64929,7 +62238,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://novita.ai/pricing", @@ -64945,7 +62253,6 @@ "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://novita.ai/pricing", @@ -64962,7 +62269,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://novita.ai/pricing", @@ -64978,7 +62284,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.6e-06, "source": "https://novita.ai/pricing", @@ -64994,7 +62299,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 1.15e-06, "source": "https://novita.ai/pricing", @@ -65010,7 +62314,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.0000000000000002e-07, "source": "https://novita.ai/pricing", @@ -65026,7 +62329,6 @@ "litellm_provider": "novita", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.13e-06, "source": "https://novita.ai/pricing", @@ -65042,7 +62344,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.3600000000000004e-07, "source": "https://novita.ai/pricing", @@ -65059,7 +62360,6 @@ "litellm_provider": "novita", "max_input_tokens": 1000000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.75e-06, "source": "https://novita.ai/pricing", @@ -65076,7 +62376,6 @@ "litellm_provider": "novita", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.044e-06, "source": "https://novita.ai/pricing", @@ -65092,7 +62391,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.6000000000000003e-06, "source": "https://novita.ai/pricing", @@ -65108,7 +62406,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.4e-06, "source": "https://novita.ai/pricing", @@ -65125,7 +62422,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://novita.ai/pricing", @@ -65142,7 +62438,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65159,7 +62454,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65175,7 +62469,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", @@ -65190,7 +62483,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", @@ -65206,7 +62498,6 @@ "litellm_provider": "novita", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65223,7 +62514,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", @@ -65240,7 +62530,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://novita.ai/pricing", @@ -65256,7 +62545,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://novita.ai/pricing", @@ -65271,7 +62559,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", @@ -65286,7 +62573,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://novita.ai/pricing", @@ -65301,7 +62587,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.6000000000000003e-06, "source": "https://novita.ai/pricing", @@ -65317,7 +62602,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://novita.ai/pricing", @@ -65334,7 +62618,6 @@ "litellm_provider": "novita", "max_input_tokens": 202800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.2000000000000003e-06, "source": "https://novita.ai/pricing", @@ -65350,7 +62633,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://novita.ai/pricing", @@ -65364,7 +62646,6 @@ "litellm_provider": "novita", "max_input_tokens": 8192, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 3e-08, "source": "https://novita.ai/pricing", @@ -65376,7 +62657,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://novita.ai/pricing", @@ -65393,7 +62673,6 @@ "litellm_provider": "novita", "max_input_tokens": 204800, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65410,7 +62689,6 @@ "litellm_provider": "novita", "max_input_tokens": 200000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.0000000000000003e-07, "source": "https://novita.ai/pricing", @@ -65426,7 +62704,6 @@ "litellm_provider": "novita", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.4850000000000002e-06, "source": "https://novita.ai/pricing", @@ -65441,7 +62718,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 8.900000000000001e-07, "source": "https://api.novita.ai/v3/openai/models", @@ -65454,7 +62730,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 16000, - "max_tokens": 16000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65468,7 +62743,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 8.900000000000001e-07, "source": "https://api.novita.ai/v3/openai/models", @@ -65481,7 +62755,6 @@ "litellm_provider": "novita", "max_input_tokens": 64000, "max_output_tokens": 8000, - "max_tokens": 8000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65495,7 +62768,6 @@ "litellm_provider": "novita", "max_input_tokens": 32000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 1.66e-06, "source": "https://api.novita.ai/v3/openai/models", @@ -65509,7 +62781,6 @@ "litellm_provider": "novita", "max_input_tokens": 131000, "max_output_tokens": 32000, - "max_tokens": 32000, "mode": "chat", "output_cost_per_token": 2e-08, "source": "https://api.novita.ai/v3/openai/models", @@ -65518,7 +62789,7 @@ }, "wandb/deepseek-ai/DeepSeek-V4-Flash": { "supports_reasoning": true, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1049000, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, @@ -65532,7 +62803,7 @@ }, "wandb/deepseek-ai/DeepSeek-V4-Flash-0731": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 2.8e-07, @@ -65545,7 +62816,7 @@ }, "wandb/deepseek-ai/DeepSeek-V4-Pro": { "supports_reasoning": true, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1049000, "input_cost_per_token": 1.15e-06, "output_cost_per_token": 2.55e-06, @@ -65559,7 +62830,7 @@ }, "wandb/google/gemma-4-31B-it": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3.4e-07, @@ -65570,7 +62841,7 @@ }, "wandb/ibm-granite/granite-4.1-8b": { "deprecation_date": "2026-10-05", - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, @@ -65581,7 +62852,7 @@ }, "wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": { "deprecation_date": "2026-10-05", - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, @@ -65592,7 +62863,7 @@ }, "wandb/meta-llama/Llama-3.1-70B-Instruct": { "deprecation_date": "2026-10-05", - "max_tokens": 128000, + "max_output_tokens": 128000, "max_input_tokens": 131000, "input_cost_per_token": 8e-07, "output_cost_per_token": 8e-07, @@ -65603,7 +62874,7 @@ }, "wandb/MiniMaxAI/MiniMax-M3": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 2.3e-07, "output_cost_per_token": 9.6e-07, @@ -65616,7 +62887,7 @@ }, "wandb/moonshotai/Kimi-K2.7-Code": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 7.1e-07, "output_cost_per_token": 3.5e-06, @@ -65629,7 +62900,7 @@ }, "wandb/moonshotai/Kimi-K2.6": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 6.5e-07, "output_cost_per_token": 3.41e-06, @@ -65642,7 +62913,7 @@ }, "wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 7e-08, "output_cost_per_token": 2e-07, @@ -65655,7 +62926,7 @@ }, "wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.15e-06, @@ -65668,7 +62939,7 @@ }, "wandb/OpenPipe/Qwen3-14B-Instruct": { "deprecation_date": "2026-10-05", - "max_tokens": 32768, + "max_output_tokens": 32768, "max_input_tokens": 32800, "input_cost_per_token": 5e-08, "output_cost_per_token": 2.2e-07, @@ -65679,7 +62950,7 @@ }, "wandb/Qwen/Qwen3.8-27B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 4e-07, "output_cost_per_token": 3e-06, @@ -65692,7 +62963,7 @@ }, "wandb/Qwen/Qwen3.6-35B-A3B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.25e-06, @@ -65703,7 +62974,7 @@ }, "wandb/Qwen/Qwen3.6-27B": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 6e-07, "output_cost_per_token": 3.6e-06, @@ -65718,7 +62989,7 @@ "wandb/Qwen/Qwen3.5-35B-A3B": { "deprecation_date": "2026-10-05", "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.25e-06, @@ -65729,7 +63000,7 @@ }, "wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": { "deprecation_date": "2026-10-05", - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, @@ -65762,7 +63033,7 @@ }, "wandb/zai-org/GLM-5.2": { "supports_reasoning": true, - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 1049000, "input_cost_per_token": 7.6e-07, "output_cost_per_token": 2.42e-06, @@ -65774,7 +63045,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "deepinfra/openai/gpt-oss-120b-Turbo": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, @@ -65788,7 +63059,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M2.7": { - "max_tokens": 196608, + "max_output_tokens": 196608, "max_input_tokens": 196608, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1e-06, @@ -65804,7 +63075,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-27B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4e-07, "output_cost_per_token": 3e-06, @@ -65820,7 +63091,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it-Ultra": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2.7e-07, "output_cost_per_token": 7.6e-07, @@ -65834,7 +63105,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.5": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 2.25e-06, @@ -65850,7 +63121,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.7-Flash": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 6e-08, "output_cost_per_token": 4e-07, @@ -65866,7 +63137,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.6": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 5e-07, "output_cost_per_token": 2e-06, @@ -65885,7 +63156,7 @@ "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 1024, @@ -65899,7 +63170,7 @@ "supports_vision": true }, "deepinfra/anthropic/claude-sonnet-4-6": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, @@ -65915,7 +63186,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.5-flash": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 1.5e-06, "output_cost_per_token": 9e-06, @@ -65930,7 +63201,7 @@ "supports_audio_input": true }, "deepinfra/XiaomiMiMo/MiMo-V2.5": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4e-07, "output_cost_per_token": 2e-06, @@ -65946,7 +63217,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Max": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, @@ -65961,7 +63232,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it-turbo": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 9e-08, "output_cost_per_token": 3.4e-07, @@ -65976,7 +63247,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/thinkingmachines/Inkling-Small": { - "max_tokens": 524288, + "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 1.2e-06, @@ -65992,7 +63263,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-models/Muse-Glimmer-30B": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, @@ -66008,7 +63279,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Max-Thinking": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06, @@ -66023,7 +63294,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 8.8e-07, @@ -66038,7 +63309,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, @@ -66051,7 +63322,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-27B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2.6e-07, "output_cost_per_token": 2.6e-06, @@ -66065,7 +63336,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.6-35B-A3B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1e-07, "output_cost_per_token": 9.5e-07, @@ -66079,7 +63350,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/Nemotron-Content-Safety-3.5": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 2e-07, @@ -66092,7 +63363,7 @@ "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 512, @@ -66106,7 +63377,7 @@ "supports_vision": true }, "deepinfra/thinkingmachines/Inkling": { - "max_tokens": 524288, + "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 9.5e-07, "output_cost_per_token": 4.05e-06, @@ -66122,7 +63393,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.6": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 3.5e-06, @@ -66138,7 +63409,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1.3e-06, "output_cost_per_token": 2.6e-06, @@ -66153,7 +63424,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.7-Max": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 2.5e-06, "output_cost_per_token": 7.5e-06, @@ -66168,7 +63439,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-mini": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1e-07, "output_cost_per_token": 4e-07, @@ -66184,7 +63455,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-2.4T-A95B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, @@ -66200,7 +63471,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M3": { - "max_tokens": 524288, + "max_output_tokens": 524288, "max_input_tokens": 524288, "input_cost_per_token": 2.8e-07, "output_cost_per_token": 1.1e-06, @@ -66216,7 +63487,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.1-flash-lite": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.5e-06, @@ -66231,7 +63502,7 @@ "supports_audio_input": true }, "deepinfra/google/gemini-3.7-flash": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 3.75e-06, @@ -66247,7 +63518,7 @@ "supports_audio_input": true }, "deepinfra/inclusionAI/Ling-3.0-flash": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 6e-08, "output_cost_per_token": 1.8e-07, @@ -66263,7 +63534,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/stepfun-ai/Step-3.7-Flash": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2e-07, "output_cost_per_token": 1.15e-06, @@ -66277,7 +63548,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-35B-A3B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 1e-06, @@ -66293,7 +63564,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-1.8": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06, @@ -66309,7 +63580,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/tencent/Hy3": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 5.8e-07, @@ -66325,7 +63596,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-code": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, @@ -66341,7 +63612,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/ByteDance/Seed-2.0-pro": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 5e-07, "output_cost_per_token": 3e-06, @@ -66357,7 +63628,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 6e-07, "output_cost_per_token": 2.08e-06, @@ -66373,7 +63644,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 5e-08, "output_cost_per_token": 2e-07, @@ -66388,7 +63659,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K2.7-Code": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 6.8e-07, "output_cost_per_token": 3.4e-06, @@ -66407,7 +63678,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1e-05, "prompt_cache_min_tokens": 1024, @@ -66421,7 +63692,7 @@ "supports_vision": true }, "deepinfra/Qwen/Qwen3.5-397B-A17B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 4.5e-07, "output_cost_per_token": 3e-06, @@ -66437,7 +63708,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 8e-08, "output_cost_per_token": 1.8e-07, @@ -66453,7 +63724,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-E4B-it": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-08, "output_cost_per_token": 1e-07, @@ -66466,7 +63737,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.2": { - "max_tokens": 163840, + "max_output_tokens": 163840, "max_input_tokens": 163840, "input_cost_per_token": 2.6e-07, "output_cost_per_token": 3.8e-07, @@ -66481,7 +63752,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.8-Max": { - "max_tokens": 256000, + "max_output_tokens": 256000, "max_input_tokens": 256000, "input_cost_per_token": 1.65e-06, "output_cost_per_token": 4.951e-06, @@ -66499,7 +63770,7 @@ "input_cost_per_token": 1e-05, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 5e-05, "prompt_cache_min_tokens": 512, @@ -66514,7 +63785,7 @@ "thinking_always_on": true }, "deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 5e-07, "output_cost_per_token": 2.2e-06, @@ -66530,7 +63801,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-122B-A10B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 2.9e-07, "output_cost_per_token": 2.4e-06, @@ -66544,7 +63815,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5.1": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 1.05e-06, "output_cost_per_token": 3.5e-06, @@ -66560,7 +63831,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Pro": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1.3e-06, "output_cost_per_token": 2.6e-06, @@ -66575,7 +63846,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 8.5e-08, "output_cost_per_token": 4e-07, @@ -66589,7 +63860,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-5.2": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 7.5e-07, "output_cost_per_token": 2.4e-06, @@ -66605,7 +63876,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/moonshotai/Kimi-K3": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 2.85e-06, "output_cost_per_token": 1.425e-05, @@ -66623,7 +63894,7 @@ "input_cost_per_token": 5e-06, "litellm_provider": "deepinfra", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-05, "prompt_cache_min_tokens": 2048, @@ -66637,7 +63908,7 @@ "supports_vision": true }, "deepinfra/Qwen/Qwen3.6-27B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 3.2e-07, "output_cost_per_token": 3.2e-06, @@ -66651,7 +63922,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-26B-A4B-it": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 7e-08, "output_cost_per_token": 3.4e-07, @@ -66665,7 +63936,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemini-3.1-pro": { - "max_tokens": 1000000, + "max_output_tokens": 1000000, "max_input_tokens": 1000000, "input_cost_per_token": 2e-06, "output_cost_per_token": 1.2e-05, @@ -66680,7 +63951,7 @@ "supports_audio_input": true }, "deepinfra/XiaomiMiMo/MiMo-V2.5-Pro": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 1e-06, "output_cost_per_token": 3e-06, @@ -66696,7 +63967,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-haiku-4-5": { - "max_tokens": 200000, + "max_output_tokens": 200000, "max_input_tokens": 200000, "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, @@ -66711,7 +63982,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V4-Flash": { - "max_tokens": 1048576, + "max_output_tokens": 1048576, "max_input_tokens": 1048576, "input_cost_per_token": 9e-08, "output_cost_per_token": 1.8e-07, @@ -66727,7 +63998,6 @@ "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, @@ -66744,7 +64014,6 @@ "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, @@ -66761,7 +64030,7 @@ "source": "https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash-1017" }, "deepinfra/openai/gpt-oss-120b-Ultra": { - "max_tokens": 131072, + "max_output_tokens": 131072, "max_input_tokens": 131072, "input_cost_per_token": 2e-07, "output_cost_per_token": 9.5e-07, @@ -66775,7 +64044,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3.5-9B": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1e-07, "output_cost_per_token": 1.5e-07, @@ -66788,7 +64057,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo": { - "max_tokens": 196608, + "max_output_tokens": 196608, "max_input_tokens": 196608, "input_cost_per_token": 3.8e-07, "output_cost_per_token": 1.7e-06, @@ -66804,7 +64073,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.7": { - "max_tokens": 202752, + "max_output_tokens": 202752, "max_input_tokens": 202752, "input_cost_per_token": 4e-07, "output_cost_per_token": 1.75e-06, @@ -66820,7 +64089,7 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-4-31B-it": { - "max_tokens": 262144, + "max_output_tokens": 262144, "max_input_tokens": 262144, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 3.8e-07, @@ -66839,7 +64108,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -66874,7 +64142,6 @@ "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, @@ -66902,7 +64169,6 @@ "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, @@ -66930,7 +64196,6 @@ "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, @@ -67206,7 +64471,6 @@ "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, @@ -67233,7 +64497,6 @@ "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, @@ -67260,7 +64523,6 @@ "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, @@ -67291,7 +64553,6 @@ "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, @@ -67319,7 +64580,6 @@ "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://console.groq.com/docs/model/qwen/qwen3.8-27b", @@ -67335,7 +64595,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -67356,7 +64615,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -67377,7 +64635,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 7.5e-06, "reasoning_effort_levels": [ @@ -67398,7 +64655,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6e-07, "reasoning_effort_levels": [ @@ -67419,7 +64675,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", @@ -67434,7 +64689,6 @@ "litellm_provider": "mistral", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://docs.mistral.ai/models/model-cards/codestral-25-08", @@ -67449,7 +64703,6 @@ "litellm_provider": "mistral", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://mistral.ai/news/devstral-2-vibe-cli", @@ -67550,7 +64803,6 @@ "litellm_provider": "mistral", "max_input_tokens": 262144, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 0.0, "source": "https://docs.mistral.ai/models/model-cards/leanstral-1-5", @@ -67566,7 +64818,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, @@ -67585,7 +64836,6 @@ "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, @@ -67604,7 +64854,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-06, "output_cost_per_token_priority": 5.5e-06, @@ -67623,7 +64872,6 @@ "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, @@ -67639,7 +64887,7 @@ "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -67681,7 +64929,7 @@ "input_cost_per_token": 2.1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", @@ -67698,7 +64946,7 @@ "input_cost_per_token_priority": 1.875e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_priority": 6.25e-07, @@ -67716,7 +64964,7 @@ "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, "output_cost_per_token_priority": 9.375e-07, @@ -67733,7 +64981,7 @@ "input_cost_per_token_priority": 1.875e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5e-07, "output_cost_per_token_priority": 6.25e-07, @@ -67751,7 +64999,7 @@ "input_cost_per_token_priority": 2.8125e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 7.5e-07, "output_cost_per_token_priority": 9.375e-07, @@ -67769,7 +65017,7 @@ "input_cost_per_token_priority": 1e-06, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.05e-06, "output_cost_per_token_priority": 4.05e-06, @@ -67785,7 +65033,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 40960, "max_output_tokens": 40960, - "max_tokens": 40960, "mode": "embedding", "source": "https://api.fireworks.ai/v1/serverless/models" }, @@ -67808,7 +65055,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_output_tokens": 1000000, "mode": "chat", "output_cost_per_token": 4.7e-07, "source": "https://api.together.ai/v1/models" @@ -67868,7 +65115,6 @@ "litellm_provider": "cerebras", "max_input_tokens": 131072, "max_output_tokens": 40960, - "max_tokens": 40960, "mode": "chat", "output_cost_per_token": 1.49e-06, "source": "https://api.cerebras.ai/public/v1/models/gemma-4-31b", @@ -67894,7 +65140,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", @@ -67908,7 +65153,6 @@ "litellm_provider": "scaleway", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", @@ -67924,7 +65168,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 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'", @@ -67947,7 +65190,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.2e-06, "supports_function_calling": true, @@ -67989,7 +65231,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -68004,7 +65245,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.1e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -68019,7 +65259,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -68034,7 +65273,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.25e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -68050,7 +65288,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6.6e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -68067,7 +65304,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", @@ -68080,7 +65316,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 7.5e-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'", @@ -68155,7 +65390,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -68173,7 +65407,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "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", @@ -68189,7 +65422,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "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", @@ -68204,7 +65436,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -68222,7 +65453,6 @@ "litellm_provider": "bedrock", "max_input_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", @@ -68242,7 +65472,6 @@ "litellm_provider": "bedrock", "max_input_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", @@ -68267,7 +65496,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, @@ -68306,7 +65534,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, @@ -68344,7 +65571,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, @@ -68381,7 +65607,6 @@ "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, @@ -68419,7 +65644,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, @@ -68454,7 +65678,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 262144, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.88e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -68472,7 +65695,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "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", @@ -68488,7 +65710,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 128000, "max_output_tokens": 8192, - "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", @@ -68503,7 +65724,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.8e-07, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -68521,7 +65741,6 @@ "litellm_provider": "bedrock", "max_input_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", @@ -68541,7 +65760,6 @@ "litellm_provider": "bedrock", "max_input_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", @@ -68566,7 +65784,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "prompt_cache_min_tokens": 1024, @@ -68600,7 +65817,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 1024, @@ -68633,7 +65849,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "prompt_cache_min_tokens": 512, @@ -68665,7 +65880,6 @@ "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, @@ -68698,7 +65912,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "supports_adaptive_thinking": true, @@ -68727,7 +65940,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -68763,7 +65975,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -68799,7 +66010,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -68830,7 +66040,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1048576, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -68854,7 +66063,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -68873,7 +66081,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 128000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "use_openai_responses_path": true, "supported_endpoints": [ @@ -68892,7 +66099,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "use_openai_responses_path": true, "supported_endpoints": [ @@ -68911,7 +66117,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "use_openai_responses_path": true, "supported_endpoints": [ @@ -68931,7 +66136,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "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": [ @@ -68951,7 +66155,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "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": [ @@ -68974,7 +66177,6 @@ "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, @@ -69010,7 +66212,6 @@ "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, @@ -69039,7 +66240,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "use_openai_responses_path": true, "supported_endpoints": [ @@ -69072,7 +66272,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "supported_endpoints": [ "/v1/chat/completions", @@ -69092,7 +66291,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "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": [ @@ -69112,7 +66310,6 @@ "litellm_provider": "bedrock_mantle", "max_input_tokens": 131072, "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": [ @@ -69136,7 +66333,6 @@ "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, @@ -69158,7 +66354,6 @@ "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, @@ -69180,7 +66375,6 @@ "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, @@ -69202,7 +66396,6 @@ "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, @@ -69225,7 +66418,6 @@ "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, @@ -69247,7 +66439,6 @@ "litellm_provider": "bedrock_mantle", "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, @@ -69268,7 +66459,6 @@ "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, @@ -69290,7 +66480,6 @@ "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, @@ -69309,7 +66498,6 @@ "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.375e-05, "supported_endpoints": [ @@ -69343,7 +66531,6 @@ "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, - "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.05e-06, "supports_prompt_caching": true, @@ -69356,7 +66543,6 @@ "input_cost_per_token": 1.63e-07, "litellm_provider": "azure", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -69364,7 +66550,6 @@ "input_cost_per_token": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 8191, - "max_tokens": 8191, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -69395,7 +66580,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_image": 0.04, "output_cost_per_token": 0, @@ -69420,7 +66604,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -69445,7 +66628,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/pricing", @@ -69470,7 +66652,6 @@ "litellm_provider": "gemini", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 0, "source": "https://ai.google.dev/gemini-api/docs/models/lyria-realtime-exp", @@ -69843,7 +67024,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://inference.baseten.co/v1/models", @@ -69867,7 +67047,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://inference.baseten.co/v1/models", @@ -69892,7 +67071,7 @@ "output_cost_per_token": 1.5e-07, "source": "https://api.together.ai/v1/models", "max_input_tokens": 128000, - "max_tokens": 128000 + "max_output_tokens": 128000 }, "vertex_ai/gemini-2.5-flash-native-audio": { "deprecation_date": "2026-12-13", @@ -69953,7 +67132,7 @@ "input_cost_per_token": 1.5e-06, "litellm_provider": "vertex_ai", "max_output_tokens": 57920, - "max_tokens": 57920, + "max_input_tokens": 57920, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, @@ -70016,7 +67195,7 @@ "output_cost_per_token": 3.5e-06, "source": "https://api.together.ai/v1/models", "max_input_tokens": 4096, - "max_tokens": 4096 + "max_output_tokens": 4096 }, "together_ai/meta-llama/Llama-3.2-1B-Instruct": { "input_cost_per_token": 6e-08, @@ -70025,7 +67204,7 @@ "output_cost_per_token": 6e-08, "source": "https://api.together.ai/v1/models", "max_input_tokens": 131072, - "max_tokens": 131072 + "max_output_tokens": 131072 }, "together_ai/meta-llama/Llama-3.2-3B-Instruct": { "input_cost_per_token": 6e-08, @@ -70034,7 +67213,7 @@ "output_cost_per_token": 6e-08, "source": "https://api.together.ai/v1/models", "max_input_tokens": 131072, - "max_tokens": 131072 + "max_output_tokens": 131072 }, "together_ai/Qwen/Qwen2-1.5B-Instruct": { "input_cost_per_token": 2e-08, @@ -70043,7 +67222,7 @@ "output_cost_per_token": 2e-08, "source": "https://api.together.ai/v1/models", "max_input_tokens": 32768, - "max_tokens": 32768 + "max_output_tokens": 32768 }, "together_ai/Qwen/Qwen2.5-14B-Instruct": { "input_cost_per_token": 8e-07, @@ -70052,7 +67231,7 @@ "output_cost_per_token": 8e-07, "source": "https://api.together.ai/v1/models", "max_input_tokens": 32768, - "max_tokens": 32768 + "max_output_tokens": 32768 }, "together_ai/Qwen/Qwen2.5-72B-Instruct": { "input_cost_per_token": 1.2e-06, @@ -70061,14 +67240,13 @@ "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", "max_input_tokens": 32768, - "max_tokens": 32768 + "max_output_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" @@ -70077,7 +67255,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 16384, "mode": "completion", "output_cost_per_token": 2e-07, "source": "https://api.together.xyz/v1/models" @@ -70095,7 +67273,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.together.ai/v1/models" @@ -70105,7 +67283,7 @@ "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" @@ -70115,7 +67293,7 @@ "input_cost_per_token": 9e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://api.together.ai/v1/models" @@ -70125,7 +67303,7 @@ "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" @@ -70135,7 +67313,7 @@ "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" @@ -70145,7 +67323,7 @@ "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "max_input_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://api.together.ai/v1/models" @@ -70155,7 +67333,7 @@ "input_cost_per_token": 1.95e-06, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://api.together.ai/v1/models" @@ -70165,7 +67343,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models" @@ -70175,7 +67353,7 @@ "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models" @@ -70185,7 +67363,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models" @@ -70195,7 +67373,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models" @@ -70205,7 +67383,7 @@ "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://api.together.ai/v1/models" @@ -70215,7 +67393,7 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 6.8e-07, "source": "https://api.together.ai/v1/models" @@ -70226,7 +67404,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.6e-06, "source": "https://api.together.ai/v1/models" @@ -70236,7 +67414,7 @@ "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models" @@ -70246,7 +67424,7 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://api.together.ai/v1/models" @@ -70256,7 +67434,7 @@ "input_cost_per_token": 1.6e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.6e-06, "source": "https://api.together.ai/v1/models" @@ -70266,7 +67444,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.7e-06, "source": "https://api.together.ai/v1/models" @@ -70276,7 +67454,7 @@ "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "max_input_tokens": 16384, - "max_tokens": 16384, + "max_output_tokens": 16384, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://api.together.ai/v1/models" @@ -70286,7 +67464,7 @@ "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 8e-07, "source": "https://api.together.ai/v1/models" @@ -70296,7 +67474,7 @@ "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 9.7e-07, "source": "https://api.together.ai/v1/models" @@ -70306,7 +67484,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://api.together.ai/v1/models" @@ -70316,7 +67494,7 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 5.9e-07, "source": "https://api.together.ai/v1/models" @@ -70326,7 +67504,7 @@ "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://api.together.ai/v1/models" @@ -70336,7 +67514,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 8192, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://api.together.ai/v1/models" @@ -70346,7 +67524,7 @@ "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://api.together.ai/v1/models" @@ -70356,7 +67534,7 @@ "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.8e-07, "source": "https://api.together.ai/v1/models" @@ -70366,7 +67544,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://api.together.ai/v1/models" @@ -70376,7 +67554,7 @@ "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://api.together.ai/v1/models" @@ -70386,7 +67564,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-07, "source": "https://api.together.ai/v1/models" @@ -70397,7 +67575,7 @@ "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://api.together.ai/v1/models" @@ -70408,7 +67586,7 @@ "input_cost_per_token": 9.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://api.together.ai/v1/models" @@ -70418,7 +67596,7 @@ "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, - "max_tokens": 32768, + "max_output_tokens": 32768, "mode": "chat", "output_cost_per_token": 8.8e-07, "source": "https://api.together.ai/v1/models" @@ -70429,7 +67607,7 @@ "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 512288, - "max_tokens": 512288, + "max_output_tokens": 512288, "mode": "chat", "output_cost_per_token": 3.6e-06, "source": "https://api.together.ai/v1/models" @@ -70439,7 +67617,7 @@ "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-07, "source": "https://api.together.ai/v1/models" @@ -70449,7 +67627,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.1e-06, "source": "https://api.together.ai/v1/models" @@ -70459,7 +67637,7 @@ "input_cost_per_token": 4.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 202752, - "max_tokens": 202752, + "max_output_tokens": 202752, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models" @@ -70469,7 +67647,7 @@ "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 202752, - "max_tokens": 202752, + "max_output_tokens": 202752, "mode": "chat", "output_cost_per_token": 3.2e-06, "source": "https://api.together.ai/v1/models" @@ -70480,7 +67658,7 @@ "input_cost_per_token": 1.4e-06, "litellm_provider": "together_ai", "max_input_tokens": 202752, - "max_tokens": 202752, + "max_output_tokens": 202752, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://api.together.ai/v1/models" @@ -70547,7 +67725,6 @@ "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, @@ -70720,7 +67897,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-05, "output_cost_per_token_above_272k_tokens": 9e-05, @@ -70764,7 +67940,6 @@ "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-07, "output_cost_per_token_above_272k_tokens": 9e-07, @@ -70813,7 +67988,6 @@ "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, @@ -70869,7 +68043,6 @@ "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, @@ -70883,7 +68056,6 @@ "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, @@ -70906,7 +68078,6 @@ "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, @@ -70920,7 +68091,6 @@ "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, @@ -70955,7 +68125,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -70977,7 +68146,6 @@ "litellm_provider": "gemini", "max_input_tokens": 131072, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 4.5e-06, @@ -71053,7 +68221,6 @@ "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, @@ -71266,7 +68433,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "output_cost_per_audio_token": 6.4e-05, "output_cost_per_token": 2.4e-05, @@ -71314,7 +68480,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "audio_transcription", "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": [ @@ -71355,7 +68520,6 @@ "litellm_provider": "azure", "max_input_tokens": 32000, "max_output_tokens": 4096, - "max_tokens": 4096, "mode": "realtime", "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_modalities": [ @@ -71373,7 +68537,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 512000, "max_output_tokens": 65500, - "max_tokens": 65500, "mode": "chat", "output_cost_per_token": 1.5e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71386,7 +68549,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71399,7 +68561,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 200000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71414,7 +68575,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71435,7 +68595,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5.5e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71453,7 +68612,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71473,7 +68631,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71494,7 +68651,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71513,7 +68669,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.2e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71528,7 +68683,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.61333e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71557,7 +68711,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.6e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71573,7 +68726,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71587,7 +68739,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 128000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71602,7 +68753,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.84e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71617,7 +68767,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.38e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71632,7 +68781,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.411e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71648,7 +68796,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.4246e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71665,7 +68812,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.0136e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71682,7 +68828,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.411e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71699,7 +68844,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.32375e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71716,7 +68860,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 119000, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.5353e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71729,7 +68872,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71746,7 +68888,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71763,7 +68904,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71780,7 +68920,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71797,7 +68936,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.499999e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71815,7 +68953,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 3.75e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71832,7 +68969,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 3.9998e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71844,7 +68980,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 131100, - "max_tokens": 131100, "mode": "chat", "output_cost_per_token": 3.9998e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71857,7 +68992,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 7.889e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71872,7 +69006,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.9438e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71887,7 +69020,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.9438e-07, "source": "https://aihubmix.com/api/v1/models", @@ -71903,7 +69035,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 200000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.09848e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71917,7 +69048,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71933,7 +69063,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71950,7 +69079,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -71967,7 +69095,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.5e-06, "source": "https://aihubmix.com/api/v1/models", @@ -71984,7 +69111,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.25e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72001,7 +69127,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://aihubmix.com/api/v1/models", @@ -72017,7 +69142,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 0.00018, "source": "https://aihubmix.com/api/v1/models", @@ -72034,7 +69158,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72051,7 +69174,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "source": "https://aihubmix.com/api/v1/models", @@ -72068,7 +69190,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1050000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.2e-05, "source": "https://aihubmix.com/api/v1/models", @@ -72084,7 +69205,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 400000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, "source": "https://aihubmix.com/api/v1/models", @@ -72129,7 +69249,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 500000, "max_output_tokens": 500000, - "max_tokens": 500000, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72145,7 +69264,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72161,7 +69279,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6.248e-07, "source": "https://aihubmix.com/api/v1/models", @@ -72177,7 +69294,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.535e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72193,7 +69309,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.9995e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72209,7 +69324,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 7.999e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72225,7 +69339,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://aihubmix.com/api/v1/models", @@ -72241,7 +69354,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.0984e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72254,7 +69366,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 256000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72290,7 +69401,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 204800, "max_output_tokens": 204800, - "max_tokens": 204800, "mode": "chat", "output_cost_per_token": 1.1832e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72304,7 +69414,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 524288, - "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.152e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72329,7 +69438,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 5.48e-07, "source": "https://aihubmix.com/api/v1/models", @@ -72341,7 +69449,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9.008e-07, "source": "https://aihubmix.com/api/v1/models", @@ -72356,7 +69463,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 9.864e-07, "source": "https://aihubmix.com/api/v1/models", @@ -72371,7 +69477,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 2.532e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72386,7 +69491,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 1.524e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72403,7 +69507,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 262144, "max_output_tokens": 65536, - "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 7.608e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72420,7 +69523,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.128e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72437,7 +69539,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72454,7 +69555,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 3.80025e-07, "source": "https://aihubmix.com/api/v1/models", @@ -72472,7 +69572,6 @@ "litellm_provider": "aihubmix", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5.07e-06, "source": "https://aihubmix.com/api/v1/models", @@ -72657,7 +69756,7 @@ "input_cost_per_token": 2e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.5e-07, "source": "https://wandb.ai/site/pricing/tokens/", @@ -72670,7 +69769,7 @@ "input_cost_per_token": 1e-07, "litellm_provider": "wandb", "max_input_tokens": 262000, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-07, "source": "https://wandb.ai/site/pricing/tokens/", @@ -72711,7 +69810,6 @@ "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, @@ -72743,7 +69841,6 @@ "token_count_tokenizer": "kimi_k3", "max_input_tokens": 1000000, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_flex": 7.5e-06, @@ -72775,7 +69872,6 @@ "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, @@ -72797,7 +69893,6 @@ "litellm_provider": "xiaomi_mimo", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 8.7e-07, "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", @@ -72820,7 +69915,6 @@ "litellm_provider": "xiaomi_mimo", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2.8e-07, "source": "https://platform.xiaomimimo.com/static/docs/price/pay-as-you-go.md", @@ -72845,7 +69939,6 @@ "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, @@ -72871,7 +69964,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -72893,7 +69985,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -72915,7 +70006,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -72937,7 +70027,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -72958,7 +70047,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -72980,7 +70068,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73001,7 +70088,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73023,7 +70109,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73045,7 +70130,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73066,7 +70150,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73088,7 +70171,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73110,7 +70192,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73131,7 +70212,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73153,7 +70233,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73178,7 +70257,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73203,7 +70281,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "responses", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73228,7 +70305,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73249,7 +70325,6 @@ "litellm_provider": "xai", "max_input_tokens": 1000000, "max_output_tokens": 1000000, - "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 2.5e-06, "source": "https://api.x.ai/v1/language-models", @@ -73271,7 +70346,6 @@ "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", @@ -73289,7 +70363,6 @@ "litellm_provider": "baseten", "max_input_tokens": 262000, "max_output_tokens": 262000, - "max_tokens": 262000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://inference.baseten.co/v1/models", @@ -73307,7 +70380,6 @@ "litellm_provider": "baseten", "max_input_tokens": 262000, "max_output_tokens": 262000, - "max_tokens": 262000, "mode": "chat", "output_cost_per_token": 4e-06, "source": "https://inference.baseten.co/v1/models", @@ -73324,7 +70396,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-05, "source": "https://inference.baseten.co/v1/models", @@ -73341,7 +70412,6 @@ "litellm_provider": "baseten", "max_input_tokens": 202800, "max_output_tokens": 202800, - "max_tokens": 202800, "mode": "chat", "output_cost_per_token": 2.4e-06, "source": "https://inference.baseten.co/v1/models", @@ -73359,7 +70429,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 4.05e-06, "source": "https://inference.baseten.co/v1/models", @@ -73377,7 +70446,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 32768, - "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://inference.baseten.co/v1/models", @@ -73394,7 +70462,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://inference.baseten.co/v1/models", @@ -73411,7 +70478,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://inference.baseten.co/v1/models", @@ -73428,7 +70494,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 384000, - "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 2.6e-07, "source": "https://inference.baseten.co/v1/models", @@ -73446,7 +70511,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.48e-06, "source": "https://inference.baseten.co/v1/models", @@ -73463,7 +70527,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.96e-06, "source": "https://inference.baseten.co/v1/models", @@ -73480,7 +70543,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 262144, - "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 6.6e-06, "source": "https://inference.baseten.co/v1/models", @@ -73500,7 +70562,6 @@ "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_above_200k_tokens": 4e-06, @@ -73521,7 +70582,6 @@ "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_above_200k_tokens": 4e-06, @@ -73542,7 +70602,6 @@ "litellm_provider": "xai", "max_input_tokens": 256000, "max_output_tokens": 256000, - "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2e-06, "output_cost_per_token_above_200k_tokens": 4e-06, @@ -73563,7 +70622,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_priority": 1.2e-06, @@ -73581,7 +70639,6 @@ "litellm_provider": "fireworks_ai", "max_input_tokens": 196608, "max_output_tokens": 196608, - "max_tokens": 196608, "mode": "chat", "output_cost_per_token_priority": 1.2e-06, "source": "https://api.fireworks.ai/v1/serverless/models", @@ -73647,7 +70704,6 @@ "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 4.4e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", @@ -73665,7 +70721,6 @@ "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 7.2e-07, "output_cost_per_token_batches": 3.6e-07, @@ -73684,7 +70739,6 @@ "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", @@ -73700,7 +70754,6 @@ "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, @@ -73717,7 +70770,6 @@ "deprecation_date": "2026-06-30", "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, - "max_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.5, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#veo", @@ -73764,7 +70816,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -73797,7 +70848,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -73830,7 +70880,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -73863,7 +70912,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -73901,7 +70949,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -73934,7 +70981,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_adaptive_thinking": true, "thinking_always_on": true, @@ -73970,7 +71016,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -74009,7 +71054,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -74049,7 +71093,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -74087,7 +71130,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -74126,7 +71168,6 @@ "supports_tool_search": true, "max_input_tokens": 1000000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "supports_assistant_prefill": false, "supports_computer_use": true, @@ -74159,7 +71200,6 @@ "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, @@ -74197,7 +71237,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, @@ -74217,7 +71256,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, @@ -74237,7 +71275,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "thinking_always_on": true, "supports_function_calling": true, @@ -74259,7 +71296,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 8192, - "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-r1.html", @@ -74272,7 +71308,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 128000, "max_output_tokens": 16384, - "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6e-06, "source": "https://aws.amazon.com/bedrock/pricing/", @@ -74285,7 +71320,6 @@ "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/", @@ -74321,7 +71355,6 @@ "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": { @@ -74359,7 +71392,6 @@ "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, @@ -74405,7 +71437,6 @@ "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": { @@ -74447,7 +71478,6 @@ "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": { @@ -74484,7 +71514,6 @@ "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, @@ -74521,7 +71550,6 @@ "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, @@ -74562,7 +71590,6 @@ "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": { @@ -74609,7 +71636,6 @@ "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": { @@ -74651,7 +71677,6 @@ "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": { @@ -74783,7 +71808,6 @@ "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, @@ -74829,7 +71853,6 @@ "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": { @@ -74874,7 +71897,6 @@ "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, @@ -74914,7 +71936,6 @@ "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, @@ -74947,7 +71968,6 @@ "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", @@ -74972,7 +71992,6 @@ "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", @@ -75005,7 +72024,6 @@ "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, @@ -75031,7 +72049,6 @@ "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, @@ -75049,7 +72066,6 @@ "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", @@ -75104,7 +72120,6 @@ "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, @@ -75172,7 +72187,6 @@ "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, @@ -75218,7 +72232,6 @@ "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, @@ -75266,7 +72279,6 @@ "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, @@ -75301,7 +72313,6 @@ "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, @@ -75315,7 +72326,6 @@ "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, @@ -75332,7 +72342,6 @@ "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, @@ -75350,7 +72359,6 @@ "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/", @@ -75383,7 +72391,6 @@ "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, @@ -75416,7 +72423,6 @@ "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, @@ -75439,7 +72445,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 256000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2.75e-06, @@ -75454,7 +72459,6 @@ "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/", @@ -75474,7 +72478,6 @@ "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, @@ -75519,7 +72522,6 @@ "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, @@ -75565,7 +72567,6 @@ "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, @@ -75609,7 +72610,6 @@ "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, @@ -75637,7 +72637,6 @@ "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, @@ -75670,7 +72669,6 @@ "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, @@ -75724,7 +72722,6 @@ "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": { @@ -75771,7 +72768,6 @@ "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": true, @@ -75816,7 +72812,6 @@ "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": { @@ -75859,7 +72854,6 @@ "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, @@ -75910,7 +72904,6 @@ "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": { @@ -75957,7 +72950,6 @@ "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": { @@ -75999,7 +72991,6 @@ "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": true, @@ -76041,7 +73032,6 @@ "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": true, @@ -76087,7 +73077,6 @@ "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": { @@ -76139,7 +73128,6 @@ "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": { @@ -76186,7 +73174,6 @@ "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": { @@ -76245,7 +73232,6 @@ "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": true, @@ -76296,7 +73282,6 @@ "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": { @@ -76346,7 +73331,6 @@ "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, @@ -76391,7 +73375,6 @@ "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, @@ -76430,7 +73413,6 @@ "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", @@ -76441,7 +73423,6 @@ "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", @@ -76452,7 +73433,6 @@ "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", @@ -76488,7 +73468,6 @@ "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, @@ -76508,7 +73487,6 @@ "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, @@ -76577,7 +73555,6 @@ "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, @@ -76623,7 +73600,6 @@ "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, @@ -76673,7 +73649,6 @@ "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, @@ -76732,7 +73707,6 @@ "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, @@ -76790,7 +73764,6 @@ "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, @@ -76838,7 +73811,6 @@ "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", @@ -76851,7 +73823,6 @@ "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, @@ -76863,7 +73834,6 @@ "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, @@ -76875,7 +73845,6 @@ "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, @@ -76954,7 +73923,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 262144, "mode": "chat", "output_cost_per_token": 5e-07, "source": "https://api.together.ai/v1/models", @@ -76977,7 +73946,6 @@ "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, @@ -76999,7 +73967,6 @@ "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", @@ -77023,7 +73990,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-05, "prompt_cache_min_tokens": 512.0, @@ -77053,7 +74019,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 4.25e-06, "source": "https://inference.baseten.co/v1/models", @@ -77071,7 +74036,6 @@ "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", @@ -77087,7 +74051,7 @@ "input_cost_per_token": 1.5e-07, "litellm_provider": "wandb", "max_input_tokens": 1049000, - "max_tokens": 943718, + "max_output_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", @@ -77103,7 +74067,7 @@ "input_cost_per_token": 4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", @@ -77117,7 +74081,6 @@ "litellm_provider": "baseten", "max_input_tokens": 1048576, "max_output_tokens": 131072, - "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://inference.baseten.co/v1/models", @@ -77131,7 +74094,7 @@ "input_cost_per_token": 2.5e-07, "litellm_provider": "nebius", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1e-06, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/reflection%2Fbeam", @@ -77144,7 +74107,6 @@ "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", @@ -77161,7 +74123,6 @@ "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", @@ -77180,7 +74141,6 @@ "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, @@ -77200,7 +74160,6 @@ "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", @@ -77222,7 +74181,6 @@ "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", @@ -77244,7 +74202,6 @@ "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, @@ -77266,7 +74223,6 @@ "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, @@ -77288,7 +74244,6 @@ "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, @@ -77307,7 +74262,7 @@ "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, - "max_tokens": 1048576, + "max_output_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, "source": "https://api.together.ai/v1/models", @@ -77344,7 +74299,6 @@ "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, @@ -77380,7 +74334,6 @@ "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, @@ -77429,7 +74382,6 @@ "litellm_provider": "azure_ai", "max_input_tokens": 256000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.2e-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'", @@ -77459,7 +74411,6 @@ "input_cost_per_token": 2e-06, "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 5e-07, - "max_tokens": 500000, "max_output_tokens": 500000, "max_input_tokens": 500000, "supports_function_calling": true, @@ -77497,7 +74448,6 @@ "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, "cache_creation_input_token_cost": 1.25e-07, - "max_tokens": 128000, "max_output_tokens": 128000, "max_input_tokens": 922000, "supports_function_calling": true, @@ -77537,7 +74487,6 @@ "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 2e-08, "cache_creation_input_token_cost": 2.5e-07, - "max_tokens": 128000, "max_output_tokens": 128000, "max_input_tokens": 922000, "supports_function_calling": true, @@ -77577,7 +74526,6 @@ "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, "cache_creation_input_token_cost": 1.25e-07, - "max_tokens": 128000, "max_output_tokens": 128000, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77616,7 +74564,6 @@ "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 1e-07, - "max_tokens": 65536, "max_output_tokens": 65536, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77633,7 +74580,6 @@ "input_cost_per_token": 1.5e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 3e-08, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77650,7 +74596,6 @@ "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77667,7 +74612,6 @@ "input_cost_per_token": 1.4e-06, "output_cost_per_token": 4.4e-06, "cache_read_input_token_cost": 2.6e-07, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77685,7 +74629,6 @@ "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 2.0000000000000002e-07, "cache_creation_input_token_cost": 2e-06, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77703,7 +74646,6 @@ "output_cost_per_token": 1.5e-05, "cache_read_input_token_cost": 3e-07, "cache_creation_input_token_cost": 3e-06, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77720,7 +74662,6 @@ "input_cost_per_token": 9.499999999999999e-07, "output_cost_per_token": 4e-06, "cache_read_input_token_cost": 1.9e-07, - "max_tokens": 262144, "max_output_tokens": 262144, "max_input_tokens": 262144, "supports_function_calling": true, @@ -77737,7 +74678,6 @@ "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 6e-09, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77754,7 +74694,6 @@ "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 6e-09, - "max_tokens": 384000, "max_output_tokens": 384000, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77771,7 +74710,6 @@ "input_cost_per_token": 1.32e-06, "output_cost_per_token": 3.96e-06, "cache_read_input_token_cost": 4.4e-08, - "max_tokens": 384000, "max_output_tokens": 384000, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77788,7 +74726,6 @@ "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 2.8e-09, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77805,7 +74742,6 @@ "input_cost_per_token": 4.35e-07, "output_cost_per_token": 8.7e-07, "cache_read_input_token_cost": 3.625e-09, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77822,7 +74758,6 @@ "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 2.8e-09, - "max_tokens": 128000, "max_output_tokens": 128000, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77839,7 +74774,6 @@ "input_cost_per_token": 4.35e-07, "output_cost_per_token": 8.7e-07, "cache_read_input_token_cost": 3.625e-09, - "max_tokens": 128000, "max_output_tokens": 128000, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77856,7 +74790,6 @@ "input_cost_per_token": 1.5e-07, "output_cost_per_token": 6e-07, "cache_read_input_token_cost": 1.5e-08, - "max_tokens": 512000, "max_output_tokens": 512000, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77873,7 +74806,6 @@ "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "cache_read_input_token_cost": 6e-08, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77890,7 +74822,6 @@ "input_cost_per_token": 1.0000000000000001e-07, "output_cost_per_token": 2.0000000000000002e-07, "cache_read_input_token_cost": 2e-09, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77907,7 +74838,6 @@ "input_cost_per_token": 1.0000000000000001e-07, "output_cost_per_token": 2.0000000000000002e-07, "cache_read_input_token_cost": 2e-09, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -77925,7 +74855,6 @@ "output_cost_per_token": 6e-06, "cache_read_input_token_cost": 2.5e-07, "cache_creation_input_token_cost": 2.5e-06, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77943,7 +74872,6 @@ "output_cost_per_token": 4.6999999999999995e-07, "cache_read_input_token_cost": 1.6e-08, "cache_creation_input_token_cost": 2.0000000000000002e-07, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -77961,7 +74889,6 @@ "output_cost_per_token": 1.6000000000000001e-06, "cache_read_input_token_cost": 4e-08, "cache_creation_input_token_cost": 5e-07, - "max_tokens": 65536, "max_output_tokens": 65536, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -78000,7 +74927,6 @@ "input_cost_per_token": 8.34e-07, "output_cost_per_token": 2.501e-06, "cache_read_input_token_cost": 4.2000000000000006e-08, - "max_tokens": 64000, "max_output_tokens": 64000, "max_input_tokens": 1024000, "supports_function_calling": true, @@ -78017,7 +74943,6 @@ "input_cost_per_token": 1.4e-07, "output_cost_per_token": 5.8e-07, "cache_read_input_token_cost": 3.5e-08, - "max_tokens": 128000, "max_output_tokens": 128000, "max_input_tokens": 192000, "supports_function_calling": true, @@ -78034,7 +74959,6 @@ "input_cost_per_token": 0, "output_cost_per_token": 0, "cache_read_input_token_cost": 0, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -78051,7 +74975,6 @@ "input_cost_per_token": 1e-06, "output_cost_per_token": 2.7e-06, "cache_read_input_token_cost": 1.0000000000000001e-07, - "max_tokens": 65536, "max_output_tokens": 65536, "max_input_tokens": 1000000, "supports_function_calling": true, @@ -78068,7 +74991,6 @@ "input_cost_per_token": 0, "output_cost_per_token": 0, "cache_read_input_token_cost": 0, - "max_tokens": 131072, "max_output_tokens": 131072, "max_input_tokens": 1048576, "supports_function_calling": true, @@ -78089,7 +75011,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -78134,7 +75055,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_batches": 2.5e-05, @@ -78178,7 +75098,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, @@ -78211,7 +75130,6 @@ "litellm_provider": "bedrock", "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, @@ -78261,7 +75179,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -78298,7 +75215,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -78341,7 +75257,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -78385,7 +75300,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -78430,7 +75344,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, "output_cost_per_token_batches": 1.25e-05, @@ -78475,7 +75388,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, "output_cost_per_token_batches": 1e-05, @@ -78520,7 +75432,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 200000, "max_output_tokens": 64000, - "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -78555,7 +75466,6 @@ "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, "output_cost_per_token_batches": 7.5e-06, @@ -78598,7 +75508,6 @@ "litellm_provider": "bedrock", "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, @@ -78642,7 +75551,6 @@ "litellm_provider": "bedrock", "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, @@ -78712,7 +75620,6 @@ "litellm_provider": "openai", "max_input_tokens": 922000, "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, @@ -78761,7 +75668,6 @@ "litellm_provider": "chatgpt", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ @@ -78788,7 +75694,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 922000, "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, @@ -78827,7 +75732,6 @@ "litellm_provider": "bedrock_converse", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5.5e-06, "output_cost_per_token_above_272k_tokens": 8.25e-06, @@ -78884,7 +75788,6 @@ "litellm_provider": "github_copilot", "max_input_tokens": 922000, "max_output_tokens": 128000, - "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 5e-06, "output_cost_per_token_above_272k_tokens": 7.5e-06, diff --git a/tests/unit/litellm_core_utils/test_fallback_generalizations.py b/tests/unit/litellm_core_utils/test_fallback_generalizations.py index 7807c438503..e59252e1571 100644 --- a/tests/unit/litellm_core_utils/test_fallback_generalizations.py +++ b/tests/unit/litellm_core_utils/test_fallback_generalizations.py @@ -369,7 +369,7 @@ def test_exact_entries_fill_only_missing_fields(restore_generalizations, monkeyp "output_cost_per_token": 2e-6, "litellm_provider": "openai", "mode": "chat", - "max_tokens": 7, + "max_output_tokens": 7, "supports_reasoning": False, }, "acme-bare": { @@ -398,7 +398,7 @@ def test_exact_entries_fill_only_missing_fields(restore_generalizations, monkeyp "name": "acme-backfill", "pattern": r"^acme-", "fill_missing_for_providers": ["openai"], - "model_info": {"supports_reasoning": True, "max_tokens": 5}, + "model_info": {"supports_reasoning": True, "max_output_tokens": 5}, } ] ) @@ -406,10 +406,12 @@ def test_exact_entries_fill_only_missing_fields(restore_generalizations, monkeyp full = litellm.get_model_info("acme-full", custom_llm_provider="openai") assert full["supports_reasoning"] is False + assert full["max_output_tokens"] == 7 assert full["max_tokens"] == 7 bare = litellm.get_model_info("acme-bare", custom_llm_provider="openai") assert bare["supports_reasoning"] is True + assert bare["max_output_tokens"] == 5 assert bare["max_tokens"] == 5 assert bare["input_cost_per_token"] == 3e-6 assert bare["key"] == "acme-bare" @@ -525,7 +527,7 @@ def test_shipped_gemini_chat_baseline_loses_to_exact_entries(shipped_cost_map): model = "gemini-2.5-flash-lite" info = litellm.get_model_info(model, custom_llm_provider="gemini") entry = litellm.model_cost["gemini/gemini-2.5-flash-lite"] - assert info["max_tokens"] == entry["max_tokens"] + assert info["max_tokens"] == entry["max_output_tokens"] assert info["input_cost_per_token"] == entry["input_cost_per_token"] assert entry["input_cost_per_token"] > 0 diff --git a/tests/unit/llms/openai_like/test_openinfer_provider.py b/tests/unit/llms/openai_like/test_openinfer_provider.py index 7bcc489fcf8..6e6e957df0b 100644 --- a/tests/unit/llms/openai_like/test_openinfer_provider.py +++ b/tests/unit/llms/openai_like/test_openinfer_provider.py @@ -11,9 +11,7 @@ from litellm.proxy.auth.model_checks import get_provider_models _REPO_ROOT: Final = Path(__file__).resolve().parents[4] _PRIMARY_PRICES: Final = json.loads((_REPO_ROOT / "model_prices_and_context_window.json").read_text()) -_BACKUP_PRICES: Final = json.loads( - (_REPO_ROOT / "litellm" / "model_prices_and_context_window_backup.json").read_text() -) +_BACKUP_PRICES: Final = json.loads((_REPO_ROOT / "litellm" / "model_prices_and_context_window_backup.json").read_text()) _CATALOG_MODELS: Final = tuple( key for key, row in _PRIMARY_PRICES.items() if isinstance(row, dict) and row.get("litellm_provider") == "openinfer" ) @@ -31,7 +29,9 @@ _CHAT_RESPONSE: Final = { "object": "chat.completion", "created": 1_792_000_000, "model": "@oi/Qwen3.5-27B", - "choices": [{"index": 0, "message": {"role": "assistant", "content": "Hello from OpenInfer"}, "finish_reason": "stop"}], + "choices": [ + {"index": 0, "message": {"role": "assistant", "content": "Hello from OpenInfer"}, "finish_reason": "stop"} + ], "usage": {"prompt_tokens": 4, "completion_tokens": 3, "total_tokens": 7}, } @@ -228,7 +228,6 @@ def test_catalog_row_matches_its_backup_and_fits_its_context(model: str): assert row == _BACKUP_PRICES[model] assert row["mode"] == "chat" - assert row["max_tokens"] == row["max_output_tokens"] assert 0 < row["max_output_tokens"] <= row["max_input_tokens"] assert row["input_cost_per_token"] > 0 assert row["output_cost_per_token"] > 0 diff --git a/tests/unit/test_model_prices_and_context_window.py b/tests/unit/test_model_prices_and_context_window.py index 45222b2c9ab..35658097880 100644 --- a/tests/unit/test_model_prices_and_context_window.py +++ b/tests/unit/test_model_prices_and_context_window.py @@ -50,7 +50,6 @@ class _CopilotEndpointRow(BaseModel): mode: str max_input_tokens: int max_output_tokens: int - max_tokens: int supported_endpoints: tuple[str, ...] @@ -96,18 +95,22 @@ def _anthropic_counterpart(key: str) -> str: @pytest.mark.parametrize(("path",), [(PRICES_PATH,), (BACKUP_PRICES_PATH,)], ids=("main", "backup")) -def test_github_copilot_rows_derive_mode_and_max_tokens_from_their_endpoints(path: Path) -> None: +def test_github_copilot_rows_derive_mode_from_their_endpoints(path: Path) -> None: rows: Final[Mapping[str, _CopilotEndpointRow]] = _copilot_endpoint_rows(path) assert rows, f"No GitHub Copilot endpoint rows found in {path}" - assert {key: (row.mode, row.max_tokens) for key, row in rows.items()} == { - key: ( - "chat" if "/v1/chat/completions" in row.supported_endpoints else "responses", - row.max_output_tokens, - ) - for key, row in rows.items() + assert {key: row.mode for key, row in rows.items()} == { + key: "chat" if "/v1/chat/completions" in row.supported_endpoints else "responses" for key, row in rows.items() } +def _rows_carrying_legacy_max_tokens(prices: Mapping[str, Mapping[str, object]]) -> tuple[str, ...]: + return tuple(key for key, row in prices.items() if "max_tokens" in row) + + +def test_no_row_carries_the_retired_max_tokens_field(prices: dict) -> None: + assert _rows_carrying_legacy_max_tokens(prices) == () + + def test_github_copilot_backup_rows_match_the_main_catalog() -> None: assert _github_copilot_catalog_rows(PRICES_PATH) == _github_copilot_catalog_rows(BACKUP_PRICES_PATH) @@ -601,7 +604,6 @@ def test_tencent_tokenhub_glm_rows_match_published_metadata(path: Path): or entry.get("litellm_provider") != "tencent" or entry.get("max_input_tokens") != 1000000 or entry.get("max_output_tokens") != 128000 - or entry.get("max_tokens") != 128000 or entry.get("input_cost_per_token_cache_hit") != entry.get("cache_read_input_token_cost") ) assert actual == TENCENT_TOKENHUB_GLM_ROWS @@ -619,7 +621,7 @@ def test_tencent_tokenhub_kimi_rows_match_published_metadata(path: Path): entry.get("input_cost_per_token"), entry.get("output_cost_per_token"), entry.get("cache_read_input_token_cost"), - entry.get("max_tokens"), + entry.get("max_output_tokens"), entry.get("supports_vision", False), entry.get("supports_video_input", False), ) @@ -793,7 +795,6 @@ def test_volcengine_doubao_seed_2_1_pro_260915_row_matches_published_metadata(pa assert entry["mode"] == "chat" assert entry["max_input_tokens"] == 1024000 assert entry["max_output_tokens"] == 256000 - assert entry["max_tokens"] == 256000 # Volcengine Ark pricing https://www.volcengine.com/docs/82379/1544106 checked 2026-10-20 assert entry["input_cost_per_token"] == pytest.approx(6.0 / 6.9565 / 1_000_000, rel=1e-4) assert entry["output_cost_per_token"] == pytest.approx(30.0 / 6.9565 / 1_000_000, rel=1e-4) diff --git a/tests/unit/test_together_ai_model_metadata.py b/tests/unit/test_together_ai_model_metadata.py index dccba3d66f9..3616c6216ca 100644 --- a/tests/unit/test_together_ai_model_metadata.py +++ b/tests/unit/test_together_ai_model_metadata.py @@ -75,18 +75,6 @@ def cost_map() -> CostMap: return COST_MAP_ADAPTER.validate_python(json.load(f)) -def test_together_chat_entries_never_carry_context_length_as_output_ceiling(cost_map: CostMap): - inflated = sorted( - model - for model, info in cost_map.items() - if info.get("litellm_provider") == "together_ai" - and info.get("mode") == "chat" - and "max_output_tokens" in info - and info["max_output_tokens"] == info.get("max_input_tokens") - ) - assert inflated == [] - - def _successor(info: dict[str, object]) -> str | None: metadata = info.get("metadata") if not isinstance(metadata, dict): @@ -95,8 +83,6 @@ def _successor(info: dict[str, object]) -> str | None: return successor if isinstance(successor, str) else None - - def test_together_backup_cost_map_in_sync(cost_map: CostMap): with open(REPO_ROOT / "litellm" / "model_prices_and_context_window_backup.json") as f: backup = COST_MAP_ADAPTER.validate_python(json.load(f)) diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py index b9baef4056a..6c7f6a9d869 100644 --- a/tests/unit/test_utils.py +++ b/tests/unit/test_utils.py @@ -2260,6 +2260,45 @@ class TestProxyFunctionCalling: @pytest.mark.usefixtures("isolated_openai_model_sets", "local_model_cost_map") +def test_get_model_info_derives_max_tokens_from_the_output_limit() -> None: + model: Final = "derived-max-tokens-chat-model" + litellm.register_model( + { + model: { + "litellm_provider": "openai", + "mode": "chat", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + } + }, + persist_across_reloads=False, + ) + info: Final = litellm.get_model_info(model, custom_llm_provider="openai") + assert info["max_tokens"] == 128000 + assert litellm.get_max_tokens(model) == 128000 + + +def test_get_model_info_derives_max_tokens_from_the_input_limit_when_the_row_has_no_output_limit() -> None: + model: Final = "derived-max-tokens-embedding-model" + litellm.register_model( + { + model: { + "litellm_provider": "openai", + "mode": "embedding", + "max_input_tokens": 8191, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + } + }, + persist_across_reloads=False, + ) + info: Final = litellm.get_model_info(model, custom_llm_provider="openai") + assert info["max_tokens"] == 8191 + assert info["max_output_tokens"] is None + + def test_register_model_price_is_used_for_completion_cost() -> None: model: Final = "migration-custom-pricing-model" price: Final = { @@ -8629,7 +8668,7 @@ def test_basic_trimming_no_max_tokens_specified(): trimmed_messages = trim_messages(messages, model="gpt-4") print("trimmed messages for gpt-4") print(trimmed_messages) - assert (get_token_count(messages=trimmed_messages, model="gpt-4")) <= litellm.model_cost["gpt-4"]["max_tokens"] + assert (get_token_count(messages=trimmed_messages, model="gpt-4")) <= litellm.model_cost["gpt-4"]["max_input_tokens"] def test_multiple_messages_trimming(): From 554b011787043a4cfc6a48d7d011bbfca05b6e22 Mon Sep 17 00:00:00 2001 From: yujonglee Date: Mon, 26 Oct 2026 17:05:04 -0700 Subject: [PATCH 007/262] feat(rust): add typed database query foundation (#48214) Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .github/workflows/test-rust-db.yml | 106 ++++++ litellm-rust/Cargo.lock | 5 + litellm-rust/Cargo.toml | 1 + ...64311d25428fd393bac4250891f148597e92e.json | 78 ++++ litellm-rust/crates/db/AGENTS.md | 25 ++ litellm-rust/crates/db/Cargo.toml | 7 + .../db/queries/end_user/find_end_user.sql | 10 + litellm-rust/crates/db/src/daily_spend.rs | 76 ++++ litellm-rust/crates/db/src/end_user.rs | 359 ++++++++++++++++++ litellm-rust/crates/db/src/error.rs | 79 ++++ litellm-rust/crates/db/src/lib.rs | 18 +- litellm-rust/crates/db/src/test_support.rs | 10 + 12 files changed, 773 insertions(+), 1 deletion(-) create mode 100644 .github/workflows/test-rust-db.yml create mode 100644 litellm-rust/crates/db/.sqlx/query-377d063cd0fc3a265d07d01f5aa64311d25428fd393bac4250891f148597e92e.json create mode 100644 litellm-rust/crates/db/AGENTS.md create mode 100644 litellm-rust/crates/db/queries/end_user/find_end_user.sql create mode 100644 litellm-rust/crates/db/src/daily_spend.rs create mode 100644 litellm-rust/crates/db/src/end_user.rs create mode 100644 litellm-rust/crates/db/src/error.rs create mode 100644 litellm-rust/crates/db/src/test_support.rs diff --git a/.github/workflows/test-rust-db.yml b/.github/workflows/test-rust-db.yml new file mode 100644 index 00000000000..bb88b593d5b --- /dev/null +++ b/.github/workflows/test-rust-db.yml @@ -0,0 +1,106 @@ +name: LiteLLM Rust DB + +on: + push: + paths: + - "litellm-rust/crates/db/**" + - "litellm-rust/Cargo.toml" + - "litellm-rust/Cargo.lock" + - "litellm-rust/clippy.toml" + - "litellm-proxy-extras/litellm_proxy_extras/migrations/**" + - "**/schema.prisma" + - ".cargo/**" + - "rust-toolchain.toml" + - "pyproject.toml" + - "uv.lock" + - ".github/actions/setup-uv-with-retries/**" + - ".github/workflows/test-rust-db.yml" + pull_request: + branches: + - main + - "litellm_**" + paths: + - "litellm-rust/crates/db/**" + - "litellm-rust/Cargo.toml" + - "litellm-rust/Cargo.lock" + - "litellm-rust/clippy.toml" + - "litellm-proxy-extras/litellm_proxy_extras/migrations/**" + - "**/schema.prisma" + - ".cargo/**" + - "rust-toolchain.toml" + - "pyproject.toml" + - "uv.lock" + - ".github/actions/setup-uv-with-retries/**" + - ".github/workflows/test-rust-db.yml" + +permissions: + contents: read + +concurrency: + group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} + cancel-in-progress: true + +env: + CARGO_TERM_COLOR: always + +jobs: + db-queries: + runs-on: ubuntu-latest + timeout-minutes: 30 + services: + postgres: + image: postgres:16.6@sha256:557fea37a744d5f4c8faab304b0a90858b53ab119735a88c131fd19dab802f36 + env: + POSTGRES_DB: litellm + POSTGRES_PASSWORD: postgres + POSTGRES_USER: postgres + ports: + - 5432:5432 + options: >- + --health-cmd "pg_isready -U postgres -d litellm" + --health-interval 10s + --health-timeout 5s + --health-retries 5 + env: + DATABASE_URL: postgresql://postgres:postgres@localhost:5432/litellm + SQLX_OFFLINE: "false" + defaults: + run: + working-directory: litellm-rust + steps: + - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0 + with: + persist-credentials: false + + - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0 + with: + python-version: "3.12" + + - uses: ./.github/actions/setup-uv-with-retries + with: + version: "0.10.9" + + - run: rustup toolchain install --no-self-update + + - uses: Swatinem/rust-cache@6323deb102c322ba6fcbdcafc7e3dddab59af2b6 # v2.9.2 + with: + workspaces: litellm-rust + cache-on-failure: true + + - name: Install Python dependencies + working-directory: . + run: uv sync --frozen --extra extra-proxy + + - name: Deploy Prisma migrations + working-directory: . + run: uv run --no-sync prisma migrate deploy --schema litellm-proxy-extras/litellm_proxy_extras/schema.prisma + + - name: Install SQLx CLI + run: cargo install sqlx-cli --version 0.9.0 --locked --no-default-features -F postgres + + - name: Check SQLx query metadata + working-directory: litellm-rust/crates/db + run: cargo sqlx prepare --check + + - name: Test database queries + run: cargo test -p litellm-db --locked -- --include-ignored diff --git a/litellm-rust/Cargo.lock b/litellm-rust/Cargo.lock index cb50324e1dd..d58ba9ecb5f 100644 --- a/litellm-rust/Cargo.lock +++ b/litellm-rust/Cargo.lock @@ -3695,8 +3695,13 @@ dependencies = [ name = "litellm-db" version = "0.1.0" dependencies = [ + "chrono", + "macro_rules_attribute", + "rstest", "serde", "sqlx", + "thiserror 2.0.19", + "tokio", ] [[package]] diff --git a/litellm-rust/Cargo.toml b/litellm-rust/Cargo.toml index 9e5e0a96b73..fc65355c047 100644 --- a/litellm-rust/Cargo.toml +++ b/litellm-rust/Cargo.toml @@ -104,6 +104,7 @@ serde_with = { version = "=3.21.0", default-features = false, features = ["std", sha2 = "0.10" syn = { version = "2", default-features = false } sqlx = { version = "0.9.0", default-features = false, features = ["json", "macros", "postgres", "runtime-tokio", "chrono", "tls-rustls-ring-native-roots"] } +chrono = { version = "0.4.45", default-features = false, features = ["std"] } proc-macro2 = "1" quote = "1" subtle = "2" diff --git a/litellm-rust/crates/db/.sqlx/query-377d063cd0fc3a265d07d01f5aa64311d25428fd393bac4250891f148597e92e.json b/litellm-rust/crates/db/.sqlx/query-377d063cd0fc3a265d07d01f5aa64311d25428fd393bac4250891f148597e92e.json new file mode 100644 index 00000000000..734935466ff --- /dev/null +++ b/litellm-rust/crates/db/.sqlx/query-377d063cd0fc3a265d07d01f5aa64311d25428fd393bac4250891f148597e92e.json @@ -0,0 +1,78 @@ +{ + "db_name": "PostgreSQL", + "query": "SELECT e.spend AS \"spend?\",\n e.blocked AS \"blocked?\",\n b.max_budget AS \"max_budget?\",\n b.rpm_limit AS \"rpm_limit?\",\n b.tpm_limit AS \"tpm_limit?\"\nFROM (SELECT 1) AS one\nLEFT JOIN \"LiteLLM_EndUserTable\" AS e ON e.user_id = $1\nLEFT JOIN \"LiteLLM_BudgetTable\" AS assigned ON assigned.budget_id = e.budget_id\nLEFT JOIN \"LiteLLM_BudgetTable\" AS key_budget ON key_budget.budget_id = $3\nLEFT JOIN \"LiteLLM_BudgetTable\" AS b ON b.budget_id = COALESCE(assigned.budget_id, key_budget.budget_id, $2)\n", + "describe": { + "columns": [ + { + "ordinal": 0, + "name": "spend?", + "type_info": "Float8", + "origin": { + "Table": { + "table": "\"LiteLLM_EndUserTable\"", + "name": "spend" + } + } + }, + { + "ordinal": 1, + "name": "blocked?", + "type_info": "Bool", + "origin": { + "Table": { + "table": "\"LiteLLM_EndUserTable\"", + "name": "blocked" + } + } + }, + { + "ordinal": 2, + "name": "max_budget?", + "type_info": "Float8", + "origin": { + "Table": { + "table": "\"LiteLLM_BudgetTable\"", + "name": "max_budget" + } + } + }, + { + "ordinal": 3, + "name": "rpm_limit?", + "type_info": "Int8", + "origin": { + "Table": { + "table": "\"LiteLLM_BudgetTable\"", + "name": "rpm_limit" + } + } + }, + { + "ordinal": 4, + "name": "tpm_limit?", + "type_info": "Int8", + "origin": { + "Table": { + "table": "\"LiteLLM_BudgetTable\"", + "name": "tpm_limit" + } + } + } + ], + "parameters": { + "Left": [ + "Text", + "Text", + "Text" + ] + }, + "nullable": [ + true, + true, + true, + true, + true + ] + }, + "hash": "377d063cd0fc3a265d07d01f5aa64311d25428fd393bac4250891f148597e92e" +} diff --git a/litellm-rust/crates/db/AGENTS.md b/litellm-rust/crates/db/AGENTS.md new file mode 100644 index 00000000000..1e08317230e --- /dev/null +++ b/litellm-rust/crates/db/AGENTS.md @@ -0,0 +1,25 @@ +# Database crate + +Keep each static query in `queries/` and call it through a typed SQLx query function. Rust does not create or migrate the database + +- Own reusable row projections in `src/` and export those consumed by other crates or integration tests +- Apply `#[macro_rules_attribute::apply(crate::db_row)]` to row types for shared derives, without adding serialization or schema derives automatically +- Apply `#[macro_rules_attribute::apply(crate::db_input)]` to write inputs, adding `Default` only where supported +- Keep function tests inline in their owning query module and reuse the strict database fixture in `test_support` +- Transaction-local setup in `begin` is the approved exception to static query files +- Keep write inputs separate from stored rows and keep test-only assertions out of public types +- `FromRow` supports runtime reads, but production static reads still use `query_file_as!` for compile-time checking + +Database integration tests are ignored by default, but still compile in workspace checks. Run them explicitly against a local database already migrated by Prisma. Missing or invalid database configuration must fail the selected tests: + +```sh +DATABASE_URL=postgresql://... cargo test -p litellm-db --locked -- --include-ignored +``` + +After changing a query, refresh the checked query metadata from this directory: + +```sh +SQLX_OFFLINE=false cargo sqlx prepare +``` + +Tests use transactions and leave them uncommitted so fixture rows roll back when each test finishes diff --git a/litellm-rust/crates/db/Cargo.toml b/litellm-rust/crates/db/Cargo.toml index ca9d6f555b0..bb6d5655b60 100644 --- a/litellm-rust/crates/db/Cargo.toml +++ b/litellm-rust/crates/db/Cargo.toml @@ -6,5 +6,12 @@ license.workspace = true repository.workspace = true [dependencies] +chrono.workspace = true +macro_rules_attribute.workspace = true serde.workspace = true sqlx.workspace = true +thiserror.workspace = true + +[dev-dependencies] +rstest.workspace = true +tokio.workspace = true diff --git a/litellm-rust/crates/db/queries/end_user/find_end_user.sql b/litellm-rust/crates/db/queries/end_user/find_end_user.sql new file mode 100644 index 00000000000..c10ef8b877d --- /dev/null +++ b/litellm-rust/crates/db/queries/end_user/find_end_user.sql @@ -0,0 +1,10 @@ +SELECT e.spend AS "spend?", + e.blocked AS "blocked?", + b.max_budget AS "max_budget?", + b.rpm_limit AS "rpm_limit?", + b.tpm_limit AS "tpm_limit?" +FROM (SELECT 1) AS one +LEFT JOIN "LiteLLM_EndUserTable" AS e ON e.user_id = $1 +LEFT JOIN "LiteLLM_BudgetTable" AS assigned ON assigned.budget_id = e.budget_id +LEFT JOIN "LiteLLM_BudgetTable" AS key_budget ON key_budget.budget_id = $3 +LEFT JOIN "LiteLLM_BudgetTable" AS b ON b.budget_id = COALESCE(assigned.budget_id, key_budget.budget_id, $2) diff --git a/litellm-rust/crates/db/src/daily_spend.rs b/litellm-rust/crates/db/src/daily_spend.rs new file mode 100644 index 00000000000..9db07514aab --- /dev/null +++ b/litellm-rust/crates/db/src/daily_spend.rs @@ -0,0 +1,76 @@ +use sqlx::types::chrono::NaiveDateTime; + +#[macro_rules_attribute::apply(crate::db_row)] +pub struct DailyUserRow { + pub id: String, + pub user_id: Option, + pub api_key: String, + pub model: Option, + pub custom_llm_provider: Option, + pub endpoint: Option, + pub model_group: Option, + pub mcp_namespaced_tool_name: Option, + pub prompt_tokens: i64, + pub completion_tokens: i64, + pub api_requests: i64, + pub successful_requests: i64, + pub failed_requests: i64, + pub cache_read_input_tokens: i64, + pub cache_creation_input_tokens: i64, + pub total_response_time_ms: i64, + pub timed_requests: i64, + pub spend: f64, + pub date: String, + pub created_at: NaiveDateTime, + pub updated_at: NaiveDateTime, +} + +#[macro_rules_attribute::apply(crate::db_row)] +pub struct DailyTeamRow { + pub id: String, + pub team_id: Option, + pub api_key: String, + pub model: Option, + pub custom_llm_provider: Option, + pub endpoint: Option, + pub model_group: Option, + pub mcp_namespaced_tool_name: Option, + pub prompt_tokens: i64, + pub completion_tokens: i64, + pub api_requests: i64, + pub successful_requests: i64, + pub failed_requests: i64, + pub cache_read_input_tokens: i64, + pub cache_creation_input_tokens: i64, + pub total_response_time_ms: i64, + pub timed_requests: i64, + pub spend: f64, + pub date: String, + pub created_at: NaiveDateTime, + pub updated_at: NaiveDateTime, +} + +#[macro_rules_attribute::apply(crate::db_row)] +pub struct DailyEndUserRow { + pub id: String, + pub end_user_id: Option, + pub api_key: String, + pub model: Option, + pub custom_llm_provider: Option, + pub endpoint: Option, + pub model_group: Option, + pub mcp_namespaced_tool_name: Option, + pub prompt_tokens: i64, + pub completion_tokens: i64, + pub api_requests: i64, + pub successful_requests: i64, + pub failed_requests: i64, + pub cache_read_input_tokens: i64, + pub cache_creation_input_tokens: i64, + pub total_response_time_ms: i64, + pub timed_requests: i64, + pub spend: f64, + pub date: String, + pub created_at: NaiveDateTime, + pub updated_at: NaiveDateTime, +} diff --git a/litellm-rust/crates/db/src/end_user.rs b/litellm-rust/crates/db/src/end_user.rs new file mode 100644 index 00000000000..66661b51640 --- /dev/null +++ b/litellm-rust/crates/db/src/end_user.rs @@ -0,0 +1,359 @@ +use sqlx::PgExecutor; + +use crate::Error; + +#[derive(Clone, Copy, Debug, Default, Eq, PartialEq)] +pub struct RateLimits { + pub rpm: Option, + pub tpm: Option, +} + +#[derive(Clone, Debug, Default, PartialEq)] +pub struct EndUser { + pub spend: Option, + pub blocked: bool, + pub max_budget: Option, + pub limits: RateLimits, +} + +#[macro_rules_attribute::apply(crate::db_row)] +struct EndUserRow { + spend: Option, + blocked: Option, + max_budget: Option, + rpm_limit: Option, + tpm_limit: Option, +} + +pub async fn find_end_user( + executor: impl PgExecutor<'_>, + end_user_id: &str, + default_budget_id: Option<&str>, + key_budget_id: Option<&str>, +) -> Result { + let row = sqlx::query_file_as!( + EndUserRow, + "queries/end_user/find_end_user.sql", + end_user_id, + default_budget_id, + key_budget_id, + ) + .fetch_one(executor) + .await?; + Ok(EndUser { + spend: row.spend, + blocked: row.blocked.unwrap_or(false), + max_budget: row.max_budget, + limits: RateLimits { + rpm: row.rpm_limit, + tpm: row.tpm_limit, + }, + }) +} + +#[cfg(test)] +mod tests { + use std::error::Error as StdError; + + use super::{EndUser, RateLimits, find_end_user}; + use crate::test_support::database_pool; + use rstest::rstest; + use sqlx::{PgPool, Postgres, Transaction}; + + #[derive(Clone, Copy)] + struct BudgetFixture { + budget_id: &'static str, + max_budget: f64, + rpm_limit: i64, + tpm_limit: i64, + } + + async fn insert_budget( + tx: &mut Transaction<'_, Postgres>, + budget: BudgetFixture, + ) -> Result<(), sqlx::Error> { + #[expect( + clippy::disallowed_methods, + reason = "Fixture inserts are outside the compile-checked query set" + )] + let result = sqlx::query( + r#" + INSERT INTO "LiteLLM_BudgetTable" + (budget_id, max_budget, rpm_limit, tpm_limit, created_by, updated_by) + VALUES ($1, $2, $3, $4, 'db-query-test', 'db-query-test') + "#, + ) + .bind(budget.budget_id) + .bind(budget.max_budget) + .bind(budget.rpm_limit) + .bind(budget.tpm_limit) + .execute(&mut **tx) + .await; + result.map(|_| ()) + } + + async fn insert_end_user( + tx: &mut Transaction<'_, Postgres>, + user_id: &str, + spend: f64, + blocked: bool, + budget_id: Option<&str>, + ) -> Result<(), sqlx::Error> { + #[expect( + clippy::disallowed_methods, + reason = "Fixture inserts are outside the compile-checked query set" + )] + let result = sqlx::query( + r#" + INSERT INTO "LiteLLM_EndUserTable" (user_id, spend, blocked, budget_id) + VALUES ($1, $2, $3, $4) + "#, + ) + .bind(user_id) + .bind(spend) + .bind(blocked) + .bind(budget_id) + .execute(&mut **tx) + .await; + result.map(|_| ()) + } + + #[rstest] + #[case::without_default_budget(None)] + #[case::with_default_budget(Some(BudgetFixture { + budget_id: "missing-user-default-budget", + max_budget: 11.5, + rpm_limit: 12, + tpm_limit: 1300, + }))] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn missing_end_user_maps_to_defaults( + #[case] default_budget: Option, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + if let Some(budget) = default_budget { + insert_budget(&mut tx, budget).await?; + } + + let actual = find_end_user( + &mut *tx, + "missing-end-user", + default_budget.map(|budget| budget.budget_id), + None, + ) + .await?; + + assert_eq!( + actual, + EndUser { + spend: None, + blocked: false, + max_budget: default_budget.map(|budget| budget.max_budget), + limits: RateLimits { + rpm: default_budget.map(|budget| budget.rpm_limit), + tpm: default_budget.map(|budget| budget.tpm_limit), + }, + } + ); + Ok(()) + } + + #[rstest] + #[case::row_budget_precedes_default( + "row-budget-priority-user", + Some(BudgetFixture { + budget_id: "row-budget-priority-row", + max_budget: 10.0, + rpm_limit: 101, + tpm_limit: 1001, + }), + BudgetFixture { + budget_id: "row-budget-priority-default", + max_budget: 20.0, + rpm_limit: 201, + tpm_limit: 2001, + }, + None, + Some(BudgetFixture { + budget_id: "row-budget-priority-row", + max_budget: 10.0, + rpm_limit: 101, + tpm_limit: 1001, + }), + false + )] + #[case::default_applies_without_row_budget( + "default-budget-user", + None, + BudgetFixture { + budget_id: "default-budget-fallback", + max_budget: 30.0, + rpm_limit: 301, + tpm_limit: 3001, + }, + None, + Some(BudgetFixture { + budget_id: "default-budget-fallback", + max_budget: 30.0, + rpm_limit: 301, + tpm_limit: 3001, + }), + false + )] + #[case::assigned_budget_precedes_key_when_all_ids_differ( + "override-priority-user", + Some(BudgetFixture { + budget_id: "override-priority-row", + max_budget: 40.0, + rpm_limit: 401, + tpm_limit: 4001, + }), + BudgetFixture { + budget_id: "override-priority-default", + max_budget: 50.0, + rpm_limit: 501, + tpm_limit: 5001, + }, + Some(BudgetFixture { + budget_id: "override-priority-override", + max_budget: 60.0, + rpm_limit: 601, + tpm_limit: 6001, + }), + Some(BudgetFixture { + budget_id: "override-priority-row", + max_budget: 40.0, + rpm_limit: 401, + tpm_limit: 4001, + }), + true + )] + #[case::missing_key_budget_keeps_assigned_budget( + "dangling-override-user", + Some(BudgetFixture { + budget_id: "dangling-override-row", + max_budget: 70.0, + rpm_limit: 701, + tpm_limit: 7001, + }), + BudgetFixture { + budget_id: "dangling-override-default", + max_budget: 80.0, + rpm_limit: 801, + tpm_limit: 8001, + }, + Some(BudgetFixture { + budget_id: "dangling-override-missing", + max_budget: 90.0, + rpm_limit: 901, + tpm_limit: 9001, + }), + Some(BudgetFixture { + budget_id: "dangling-override-row", + max_budget: 70.0, + rpm_limit: 701, + tpm_limit: 7001, + }), + false + )] + #[case::key_budget_precedes_proxy_default( + "key-default-user", + None, + BudgetFixture { + budget_id: "key-default-proxy", + max_budget: 80.0, + rpm_limit: 801, + tpm_limit: 8001, + }, + Some(BudgetFixture { + budget_id: "key-default-key", + max_budget: 90.0, + rpm_limit: 901, + tpm_limit: 9001, + }), + Some(BudgetFixture { + budget_id: "key-default-key", + max_budget: 90.0, + rpm_limit: 901, + tpm_limit: 9001, + }), + true + )] + #[case::missing_key_budget_falls_back_to_proxy_default( + "missing-key-default-user", + None, + BudgetFixture { + budget_id: "missing-key-default-proxy", + max_budget: 80.0, + rpm_limit: 801, + tpm_limit: 8001, + }, + Some(BudgetFixture { + budget_id: "missing-key-default-key", + max_budget: 90.0, + rpm_limit: 901, + tpm_limit: 9001, + }), + Some(BudgetFixture { + budget_id: "missing-key-default-proxy", + max_budget: 80.0, + rpm_limit: 801, + tpm_limit: 8001, + }), + false + )] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn budget_resolution_matches_python_precedence( + #[case] user_id: &'static str, + #[case] user_budget: Option, + #[case] default_budget: BudgetFixture, + #[case] override_budget: Option, + #[case] expected_budget: Option, + #[case] insert_override_budget: bool, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + insert_budget(&mut tx, default_budget).await?; + if let Some(budget) = user_budget { + insert_budget(&mut tx, budget).await?; + } + if let (Some(budget), true) = (override_budget, insert_override_budget) { + insert_budget(&mut tx, budget).await?; + } + insert_end_user( + &mut tx, + user_id, + 7.5, + true, + user_budget.map(|budget| budget.budget_id), + ) + .await?; + + let actual = find_end_user( + &mut *tx, + user_id, + Some(default_budget.budget_id), + override_budget.map(|budget| budget.budget_id), + ) + .await?; + + assert_eq!( + actual, + EndUser { + spend: Some(7.5), + blocked: true, + max_budget: expected_budget.map(|budget| budget.max_budget), + limits: RateLimits { + rpm: expected_budget.map(|budget| budget.rpm_limit), + tpm: expected_budget.map(|budget| budget.tpm_limit), + }, + } + ); + Ok(()) + } +} diff --git a/litellm-rust/crates/db/src/error.rs b/litellm-rust/crates/db/src/error.rs new file mode 100644 index 00000000000..af0ee030896 --- /dev/null +++ b/litellm-rust/crates/db/src/error.rs @@ -0,0 +1,79 @@ +#[derive(Debug, thiserror::Error)] +pub enum Error { + #[error("database query failed")] + Query(#[from] sqlx::Error), + #[error("spend batch has {ids} ids and {costs} costs")] + InvalidSpendBatch { ids: usize, costs: usize }, + #[error("invalid spend timestamp")] + InvalidTimestamp(#[from] chrono::ParseError), +} + +impl Error { + pub fn is_retryable(&self) -> bool { + match self { + Self::Query(sqlx::Error::Database(error)) => { + matches!( + error.code().as_deref(), + Some("40P01" | "55P03" | "40001" | "53300") + ) + } + Self::Query(sqlx::Error::Io(_) | sqlx::Error::PoolTimedOut) => true, + _ => false, + } + } +} + +#[cfg(test)] +mod tests { + use std::error::Error as StdError; + + use rstest::rstest; + use sqlx::PgPool; + + use super::Error; + use crate::test_support::database_pool; + + #[rstest] + #[case::closed_pool(sqlx::Error::PoolClosed, false)] + #[case::pool_timeout(sqlx::Error::PoolTimedOut, true)] + #[case::io(sqlx::Error::Io(std::io::ErrorKind::ConnectionReset.into()), true)] + #[case::missing_row(sqlx::Error::RowNotFound, false)] + fn classifies_client_errors(#[case] error: sqlx::Error, #[case] retryable: bool) { + assert_eq!(Error::from(error).is_retryable(), retryable); + } + + #[rstest] + #[case::connection_capacity("53300", true)] + #[case::deadlock("40P01", true)] + #[case::lock_unavailable("55P03", true)] + #[case::serialization_failure("40001", true)] + #[case::unique_violation("23505", false)] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn classifies_server_errors( + #[case] code: &str, + #[case] retryable: bool, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Test query must raise the requested SQLSTATE" + )] + let error = sqlx::query(sqlx::AssertSqlSafe(format!( + "DO $$ BEGIN RAISE EXCEPTION USING ERRCODE = '{code}'; END $$" + ))) + .execute(&mut *tx) + .await + .expect_err("PostgreSQL must raise the requested error"); + + assert_eq!( + error.as_database_error().and_then(|error| error.code()), + Some(code.into()) + ); + assert_eq!(Error::from(error).is_retryable(), retryable); + tx.rollback().await?; + Ok(()) + } +} diff --git a/litellm-rust/crates/db/src/lib.rs b/litellm-rust/crates/db/src/lib.rs index b7ce211d906..ca5cd366eec 100644 --- a/litellm-rust/crates/db/src/lib.rs +++ b/litellm-rust/crates/db/src/lib.rs @@ -1,3 +1,19 @@ -mod failure; +macro_rules_attribute::attribute_alias! { + #[apply(db_input)] = + #[derive(Clone, Debug, PartialEq)]; + #[apply(db_row)] = + #[derive(Clone, Debug, PartialEq, sqlx::FromRow)]; +} + +mod daily_spend; +mod end_user; +mod error; +mod failure; +#[cfg(test)] +mod test_support; + +pub use daily_spend::{DailyEndUserRow, DailyTeamRow, DailyUserRow}; +pub use end_user::{EndUser, RateLimits, find_end_user}; +pub use error::Error; pub use failure::DbFailure; diff --git a/litellm-rust/crates/db/src/test_support.rs b/litellm-rust/crates/db/src/test_support.rs new file mode 100644 index 00000000000..992be4a4447 --- /dev/null +++ b/litellm-rust/crates/db/src/test_support.rs @@ -0,0 +1,10 @@ +use std::error::Error as StdError; + +use rstest::fixture; +use sqlx::PgPool; + +#[fixture] +pub async fn database_pool() -> Result> { + let database_url = std::env::var("DATABASE_URL")?; + Ok(PgPool::connect(&database_url).await?) +} From 35cd5fc05f7e91c7bc9c91637e14452a3ed55360 Mon Sep 17 00:00:00 2001 From: yujonglee Date: Mon, 26 Oct 2026 17:05:04 -0700 Subject: [PATCH 008/262] feat(db): add typed key spend query (#48217) Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...10731a0cacc1ae5b92eec32967f539948f563.json | 15 + .../crates/db/queries/spend/add_key_spend.sql | 16 + litellm-rust/crates/db/src/lib.rs | 2 + litellm-rust/crates/db/src/spend/key_spend.rs | 309 ++++++++++++++++++ litellm-rust/crates/db/src/spend/mod.rs | 3 + 5 files changed, 345 insertions(+) create mode 100644 litellm-rust/crates/db/.sqlx/query-3829a383d0ae50578f0fd75da3910731a0cacc1ae5b92eec32967f539948f563.json create mode 100644 litellm-rust/crates/db/queries/spend/add_key_spend.sql create mode 100644 litellm-rust/crates/db/src/spend/key_spend.rs create mode 100644 litellm-rust/crates/db/src/spend/mod.rs diff --git a/litellm-rust/crates/db/.sqlx/query-3829a383d0ae50578f0fd75da3910731a0cacc1ae5b92eec32967f539948f563.json b/litellm-rust/crates/db/.sqlx/query-3829a383d0ae50578f0fd75da3910731a0cacc1ae5b92eec32967f539948f563.json new file mode 100644 index 00000000000..e85c0986a60 --- /dev/null +++ b/litellm-rust/crates/db/.sqlx/query-3829a383d0ae50578f0fd75da3910731a0cacc1ae5b92eec32967f539948f563.json @@ -0,0 +1,15 @@ +{ + "db_name": "PostgreSQL", + "query": "WITH added AS (\n SELECT id, SUM(cost) AS cost\n FROM UNNEST($1::text[], $2::float8[]) AS a(id, cost)\n GROUP BY id\n), locked AS (\n SELECT t.token FROM \"LiteLLM_VerificationToken\" t\n WHERE t.token IN (SELECT id FROM added)\n ORDER BY t.token FOR UPDATE\n)\nUPDATE \"LiteLLM_VerificationToken\" t\nSET spend = t.spend + added.cost,\n total_spend = t.total_spend + added.cost,\n last_active = (clock_timestamp() AT TIME ZONE 'UTC'),\n updated_at = (clock_timestamp() AT TIME ZONE 'UTC')\nFROM added\nWHERE t.token = added.id AND t.token IN (SELECT token FROM locked)\n", + "describe": { + "columns": [], + "parameters": { + "Left": [ + "TextArray", + "Float8Array" + ] + }, + "nullable": [] + }, + "hash": "3829a383d0ae50578f0fd75da3910731a0cacc1ae5b92eec32967f539948f563" +} diff --git a/litellm-rust/crates/db/queries/spend/add_key_spend.sql b/litellm-rust/crates/db/queries/spend/add_key_spend.sql new file mode 100644 index 00000000000..61850714acd --- /dev/null +++ b/litellm-rust/crates/db/queries/spend/add_key_spend.sql @@ -0,0 +1,16 @@ +WITH added AS ( + SELECT id, SUM(cost) AS cost + FROM UNNEST($1::text[], $2::float8[]) AS a(id, cost) + GROUP BY id +), locked AS ( + SELECT t.token FROM "LiteLLM_VerificationToken" t + WHERE t.token IN (SELECT id FROM added) + ORDER BY t.token FOR UPDATE +) +UPDATE "LiteLLM_VerificationToken" t +SET spend = t.spend + added.cost, + total_spend = t.total_spend + added.cost, + last_active = (clock_timestamp() AT TIME ZONE 'UTC'), + updated_at = (clock_timestamp() AT TIME ZONE 'UTC') +FROM added +WHERE t.token = added.id AND t.token IN (SELECT token FROM locked) diff --git a/litellm-rust/crates/db/src/lib.rs b/litellm-rust/crates/db/src/lib.rs index ca5cd366eec..b3abf5f5173 100644 --- a/litellm-rust/crates/db/src/lib.rs +++ b/litellm-rust/crates/db/src/lib.rs @@ -10,6 +10,7 @@ mod daily_spend; mod end_user; mod error; mod failure; +mod spend; #[cfg(test)] mod test_support; @@ -17,3 +18,4 @@ pub use daily_spend::{DailyEndUserRow, DailyTeamRow, DailyUserRow}; pub use end_user::{EndUser, RateLimits, find_end_user}; pub use error::Error; pub use failure::DbFailure; +pub use spend::{EntitySpend, add_key_spend}; diff --git a/litellm-rust/crates/db/src/spend/key_spend.rs b/litellm-rust/crates/db/src/spend/key_spend.rs new file mode 100644 index 00000000000..5a6ba13307c --- /dev/null +++ b/litellm-rust/crates/db/src/spend/key_spend.rs @@ -0,0 +1,309 @@ +use sqlx::PgExecutor; +use std::collections::BTreeMap; + +use crate::Error; + +#[macro_rules_attribute::apply(crate::db_input)] +#[derive(Default)] +pub struct EntitySpend { + pub ids: Vec, + pub costs: Vec, +} + +impl EntitySpend { + pub(crate) fn validate(&self) -> Result<(), Error> { + if self.ids.len() != self.costs.len() { + return Err(Error::InvalidSpendBatch { + ids: self.ids.len(), + costs: self.costs.len(), + }); + } + Ok(()) + } + + pub fn is_empty(&self) -> bool { + self.ids.is_empty() + } +} + +impl FromIterator<(String, f64)> for EntitySpend { + fn from_iter>(entries: I) -> Self { + let entries = entries + .into_iter() + .fold(BTreeMap::new(), |mut sums, (id, cost)| { + *sums.entry(id).or_insert(0.0) += cost; + sums + }); + let (ids, costs) = entries.into_iter().unzip(); + Self { ids, costs } + } +} + +pub async fn add_key_spend( + executor: impl PgExecutor<'_>, + spend: &EntitySpend, +) -> Result<(), Error> { + spend.validate()?; + if spend.is_empty() { + return Ok(()); + } + sqlx::query_file!("queries/spend/add_key_spend.sql", &spend.ids, &spend.costs) + .execute(executor) + .await?; + Ok(()) +} + +#[cfg(test)] +mod tests { + use std::error::Error as StdError; + + use super::{EntitySpend, add_key_spend}; + use crate::{Error, test_support::database_pool}; + use rstest::rstest; + use sqlx::PgPool; + + #[rstest] + #[case::direct(false)] + #[case::collected(true)] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn duplicate_key_spend_accumulates( + #[case] collected: bool, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + sqlx::query( + r#"INSERT INTO "LiteLLM_VerificationToken" (token, spend, total_spend, updated_at) + VALUES ('key-spend-duplicate', 2, 7, '2000-01-01')"#, + ) + .execute(&mut *tx) + .await?; + let spend = if collected { + [ + ("key-spend-duplicate".into(), 0.25), + ("key-spend-duplicate".into(), 0.75), + ] + .into_iter() + .collect() + } else { + EntitySpend { + ids: vec!["key-spend-duplicate".into(), "key-spend-duplicate".into()], + costs: vec![0.25, 0.75], + } + }; + add_key_spend(&mut *tx, &spend).await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let row: (f64, f64) = sqlx::query_as( + r#"SELECT spend, total_spend FROM "LiteLLM_VerificationToken" + WHERE token = 'key-spend-duplicate'"#, + ) + .fetch_one(&mut *tx) + .await?; + assert_eq!(row, (3.0, 8.0)); + Ok(()) + } + + #[rstest] + #[case::extra_id(vec!["key-spend-invalid".into(), "key-spend-invalid".into()], vec![0.25])] + #[case::extra_cost(vec!["key-spend-invalid".into()], vec![0.25, 0.75])] + #[case::empty_ids(vec![], vec![0.25])] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn malformed_key_spend_leaves_transaction_usable( + #[case] ids: Vec, + #[case] costs: Vec, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + sqlx::query( + r#"INSERT INTO "LiteLLM_VerificationToken" + (token, spend, total_spend, last_active, updated_at) + VALUES ('key-spend-invalid', 2, 7, NULL, '2000-01-01')"#, + ) + .execute(&mut *tx) + .await?; + let spend = EntitySpend { ids, costs }; + let result = add_key_spend(&mut *tx, &spend).await; + assert!(matches!( + result, + Err(Error::InvalidSpendBatch { ids, costs }) + if ids == spend.ids.len() && costs == spend.costs.len() + )); + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let unchanged: (f64, f64, bool, bool) = sqlx::query_as( + r#"SELECT spend, total_spend, last_active IS NULL, + updated_at = TIMESTAMP '2000-01-01' + FROM "LiteLLM_VerificationToken" WHERE token = 'key-spend-invalid'"#, + ) + .fetch_one(&mut *tx) + .await?; + assert_eq!(unchanged, (2.0, 7.0, true, true)); + let valid = EntitySpend { + ids: vec!["key-spend-invalid".into()], + costs: vec![0.5], + }; + add_key_spend(&mut *tx, &valid).await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let updated: (f64, f64) = sqlx::query_as( + r#"SELECT spend, total_spend FROM "LiteLLM_VerificationToken" + WHERE token = 'key-spend-invalid'"#, + ) + .fetch_one(&mut *tx) + .await?; + assert_eq!(updated, (2.5, 7.5)); + Ok(()) + } + + #[rstest] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn key_activity_uses_update_time_in_old_transaction( + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + sqlx::query( + r#"INSERT INTO "LiteLLM_VerificationToken" (token, spend, total_spend, updated_at) + VALUES ('key-spend-old-transaction', 2, 7, '2000-01-01')"#, + ) + .execute(&mut *tx) + .await?; + #[expect( + clippy::disallowed_methods, + reason = "Transaction timing setup is outside the compile-checked query set" + )] + sqlx::query("SELECT pg_sleep(0.02)") + .execute(&mut *tx) + .await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let boundary: chrono::NaiveDateTime = sqlx::query_scalar( + "SELECT date_trunc('milliseconds', clock_timestamp() AT TIME ZONE 'UTC')", + ) + .fetch_one(&mut *tx) + .await?; + let spend = EntitySpend { + ids: vec!["key-spend-old-transaction".into()], + costs: vec![0.25], + }; + add_key_spend(&mut *tx, &spend).await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let row: (chrono::NaiveDateTime, chrono::NaiveDateTime) = sqlx::query_as( + r#"SELECT last_active, updated_at FROM "LiteLLM_VerificationToken" + WHERE token = 'key-spend-old-transaction'"#, + ) + .fetch_one(&mut *tx) + .await?; + assert!(row.0 >= boundary, "last_active predates update boundary"); + assert!(row.1 >= boundary, "updated_at predates update boundary"); + Ok(()) + } + + #[rstest] + #[case::fractional_costs(0.25, 2.5, 7.5, 4.0, 12.0)] + #[case::zero_costs(0.0, 2.0, 7.0, 3.0, 11.0)] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn key_spend_matches_python_update_many( + #[case] cost: f64, + #[case] expected_a_spend: f64, + #[case] expected_a_total: f64, + #[case] expected_z_spend: f64, + #[case] expected_z_total: f64, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + let _inserted = sqlx::query( + r#"INSERT INTO "LiteLLM_VerificationToken" + (token, spend, total_spend, last_active, updated_at) + VALUES ('key-spend-a', 2, 7, NULL, '2000-01-01'), + ('key-spend-z', 3, 11, NULL, '2000-01-01'), + ('key-spend-untouched', 100, 200, NULL, '2000-01-01')"#, + ) + .execute(&mut *tx) + .await?; + let spend = EntitySpend { + ids: vec![ + "key-spend-z".into(), + "key-spend-a".into(), + "key-spend-missing".into(), + ], + costs: vec![2.0 * cost, cost, 50.0], + }; + add_key_spend(&mut *tx, &EntitySpend::default()).await?; + add_key_spend(&mut *tx, &spend).await?; + add_key_spend(&mut *tx, &spend).await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let rows: Vec<(String, f64, f64, bool, bool)> = sqlx::query_as( + r#"SELECT token, spend, total_spend, last_active IS NOT NULL, + updated_at > TIMESTAMP '2000-01-01' + FROM "LiteLLM_VerificationToken" + WHERE token = ANY($1) ORDER BY token"#, + ) + .bind(vec![ + "key-spend-a", + "key-spend-z", + "key-spend-missing", + "key-spend-untouched", + ]) + .fetch_all(&mut *tx) + .await?; + assert_eq!( + rows, + vec![ + ( + "key-spend-a".into(), + expected_a_spend, + expected_a_total, + true, + true + ), + ("key-spend-untouched".into(), 100.0, 200.0, false, false), + ( + "key-spend-z".into(), + expected_z_spend, + expected_z_total, + true, + true + ), + ] + ); + Ok(()) + } +} diff --git a/litellm-rust/crates/db/src/spend/mod.rs b/litellm-rust/crates/db/src/spend/mod.rs new file mode 100644 index 00000000000..e34886c6130 --- /dev/null +++ b/litellm-rust/crates/db/src/spend/mod.rs @@ -0,0 +1,3 @@ +mod key_spend; + +pub use key_spend::{EntitySpend, add_key_spend}; From 8e61c22fe0be640b4cfb0d22c9bfa178c250cc45 Mon Sep 17 00:00:00 2001 From: yujonglee Date: Mon, 26 Oct 2026 17:05:04 -0700 Subject: [PATCH 009/262] feat(db): add typed user spend query (#48229) Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...3b87a20a2664b0bef3616631d2c24487c1e54.json | 15 ++ .../db/queries/spend/add_user_spend.sql | 14 ++ litellm-rust/crates/db/src/lib.rs | 2 +- litellm-rust/crates/db/src/spend/mod.rs | 2 + .../crates/db/src/spend/user_spend.rs | 173 ++++++++++++++++++ 5 files changed, 205 insertions(+), 1 deletion(-) create mode 100644 litellm-rust/crates/db/.sqlx/query-43f2e12a3ffb1de29b5b031a1173b87a20a2664b0bef3616631d2c24487c1e54.json create mode 100644 litellm-rust/crates/db/queries/spend/add_user_spend.sql create mode 100644 litellm-rust/crates/db/src/spend/user_spend.rs diff --git a/litellm-rust/crates/db/.sqlx/query-43f2e12a3ffb1de29b5b031a1173b87a20a2664b0bef3616631d2c24487c1e54.json b/litellm-rust/crates/db/.sqlx/query-43f2e12a3ffb1de29b5b031a1173b87a20a2664b0bef3616631d2c24487c1e54.json new file mode 100644 index 00000000000..a758ae5126a --- /dev/null +++ b/litellm-rust/crates/db/.sqlx/query-43f2e12a3ffb1de29b5b031a1173b87a20a2664b0bef3616631d2c24487c1e54.json @@ -0,0 +1,15 @@ +{ + "db_name": "PostgreSQL", + "query": "WITH added AS (\n SELECT id, SUM(cost) AS cost\n FROM UNNEST($1::text[], $2::float8[]) AS a(id, cost)\n GROUP BY id\n), locked AS (\n SELECT u.user_id FROM \"LiteLLM_UserTable\" u\n WHERE u.user_id IN (SELECT id FROM added)\n ORDER BY u.user_id FOR UPDATE\n)\nUPDATE \"LiteLLM_UserTable\" u\nSET spend = u.spend + added.cost,\n updated_at = (NOW() AT TIME ZONE 'UTC')\nFROM added\nWHERE u.user_id = added.id AND u.user_id IN (SELECT user_id FROM locked)\n", + "describe": { + "columns": [], + "parameters": { + "Left": [ + "TextArray", + "Float8Array" + ] + }, + "nullable": [] + }, + "hash": "43f2e12a3ffb1de29b5b031a1173b87a20a2664b0bef3616631d2c24487c1e54" +} diff --git a/litellm-rust/crates/db/queries/spend/add_user_spend.sql b/litellm-rust/crates/db/queries/spend/add_user_spend.sql new file mode 100644 index 00000000000..27fc12e82f0 --- /dev/null +++ b/litellm-rust/crates/db/queries/spend/add_user_spend.sql @@ -0,0 +1,14 @@ +WITH added AS ( + SELECT id, SUM(cost) AS cost + FROM UNNEST($1::text[], $2::float8[]) AS a(id, cost) + GROUP BY id +), locked AS ( + SELECT u.user_id FROM "LiteLLM_UserTable" u + WHERE u.user_id IN (SELECT id FROM added) + ORDER BY u.user_id FOR UPDATE +) +UPDATE "LiteLLM_UserTable" u +SET spend = u.spend + added.cost, + updated_at = (NOW() AT TIME ZONE 'UTC') +FROM added +WHERE u.user_id = added.id AND u.user_id IN (SELECT user_id FROM locked) diff --git a/litellm-rust/crates/db/src/lib.rs b/litellm-rust/crates/db/src/lib.rs index b3abf5f5173..6589b46b24a 100644 --- a/litellm-rust/crates/db/src/lib.rs +++ b/litellm-rust/crates/db/src/lib.rs @@ -18,4 +18,4 @@ pub use daily_spend::{DailyEndUserRow, DailyTeamRow, DailyUserRow}; pub use end_user::{EndUser, RateLimits, find_end_user}; pub use error::Error; pub use failure::DbFailure; -pub use spend::{EntitySpend, add_key_spend}; +pub use spend::{EntitySpend, add_key_spend, add_user_spend}; diff --git a/litellm-rust/crates/db/src/spend/mod.rs b/litellm-rust/crates/db/src/spend/mod.rs index e34886c6130..98530805fdd 100644 --- a/litellm-rust/crates/db/src/spend/mod.rs +++ b/litellm-rust/crates/db/src/spend/mod.rs @@ -1,3 +1,5 @@ mod key_spend; +mod user_spend; pub use key_spend::{EntitySpend, add_key_spend}; +pub use user_spend::add_user_spend; diff --git a/litellm-rust/crates/db/src/spend/user_spend.rs b/litellm-rust/crates/db/src/spend/user_spend.rs new file mode 100644 index 00000000000..2c89c04c1ef --- /dev/null +++ b/litellm-rust/crates/db/src/spend/user_spend.rs @@ -0,0 +1,173 @@ +use sqlx::PgExecutor; + +use super::EntitySpend; +use crate::Error; + +pub async fn add_user_spend( + executor: impl PgExecutor<'_>, + spend: &EntitySpend, +) -> Result<(), Error> { + spend.validate()?; + if spend.is_empty() { + return Ok(()); + } + sqlx::query_file!("queries/spend/add_user_spend.sql", &spend.ids, &spend.costs) + .execute(executor) + .await?; + Ok(()) +} + +#[cfg(test)] +mod tests { + use std::error::Error as StdError; + + use super::{EntitySpend, add_user_spend}; + use crate::{Error, test_support::database_pool}; + use rstest::rstest; + use sqlx::PgPool; + + #[rstest] + #[case::fractional_costs(0.25, 2.5, 4.0)] + #[case::zero_costs(0.0, 2.0, 3.0)] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn user_spend_matches_python_update_many( + #[case] cost: f64, + #[case] expected_a_spend: f64, + #[case] expected_z_spend: f64, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + let _inserted = sqlx::query( + r#"INSERT INTO "LiteLLM_UserTable" (user_id, spend, updated_at) + VALUES ('user-spend-a', 2, '2000-01-01'), + ('user-spend-z', 3, '2000-01-01'), + ('user-spend-untouched', 100, '2000-01-01')"#, + ) + .execute(&mut *tx) + .await?; + let spend = EntitySpend { + ids: vec![ + "user-spend-z".into(), + "user-spend-a".into(), + "user-spend-missing".into(), + ], + costs: vec![2.0 * cost, cost, 50.0], + }; + add_user_spend(&mut *tx, &EntitySpend::default()).await?; + add_user_spend(&mut *tx, &spend).await?; + add_user_spend(&mut *tx, &spend).await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let rows: Vec<(String, f64, bool)> = sqlx::query_as( + r#"SELECT user_id, spend, updated_at > TIMESTAMP '2000-01-01' + FROM "LiteLLM_UserTable" + WHERE user_id = ANY($1) ORDER BY user_id"#, + ) + .bind(vec![ + "user-spend-a", + "user-spend-z", + "user-spend-missing", + "user-spend-untouched", + ]) + .fetch_all(&mut *tx) + .await?; + assert_eq!( + rows, + vec![ + ("user-spend-a".into(), expected_a_spend, true), + ("user-spend-untouched".into(), 100.0, false), + ("user-spend-z".into(), expected_z_spend, true), + ] + ); + Ok(()) + } + + #[rstest] + #[case::direct_duplicate_batch(vec![0.25, 0.75], 3.0)] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn user_spend_sums_duplicate_ids( + #[case] costs: Vec, + #[case] expected_spend: f64, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + let _inserted = sqlx::query( + r#"INSERT INTO "LiteLLM_UserTable" (user_id, spend, updated_at) + VALUES ('user-spend-duplicate', 2, '2000-01-01')"#, + ) + .execute(&mut *tx) + .await?; + let spend = EntitySpend { + ids: vec!["user-spend-duplicate".into(), "user-spend-duplicate".into()], + costs, + }; + add_user_spend(&mut *tx, &spend).await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let row: (f64, bool) = sqlx::query_as( + r#"SELECT spend, updated_at > TIMESTAMP '2000-01-01' + FROM "LiteLLM_UserTable" WHERE user_id = 'user-spend-duplicate'"#, + ) + .fetch_one(&mut *tx) + .await?; + assert_eq!(row, (expected_spend, true)); + Ok(()) + } + + #[rstest] + #[case::missing_cost(vec![])] + #[case::extra_cost(vec![0.25, 0.75])] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn user_spend_rejects_malformed_batch_without_writes( + #[case] costs: Vec, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + let _inserted = sqlx::query( + r#"INSERT INTO "LiteLLM_UserTable" (user_id, spend, updated_at) + VALUES ('user-spend-malformed', 2, '2000-01-01')"#, + ) + .execute(&mut *tx) + .await?; + let spend = EntitySpend { + ids: vec!["user-spend-malformed".into()], + costs, + }; + let result = add_user_spend(&mut *tx, &spend).await; + assert!(matches!(result, Err(Error::InvalidSpendBatch { .. }))); + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let row: (f64, bool) = sqlx::query_as( + r#"SELECT spend, updated_at = TIMESTAMP '2000-01-01' + FROM "LiteLLM_UserTable" WHERE user_id = 'user-spend-malformed'"#, + ) + .fetch_one(&mut *tx) + .await?; + assert_eq!(row, (2.0, true)); + Ok(()) + } +} From 3b72c08c4fc15a4607914652b54c21df71b530a1 Mon Sep 17 00:00:00 2001 From: yujonglee Date: Mon, 26 Oct 2026 17:05:05 -0700 Subject: [PATCH 010/262] feat(db): add typed team spend query (#48230) Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...edd37a575d641bb68d91e61f5123173c275ce.json | 15 ++ .../db/queries/spend/add_team_spend.sql | 15 ++ litellm-rust/crates/db/src/lib.rs | 2 +- litellm-rust/crates/db/src/spend/mod.rs | 2 + .../crates/db/src/spend/team_spend.rs | 182 ++++++++++++++++++ 5 files changed, 215 insertions(+), 1 deletion(-) create mode 100644 litellm-rust/crates/db/.sqlx/query-c3e5542906e89995fae2a16eca1edd37a575d641bb68d91e61f5123173c275ce.json create mode 100644 litellm-rust/crates/db/queries/spend/add_team_spend.sql create mode 100644 litellm-rust/crates/db/src/spend/team_spend.rs diff --git a/litellm-rust/crates/db/.sqlx/query-c3e5542906e89995fae2a16eca1edd37a575d641bb68d91e61f5123173c275ce.json b/litellm-rust/crates/db/.sqlx/query-c3e5542906e89995fae2a16eca1edd37a575d641bb68d91e61f5123173c275ce.json new file mode 100644 index 00000000000..250971b053a --- /dev/null +++ b/litellm-rust/crates/db/.sqlx/query-c3e5542906e89995fae2a16eca1edd37a575d641bb68d91e61f5123173c275ce.json @@ -0,0 +1,15 @@ +{ + "db_name": "PostgreSQL", + "query": "WITH added AS (\n SELECT id, SUM(cost) AS cost\n FROM UNNEST($1::text[], $2::float8[]) AS a(id, cost)\n GROUP BY id\n),\nlocked AS (\n SELECT t.team_id FROM \"LiteLLM_TeamTable\" t\n WHERE t.team_id IN (SELECT id FROM added)\n ORDER BY t.team_id FOR UPDATE\n)\nUPDATE \"LiteLLM_TeamTable\" t\nSET spend = t.spend + added.cost,\n updated_at = (NOW() AT TIME ZONE 'UTC')\nFROM added\nWHERE t.team_id = added.id AND t.team_id IN (SELECT team_id FROM locked)\n", + "describe": { + "columns": [], + "parameters": { + "Left": [ + "TextArray", + "Float8Array" + ] + }, + "nullable": [] + }, + "hash": "c3e5542906e89995fae2a16eca1edd37a575d641bb68d91e61f5123173c275ce" +} diff --git a/litellm-rust/crates/db/queries/spend/add_team_spend.sql b/litellm-rust/crates/db/queries/spend/add_team_spend.sql new file mode 100644 index 00000000000..58b8e3d6ab9 --- /dev/null +++ b/litellm-rust/crates/db/queries/spend/add_team_spend.sql @@ -0,0 +1,15 @@ +WITH added AS ( + SELECT id, SUM(cost) AS cost + FROM UNNEST($1::text[], $2::float8[]) AS a(id, cost) + GROUP BY id +), +locked AS ( + SELECT t.team_id FROM "LiteLLM_TeamTable" t + WHERE t.team_id IN (SELECT id FROM added) + ORDER BY t.team_id FOR UPDATE +) +UPDATE "LiteLLM_TeamTable" t +SET spend = t.spend + added.cost, + updated_at = (NOW() AT TIME ZONE 'UTC') +FROM added +WHERE t.team_id = added.id AND t.team_id IN (SELECT team_id FROM locked) diff --git a/litellm-rust/crates/db/src/lib.rs b/litellm-rust/crates/db/src/lib.rs index 6589b46b24a..1dda3a987b0 100644 --- a/litellm-rust/crates/db/src/lib.rs +++ b/litellm-rust/crates/db/src/lib.rs @@ -18,4 +18,4 @@ pub use daily_spend::{DailyEndUserRow, DailyTeamRow, DailyUserRow}; pub use end_user::{EndUser, RateLimits, find_end_user}; pub use error::Error; pub use failure::DbFailure; -pub use spend::{EntitySpend, add_key_spend, add_user_spend}; +pub use spend::{EntitySpend, add_key_spend, add_team_spend, add_user_spend}; diff --git a/litellm-rust/crates/db/src/spend/mod.rs b/litellm-rust/crates/db/src/spend/mod.rs index 98530805fdd..775be335150 100644 --- a/litellm-rust/crates/db/src/spend/mod.rs +++ b/litellm-rust/crates/db/src/spend/mod.rs @@ -1,5 +1,7 @@ mod key_spend; +mod team_spend; mod user_spend; pub use key_spend::{EntitySpend, add_key_spend}; +pub use team_spend::add_team_spend; pub use user_spend::add_user_spend; diff --git a/litellm-rust/crates/db/src/spend/team_spend.rs b/litellm-rust/crates/db/src/spend/team_spend.rs new file mode 100644 index 00000000000..a105899bc2a --- /dev/null +++ b/litellm-rust/crates/db/src/spend/team_spend.rs @@ -0,0 +1,182 @@ +use sqlx::PgExecutor; + +use super::EntitySpend; +use crate::Error; + +pub async fn add_team_spend( + executor: impl PgExecutor<'_>, + spend: &EntitySpend, +) -> Result<(), Error> { + spend.validate()?; + if spend.is_empty() { + return Ok(()); + } + sqlx::query_file!("queries/spend/add_team_spend.sql", &spend.ids, &spend.costs) + .execute(executor) + .await?; + Ok(()) +} + +#[cfg(test)] +mod tests { + use std::error::Error as StdError; + + use super::{EntitySpend, add_team_spend}; + use crate::Error; + use crate::test_support::database_pool; + use rstest::rstest; + use sqlx::PgPool; + + #[rstest] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn duplicate_team_ids_add_every_cost( + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + let _inserted = sqlx::query( + r#"INSERT INTO "LiteLLM_TeamTable" (team_id, spend, created_at, updated_at) + VALUES ('team-spend-duplicate-a', 2, '2000-01-01', '2000-01-01'), + ('team-spend-duplicate-z', 3, '2000-01-01', '2000-01-01')"#, + ) + .execute(&mut *tx) + .await?; + let spend = EntitySpend { + ids: vec![ + "team-spend-duplicate-z".into(), + "team-spend-duplicate-a".into(), + "team-spend-duplicate-z".into(), + "team-spend-duplicate-a".into(), + ], + costs: vec![0.5, 0.25, 1.0, 0.5], + }; + add_team_spend(&mut *tx, &spend).await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let rows: Vec<(String, f64)> = sqlx::query_as( + r#"SELECT team_id, spend FROM "LiteLLM_TeamTable" + WHERE team_id = ANY($1) ORDER BY team_id"#, + ) + .bind(&spend.ids) + .fetch_all(&mut *tx) + .await?; + assert_eq!( + rows, + vec![ + ("team-spend-duplicate-a".into(), 2.75), + ("team-spend-duplicate-z".into(), 4.5), + ] + ); + Ok(()) + } + + #[rstest] + #[case::missing_cost(vec!["team-spend-malformed".into()], vec![])] + #[case::extra_cost(vec!["team-spend-malformed".into()], vec![0.25, 0.5])] + #[case::empty_ids(vec![], vec![0.25])] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn malformed_team_batch_does_not_write( + #[case] ids: Vec, + #[case] costs: Vec, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + let _inserted = sqlx::query( + r#"INSERT INTO "LiteLLM_TeamTable" (team_id, spend, created_at, updated_at) + VALUES ('team-spend-malformed', 2, '2000-01-01', '2000-01-01')"#, + ) + .execute(&mut *tx) + .await?; + let result = add_team_spend(&mut *tx, &EntitySpend { ids, costs }).await; + assert!(matches!(result, Err(Error::InvalidSpendBatch { .. }))); + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let row: (f64, bool) = sqlx::query_as( + r#"SELECT spend, updated_at = TIMESTAMP '2000-01-01' + FROM "LiteLLM_TeamTable" WHERE team_id = 'team-spend-malformed'"#, + ) + .fetch_one(&mut *tx) + .await?; + assert_eq!(row, (2.0, true)); + Ok(()) + } + + #[rstest] + #[case::fractional_costs(0.25, 2.5, 4.0)] + #[case::zero_costs(0.0, 2.0, 3.0)] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn team_spend_matches_python_update_many( + #[case] cost: f64, + #[case] expected_a_spend: f64, + #[case] expected_z_spend: f64, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + let _inserted = sqlx::query( + r#"INSERT INTO "LiteLLM_TeamTable" (team_id, spend, created_at, updated_at) + VALUES ('team-spend-a', 2, '2000-01-01', '2000-01-01'), + ('team-spend-z', 3, '2000-01-01', '2000-01-01'), + ('team-spend-untouched', 100, '2000-01-01', '2000-01-01')"#, + ) + .execute(&mut *tx) + .await?; + let spend = EntitySpend { + ids: vec![ + "team-spend-z".into(), + "team-spend-a".into(), + "team-spend-missing".into(), + ], + costs: vec![2.0 * cost, cost, 50.0], + }; + add_team_spend(&mut *tx, &EntitySpend::default()).await?; + add_team_spend(&mut *tx, &spend).await?; + add_team_spend(&mut *tx, &spend).await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let rows: Vec<(String, f64, bool)> = sqlx::query_as( + r#"SELECT team_id, spend, updated_at > TIMESTAMP '2000-01-01' + FROM "LiteLLM_TeamTable" + WHERE team_id = ANY($1) ORDER BY team_id"#, + ) + .bind(vec![ + "team-spend-a", + "team-spend-z", + "team-spend-missing", + "team-spend-untouched", + ]) + .fetch_all(&mut *tx) + .await?; + assert_eq!( + rows, + vec![ + ("team-spend-a".into(), expected_a_spend, true), + ("team-spend-untouched".into(), 100.0, false), + ("team-spend-z".into(), expected_z_spend, true), + ] + ); + Ok(()) + } +} From 8f456eb7d51f52d62621e5672ee47ae9079e078d Mon Sep 17 00:00:00 2001 From: yujonglee Date: Mon, 26 Oct 2026 17:05:05 -0700 Subject: [PATCH 011/262] feat(db): add typed end-user spend query (#48231) Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...2288e0f2c1f12a2a79ed53f0002826724cd0a.json | 15 ++ .../db/queries/spend/add_end_user_spend.sql | 6 + litellm-rust/crates/db/src/lib.rs | 2 +- .../crates/db/src/spend/end_user_spend.rs | 197 ++++++++++++++++++ litellm-rust/crates/db/src/spend/mod.rs | 2 + 5 files changed, 221 insertions(+), 1 deletion(-) create mode 100644 litellm-rust/crates/db/.sqlx/query-345c02595f55a7f0274ef7214b02288e0f2c1f12a2a79ed53f0002826724cd0a.json create mode 100644 litellm-rust/crates/db/queries/spend/add_end_user_spend.sql create mode 100644 litellm-rust/crates/db/src/spend/end_user_spend.rs diff --git a/litellm-rust/crates/db/.sqlx/query-345c02595f55a7f0274ef7214b02288e0f2c1f12a2a79ed53f0002826724cd0a.json b/litellm-rust/crates/db/.sqlx/query-345c02595f55a7f0274ef7214b02288e0f2c1f12a2a79ed53f0002826724cd0a.json new file mode 100644 index 00000000000..123ff15ade2 --- /dev/null +++ b/litellm-rust/crates/db/.sqlx/query-345c02595f55a7f0274ef7214b02288e0f2c1f12a2a79ed53f0002826724cd0a.json @@ -0,0 +1,15 @@ +{ + "db_name": "PostgreSQL", + "query": "INSERT INTO \"LiteLLM_EndUserTable\" (user_id, spend, blocked)\nSELECT id, SUM(cost), false FROM UNNEST($1::text[], $2::float8[]) AS a(id, cost)\nGROUP BY id\nORDER BY id\nON CONFLICT (user_id) DO UPDATE\nSET spend = \"LiteLLM_EndUserTable\".spend + EXCLUDED.spend\n", + "describe": { + "columns": [], + "parameters": { + "Left": [ + "TextArray", + "Float8Array" + ] + }, + "nullable": [] + }, + "hash": "345c02595f55a7f0274ef7214b02288e0f2c1f12a2a79ed53f0002826724cd0a" +} diff --git a/litellm-rust/crates/db/queries/spend/add_end_user_spend.sql b/litellm-rust/crates/db/queries/spend/add_end_user_spend.sql new file mode 100644 index 00000000000..06a5b96d254 --- /dev/null +++ b/litellm-rust/crates/db/queries/spend/add_end_user_spend.sql @@ -0,0 +1,6 @@ +INSERT INTO "LiteLLM_EndUserTable" (user_id, spend, blocked) +SELECT id, SUM(cost), false FROM UNNEST($1::text[], $2::float8[]) AS a(id, cost) +GROUP BY id +ORDER BY id +ON CONFLICT (user_id) DO UPDATE +SET spend = "LiteLLM_EndUserTable".spend + EXCLUDED.spend diff --git a/litellm-rust/crates/db/src/lib.rs b/litellm-rust/crates/db/src/lib.rs index 1dda3a987b0..3a9032d73dc 100644 --- a/litellm-rust/crates/db/src/lib.rs +++ b/litellm-rust/crates/db/src/lib.rs @@ -18,4 +18,4 @@ pub use daily_spend::{DailyEndUserRow, DailyTeamRow, DailyUserRow}; pub use end_user::{EndUser, RateLimits, find_end_user}; pub use error::Error; pub use failure::DbFailure; -pub use spend::{EntitySpend, add_key_spend, add_team_spend, add_user_spend}; +pub use spend::{EntitySpend, add_end_user_spend, add_key_spend, add_team_spend, add_user_spend}; diff --git a/litellm-rust/crates/db/src/spend/end_user_spend.rs b/litellm-rust/crates/db/src/spend/end_user_spend.rs new file mode 100644 index 00000000000..ca327ac7e18 --- /dev/null +++ b/litellm-rust/crates/db/src/spend/end_user_spend.rs @@ -0,0 +1,197 @@ +use sqlx::PgExecutor; + +use super::EntitySpend; +use crate::Error; + +pub async fn add_end_user_spend( + executor: impl PgExecutor<'_>, + spend: &EntitySpend, +) -> Result<(), Error> { + spend.validate()?; + if spend.is_empty() { + return Ok(()); + } + sqlx::query_file!( + "queries/spend/add_end_user_spend.sql", + &spend.ids, + &spend.costs + ) + .execute(executor) + .await?; + Ok(()) +} + +#[cfg(test)] +mod tests { + use std::error::Error as StdError; + + use super::{EntitySpend, add_end_user_spend}; + use crate::test_support::database_pool; + use rstest::rstest; + use sqlx::PgPool; + + #[rstest] + #[case::fractional_costs(0.25, 0.75, false, 2.5, 1.5)] + #[case::zero_costs(0.0, 0.0, false, 2.0, 0.0)] + #[case::duplicate_ids(0.25, 0.75, true, 3.0, 3.0)] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn end_user_spend_matches_python_upsert( + #[case] existing_cost: f64, + #[case] new_cost: f64, + #[case] duplicate_ids: bool, + #[case] expected_existing_spend: f64, + #[case] expected_new_spend: f64, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + let _budget = sqlx::query( + r#"INSERT INTO "LiteLLM_BudgetTable" (budget_id, created_by, updated_by) + VALUES ('end-user-spend-budget', 'db-query-test', 'db-query-test')"#, + ) + .execute(&mut *tx) + .await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + let _users = sqlx::query( + r#"INSERT INTO "LiteLLM_EndUserTable" (user_id, spend, blocked, budget_id) + VALUES ('end-user-spend-z', 2, true, 'end-user-spend-budget'), + ('end-user-spend-untouched', 100, true, NULL)"#, + ) + .execute(&mut *tx) + .await?; + let spend = if duplicate_ids { + EntitySpend { + ids: vec![ + "end-user-spend-z".into(), + "end-user-spend-a".into(), + "end-user-spend-z".into(), + "end-user-spend-a".into(), + ], + costs: vec![existing_cost, new_cost, existing_cost, new_cost], + } + } else { + EntitySpend { + ids: vec!["end-user-spend-z".into(), "end-user-spend-a".into()], + costs: vec![existing_cost, new_cost], + } + }; + add_end_user_spend(&mut *tx, &spend).await?; + add_end_user_spend(&mut *tx, &spend).await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let rows: Vec<(String, f64, bool, Option)> = sqlx::query_as( + r#"SELECT user_id, spend, blocked, budget_id FROM "LiteLLM_EndUserTable" + WHERE user_id = ANY($1) ORDER BY user_id"#, + ) + .bind(vec![ + "end-user-spend-a", + "end-user-spend-z", + "end-user-spend-untouched", + ]) + .fetch_all(&mut *tx) + .await?; + assert_eq!( + rows, + vec![ + ("end-user-spend-a".into(), expected_new_spend, false, None), + ("end-user-spend-untouched".into(), 100.0, true, None), + ( + "end-user-spend-z".into(), + expected_existing_spend, + true, + Some("end-user-spend-budget".into()), + ), + ] + ); + Ok(()) + } + + #[rstest] + #[case::missing_cost(vec!["end-user-invalid-existing".into(), "end-user-invalid-new".into()], vec![1.0])] + #[case::extra_cost(vec!["end-user-invalid-existing".into()], vec![1.0, 2.0])] + #[case::empty_ids(vec![], vec![1.0])] + #[case::empty_costs(vec!["end-user-invalid-existing".into()], vec![])] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn malformed_end_user_spend_is_rejected_before_writes( + #[case] ids: Vec, + #[case] costs: Vec, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + let _user = sqlx::query( + r#"INSERT INTO "LiteLLM_EndUserTable" (user_id, spend, blocked) + VALUES ('end-user-invalid-existing', 8.5, true)"#, + ) + .execute(&mut *tx) + .await?; + let spend = EntitySpend { ids, costs }; + let result = add_end_user_spend(&mut *tx, &spend).await; + assert!(matches!( + result, + Err(crate::Error::InvalidSpendBatch { ids, costs }) + if ids == spend.ids.len() && costs == spend.costs.len() + )); + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let rows: Vec<(String, f64, bool)> = sqlx::query_as( + r#"SELECT user_id, spend, blocked FROM "LiteLLM_EndUserTable" + WHERE user_id IN ('end-user-invalid-existing', 'end-user-invalid-new')"#, + ) + .fetch_all(&mut *tx) + .await?; + assert_eq!(rows, vec![("end-user-invalid-existing".into(), 8.5, true)]); + Ok(()) + } + + #[rstest] + #[case::empty_batch()] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn empty_end_user_spend_is_a_noop( + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + let _user = sqlx::query( + r#"INSERT INTO "LiteLLM_EndUserTable" (user_id, spend, blocked) + VALUES ('end-user-empty-spend', 8.5, true)"#, + ) + .execute(&mut *tx) + .await?; + add_end_user_spend(&mut *tx, &EntitySpend::default()).await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let row: (f64, bool, Option) = sqlx::query_as( + r#"SELECT spend, blocked, budget_id FROM "LiteLLM_EndUserTable" + WHERE user_id = 'end-user-empty-spend'"#, + ) + .fetch_one(&mut *tx) + .await?; + assert_eq!(row, (8.5, true, None)); + Ok(()) + } +} diff --git a/litellm-rust/crates/db/src/spend/mod.rs b/litellm-rust/crates/db/src/spend/mod.rs index 775be335150..5191da2adb5 100644 --- a/litellm-rust/crates/db/src/spend/mod.rs +++ b/litellm-rust/crates/db/src/spend/mod.rs @@ -1,7 +1,9 @@ +mod end_user_spend; mod key_spend; mod team_spend; mod user_spend; +pub use end_user_spend::add_end_user_spend; pub use key_spend::{EntitySpend, add_key_spend}; pub use team_spend::add_team_spend; pub use user_spend::add_user_spend; From c531692976b348dc4c44f9c6d235e0cf981632fe Mon Sep 17 00:00:00 2001 From: yujonglee Date: Mon, 26 Oct 2026 17:05:06 -0700 Subject: [PATCH 012/262] feat(db): add transaction-scoped team lock query (#48232) Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...7bb2d97532a9cd461cc5d8da1e1090560ca1f.json | 23 +++++ ...92bf33e16fea1dbb0c32cf89a376a874927f4.json | 21 ++++ .../crates/db/queries/spend/lock_team.sql | 1 + litellm-rust/crates/db/src/lib.rs | 5 +- litellm-rust/crates/db/src/spend/mod.rs | 2 + litellm-rust/crates/db/src/spend/team_lock.rs | 98 +++++++++++++++++++ 6 files changed, 149 insertions(+), 1 deletion(-) create mode 100644 litellm-rust/crates/db/.sqlx/query-085edfb9af2a914466c75b447bc7bb2d97532a9cd461cc5d8da1e1090560ca1f.json create mode 100644 litellm-rust/crates/db/.sqlx/query-5c74f47a2b84574133c520d235192bf33e16fea1dbb0c32cf89a376a874927f4.json create mode 100644 litellm-rust/crates/db/queries/spend/lock_team.sql create mode 100644 litellm-rust/crates/db/src/spend/team_lock.rs diff --git a/litellm-rust/crates/db/.sqlx/query-085edfb9af2a914466c75b447bc7bb2d97532a9cd461cc5d8da1e1090560ca1f.json b/litellm-rust/crates/db/.sqlx/query-085edfb9af2a914466c75b447bc7bb2d97532a9cd461cc5d8da1e1090560ca1f.json new file mode 100644 index 00000000000..a415666d0be --- /dev/null +++ b/litellm-rust/crates/db/.sqlx/query-085edfb9af2a914466c75b447bc7bb2d97532a9cd461cc5d8da1e1090560ca1f.json @@ -0,0 +1,23 @@ +{ + "db_name": "PostgreSQL", + "query": "SELECT pg_advisory_xact_lock(hashtext($1)) IS NULL AS \"locked!\"\n", + "describe": { + "columns": [ + { + "ordinal": 0, + "name": "locked!", + "type_info": "Bool", + "origin": "Expression" + } + ], + "parameters": { + "Left": [ + "Text" + ] + }, + "nullable": [ + null + ] + }, + "hash": "085edfb9af2a914466c75b447bc7bb2d97532a9cd461cc5d8da1e1090560ca1f" +} diff --git a/litellm-rust/crates/db/.sqlx/query-5c74f47a2b84574133c520d235192bf33e16fea1dbb0c32cf89a376a874927f4.json b/litellm-rust/crates/db/.sqlx/query-5c74f47a2b84574133c520d235192bf33e16fea1dbb0c32cf89a376a874927f4.json new file mode 100644 index 00000000000..7eef5278cb5 --- /dev/null +++ b/litellm-rust/crates/db/.sqlx/query-5c74f47a2b84574133c520d235192bf33e16fea1dbb0c32cf89a376a874927f4.json @@ -0,0 +1,21 @@ +{ + "db_name": "PostgreSQL", + "query": "SELECT set_config('lock_timeout', '5000ms', true)", + "describe": { + "columns": [ + { + "ordinal": 0, + "name": "set_config", + "type_info": "Text", + "origin": "Expression" + } + ], + "parameters": { + "Left": [] + }, + "nullable": [ + null + ] + }, + "hash": "5c74f47a2b84574133c520d235192bf33e16fea1dbb0c32cf89a376a874927f4" +} diff --git a/litellm-rust/crates/db/queries/spend/lock_team.sql b/litellm-rust/crates/db/queries/spend/lock_team.sql new file mode 100644 index 00000000000..06cdb806ef0 --- /dev/null +++ b/litellm-rust/crates/db/queries/spend/lock_team.sql @@ -0,0 +1 @@ +SELECT pg_advisory_xact_lock(hashtext($1)) IS NULL AS "locked!" diff --git a/litellm-rust/crates/db/src/lib.rs b/litellm-rust/crates/db/src/lib.rs index 3a9032d73dc..4f009b411fd 100644 --- a/litellm-rust/crates/db/src/lib.rs +++ b/litellm-rust/crates/db/src/lib.rs @@ -18,4 +18,7 @@ pub use daily_spend::{DailyEndUserRow, DailyTeamRow, DailyUserRow}; pub use end_user::{EndUser, RateLimits, find_end_user}; pub use error::Error; pub use failure::DbFailure; -pub use spend::{EntitySpend, add_end_user_spend, add_key_spend, add_team_spend, add_user_spend}; +pub use spend::{ + EntitySpend, add_end_user_spend, add_key_spend, add_team_spend, add_user_spend, begin, + lock_team, +}; diff --git a/litellm-rust/crates/db/src/spend/mod.rs b/litellm-rust/crates/db/src/spend/mod.rs index 5191da2adb5..0459e63aaf8 100644 --- a/litellm-rust/crates/db/src/spend/mod.rs +++ b/litellm-rust/crates/db/src/spend/mod.rs @@ -1,9 +1,11 @@ mod end_user_spend; mod key_spend; +mod team_lock; mod team_spend; mod user_spend; pub use end_user_spend::add_end_user_spend; pub use key_spend::{EntitySpend, add_key_spend}; +pub use team_lock::{begin, lock_team}; pub use team_spend::add_team_spend; pub use user_spend::add_user_spend; diff --git a/litellm-rust/crates/db/src/spend/team_lock.rs b/litellm-rust/crates/db/src/spend/team_lock.rs new file mode 100644 index 00000000000..7a6b9c7f7d0 --- /dev/null +++ b/litellm-rust/crates/db/src/spend/team_lock.rs @@ -0,0 +1,98 @@ +use sqlx::{PgPool, Postgres, Transaction}; + +use crate::Error; + +pub async fn begin(pool: &PgPool) -> Result, Error> { + let mut transaction = pool.begin().await?; + sqlx::query!("SELECT set_config('lock_timeout', '5000ms', true)") + .fetch_one(&mut *transaction) + .await?; + Ok(transaction) +} + +pub async fn lock_team( + transaction: &mut Transaction<'_, Postgres>, + team_id: &str, +) -> Result<(), Error> { + sqlx::query_file!("queries/spend/lock_team.sql", team_id) + .fetch_one(&mut **transaction) + .await?; + Ok(()) +} + +#[cfg(test)] +mod tests { + use std::error::Error as StdError; + + use super::{begin, lock_team}; + use crate::test_support::database_pool; + use rstest::rstest; + use sqlx::{PgPool, postgres::PgPoolOptions}; + + #[rstest] + #[case::transaction_scoped("team-lock-scope")] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn team_lock_is_held_until_rollback( + #[case] team_id: &str, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let database_pool = database_pool?; + let pool = PgPoolOptions::new() + .max_connections(2) + .connect_with(database_pool.connect_options().as_ref().clone()) + .await?; + let mut first = begin(&pool).await?; + let mut second = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let original_timeout: String = sqlx::query_scalar("SELECT current_setting('lock_timeout')") + .fetch_one(&mut *second) + .await?; + lock_team(&mut first, team_id).await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let (backend, timeout): (i32, String) = + sqlx::query_as("SELECT pg_backend_pid(), current_setting('lock_timeout')") + .fetch_one(&mut *first) + .await?; + assert_eq!(timeout, "5s"); + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let held: bool = sqlx::query_scalar("SELECT pg_try_advisory_xact_lock(hashtext($1))") + .bind(team_id) + .fetch_one(&mut *second) + .await?; + assert!(!held); + first.rollback().await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let released: bool = sqlx::query_scalar("SELECT pg_try_advisory_xact_lock(hashtext($1))") + .bind(team_id) + .fetch_one(&mut *second) + .await?; + assert!(released); + let mut next = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let (next_backend, next_timeout): (i32, String) = + sqlx::query_as("SELECT pg_backend_pid(), current_setting('lock_timeout')") + .fetch_one(&mut *next) + .await?; + assert_eq!(next_backend, backend); + assert_eq!(next_timeout, original_timeout); + next.rollback().await?; + second.rollback().await?; + Ok(()) + } +} From 46410c8da9589c716fcd2619ea4a0358dac1adc8 Mon Sep 17 00:00:00 2001 From: yujonglee Date: Mon, 26 Oct 2026 17:05:06 -0700 Subject: [PATCH 013/262] feat(db): add typed team-member spend upsert (#48233) Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm-rust/Cargo.lock | 1 + ...27df60ff71d8fed05b53be4458b335af88147.json | 14 ++ litellm-rust/crates/db/Cargo.toml | 1 + .../spend/upsert_team_member_spend.sql | 15 ++ litellm-rust/crates/db/src/lib.rs | 4 +- litellm-rust/crates/db/src/spend/mod.rs | 2 + .../crates/db/src/spend/team_member_spend.rs | 162 ++++++++++++++++++ 7 files changed, 197 insertions(+), 2 deletions(-) create mode 100644 litellm-rust/crates/db/.sqlx/query-b0eb48b795bdaf728c79e986d2027df60ff71d8fed05b53be4458b335af88147.json create mode 100644 litellm-rust/crates/db/queries/spend/upsert_team_member_spend.sql create mode 100644 litellm-rust/crates/db/src/spend/team_member_spend.rs diff --git a/litellm-rust/Cargo.lock b/litellm-rust/Cargo.lock index d58ba9ecb5f..d0757ebbd2c 100644 --- a/litellm-rust/Cargo.lock +++ b/litellm-rust/Cargo.lock @@ -3699,6 +3699,7 @@ dependencies = [ "macro_rules_attribute", "rstest", "serde", + "serde_json", "sqlx", "thiserror 2.0.19", "tokio", diff --git a/litellm-rust/crates/db/.sqlx/query-b0eb48b795bdaf728c79e986d2027df60ff71d8fed05b53be4458b335af88147.json b/litellm-rust/crates/db/.sqlx/query-b0eb48b795bdaf728c79e986d2027df60ff71d8fed05b53be4458b335af88147.json new file mode 100644 index 00000000000..b333ec814a1 --- /dev/null +++ b/litellm-rust/crates/db/.sqlx/query-b0eb48b795bdaf728c79e986d2027df60ff71d8fed05b53be4458b335af88147.json @@ -0,0 +1,14 @@ +{ + "db_name": "PostgreSQL", + "query": "INSERT INTO \"LiteLLM_TeamMembership\" (user_id, team_id, spend, total_spend)\nSELECT member.user_id, member.team_id, member.cost, member.cost\nFROM jsonb_to_recordset($1::jsonb) AS member(user_id text, team_id text, cost float8)\nWHERE EXISTS (\n SELECT 1 FROM \"LiteLLM_TeamTable\" t\n WHERE t.team_id = member.team_id\n AND t.members_with_roles @> jsonb_build_array(jsonb_build_object('user_id', member.user_id))\n)\n OR EXISTS (\n SELECT 1 FROM \"LiteLLM_TeamMembership\" m\n WHERE m.user_id = member.user_id AND m.team_id = member.team_id\n)\nON CONFLICT (user_id, team_id) DO UPDATE\nSET spend = \"LiteLLM_TeamMembership\".spend + EXCLUDED.spend,\n total_spend = \"LiteLLM_TeamMembership\".total_spend + EXCLUDED.total_spend\n", + "describe": { + "columns": [], + "parameters": { + "Left": [ + "Jsonb" + ] + }, + "nullable": [] + }, + "hash": "b0eb48b795bdaf728c79e986d2027df60ff71d8fed05b53be4458b335af88147" +} diff --git a/litellm-rust/crates/db/Cargo.toml b/litellm-rust/crates/db/Cargo.toml index bb6d5655b60..8c1a35c7535 100644 --- a/litellm-rust/crates/db/Cargo.toml +++ b/litellm-rust/crates/db/Cargo.toml @@ -9,6 +9,7 @@ repository.workspace = true chrono.workspace = true macro_rules_attribute.workspace = true serde.workspace = true +serde_json.workspace = true sqlx.workspace = true thiserror.workspace = true diff --git a/litellm-rust/crates/db/queries/spend/upsert_team_member_spend.sql b/litellm-rust/crates/db/queries/spend/upsert_team_member_spend.sql new file mode 100644 index 00000000000..460c631cbbd --- /dev/null +++ b/litellm-rust/crates/db/queries/spend/upsert_team_member_spend.sql @@ -0,0 +1,15 @@ +INSERT INTO "LiteLLM_TeamMembership" (user_id, team_id, spend, total_spend) +SELECT member.user_id, member.team_id, member.cost, member.cost +FROM jsonb_to_recordset($1::jsonb) AS member(user_id text, team_id text, cost float8) +WHERE EXISTS ( + SELECT 1 FROM "LiteLLM_TeamTable" t + WHERE t.team_id = member.team_id + AND t.members_with_roles @> jsonb_build_array(jsonb_build_object('user_id', member.user_id)) +) + OR EXISTS ( + SELECT 1 FROM "LiteLLM_TeamMembership" m + WHERE m.user_id = member.user_id AND m.team_id = member.team_id +) +ON CONFLICT (user_id, team_id) DO UPDATE +SET spend = "LiteLLM_TeamMembership".spend + EXCLUDED.spend, + total_spend = "LiteLLM_TeamMembership".total_spend + EXCLUDED.total_spend diff --git a/litellm-rust/crates/db/src/lib.rs b/litellm-rust/crates/db/src/lib.rs index 4f009b411fd..afa962cff0e 100644 --- a/litellm-rust/crates/db/src/lib.rs +++ b/litellm-rust/crates/db/src/lib.rs @@ -19,6 +19,6 @@ pub use end_user::{EndUser, RateLimits, find_end_user}; pub use error::Error; pub use failure::DbFailure; pub use spend::{ - EntitySpend, add_end_user_spend, add_key_spend, add_team_spend, add_user_spend, begin, - lock_team, + EntitySpend, TeamMemberSpend, add_end_user_spend, add_key_spend, add_team_member_spend, + add_team_spend, add_user_spend, begin, lock_team, }; diff --git a/litellm-rust/crates/db/src/spend/mod.rs b/litellm-rust/crates/db/src/spend/mod.rs index 0459e63aaf8..1acf629af4e 100644 --- a/litellm-rust/crates/db/src/spend/mod.rs +++ b/litellm-rust/crates/db/src/spend/mod.rs @@ -1,11 +1,13 @@ mod end_user_spend; mod key_spend; mod team_lock; +mod team_member_spend; mod team_spend; mod user_spend; pub use end_user_spend::add_end_user_spend; pub use key_spend::{EntitySpend, add_key_spend}; pub use team_lock::{begin, lock_team}; +pub use team_member_spend::{TeamMemberSpend, add_team_member_spend}; pub use team_spend::add_team_spend; pub use user_spend::add_user_spend; diff --git a/litellm-rust/crates/db/src/spend/team_member_spend.rs b/litellm-rust/crates/db/src/spend/team_member_spend.rs new file mode 100644 index 00000000000..965a39ada4f --- /dev/null +++ b/litellm-rust/crates/db/src/spend/team_member_spend.rs @@ -0,0 +1,162 @@ +use sqlx::{Postgres, Transaction}; + +use super::lock_team; +use crate::Error; + +#[macro_rules_attribute::apply(crate::db_input)] +pub struct TeamMemberSpend { + pub team_id: String, + pub user_id: String, + pub cost: f64, +} + +pub async fn add_team_member_spend( + transaction: &mut Transaction<'_, Postgres>, + members: &[TeamMemberSpend], +) -> Result<(), Error> { + if members.is_empty() { + return Ok(()); + } + let mut members = members.to_vec(); + members.sort_by(|left, right| { + (&left.team_id, &left.user_id).cmp(&(&right.team_id, &right.user_id)) + }); + let mut teams: Vec<&str> = members + .iter() + .map(|member| member.team_id.as_str()) + .collect(); + teams.dedup(); + for team in teams { + lock_team(transaction, team).await?; + } + let rows = serde_json::Value::Array( + members + .iter() + .map(|member| { + serde_json::json!({ + "user_id": member.user_id, + "team_id": member.team_id, + "cost": member.cost, + }) + }) + .collect(), + ); + sqlx::query_file!("queries/spend/upsert_team_member_spend.sql", rows) + .execute(&mut **transaction) + .await?; + Ok(()) +} + +#[cfg(test)] +mod tests { + use std::error::Error as StdError; + + use super::super::begin; + use super::{TeamMemberSpend, add_team_member_spend}; + use crate::test_support::database_pool; + use rstest::rstest; + use sqlx::PgPool; + + fn members(cost: f64) -> [TeamMemberSpend; 3] { + [ + TeamMemberSpend { + team_id: "member-spend-z".into(), + user_id: "off-roster-existing".into(), + cost: 2.0 * cost, + }, + TeamMemberSpend { + team_id: "member-spend-a".into(), + user_id: "on-roster-missing".into(), + cost, + }, + TeamMemberSpend { + team_id: "member-spend-a".into(), + user_id: "off-roster-missing".into(), + cost: 50.0 * cost, + }, + ] + } + + #[rstest] + #[case::zero_then_quarter(0.25, 0.5, 3.0, 8.0)] + #[case::zero_then_eighth(0.125, 0.25, 2.5, 7.5)] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn membership_spend_preserves_roster_guard_and_fractional_costs( + #[case] cost: f64, + #[case] expected_created: f64, + #[case] expected_spend: f64, + #[case] expected_total: f64, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = begin(&pool).await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + let _teams = sqlx::query( + r#"INSERT INTO "LiteLLM_TeamTable" (team_id, members_with_roles) + VALUES ('member-spend-a', '[{"user_id":"on-roster-missing","role":"user"}]'), + ('member-spend-z', '[]')"#, + ) + .execute(&mut *tx) + .await?; + #[expect( + clippy::disallowed_methods, + reason = "Fixture writes are outside the compile-checked query set" + )] + let _members = sqlx::query( + r#"INSERT INTO "LiteLLM_TeamMembership" (team_id, user_id, spend, total_spend) + VALUES ('member-spend-z', 'off-roster-existing', 2, 7), + ('member-spend-a', 'untouched', 100, 200)"#, + ) + .execute(&mut *tx) + .await?; + add_team_member_spend(&mut tx, &[]).await?; + add_team_member_spend(&mut tx, &members(0.0)).await?; + add_team_member_spend(&mut tx, &members(cost)).await?; + add_team_member_spend(&mut tx, &members(cost)).await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let rows: Vec<(String, String, f64, f64)> = sqlx::query_as( + r#"SELECT team_id, user_id, spend, total_spend FROM "LiteLLM_TeamMembership" + WHERE team_id IN ('member-spend-a', 'member-spend-z') ORDER BY team_id, user_id"#, + ) + .fetch_all(&mut *tx) + .await?; + assert_eq!( + rows, + vec![ + ( + "member-spend-a".into(), + "on-roster-missing".into(), + expected_created, + expected_created + ), + ("member-spend-a".into(), "untouched".into(), 100.0, 200.0), + ( + "member-spend-z".into(), + "off-roster-existing".into(), + expected_spend, + expected_total + ), + ] + ); + tx.rollback().await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let remaining: i64 = sqlx::query_scalar( + r#"SELECT COUNT(*) FROM "LiteLLM_TeamMembership" + WHERE team_id IN ('member-spend-a', 'member-spend-z')"#, + ) + .fetch_one(&pool) + .await?; + assert_eq!(remaining, 0); + Ok(()) + } +} From b446d589090e73f118462f4d1d4d57823cd03bcf Mon Sep 17 00:00:00 2001 From: yujonglee Date: Mon, 26 Oct 2026 17:05:06 -0700 Subject: [PATCH 014/262] feat(db): add typed spend-log insert query (#48234) Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...acf6d06eb22facdf478f88107c9dccdac326b.json | 40 ++ .../db/queries/spend/insert_spend_logs.sql | 26 + litellm-rust/crates/db/src/lib.rs | 4 +- litellm-rust/crates/db/src/spend/mod.rs | 2 + .../crates/db/src/spend/spend_logs.rs | 517 ++++++++++++++++++ 5 files changed, 587 insertions(+), 2 deletions(-) create mode 100644 litellm-rust/crates/db/.sqlx/query-32f3c07ced96324b535bbc703c1acf6d06eb22facdf478f88107c9dccdac326b.json create mode 100644 litellm-rust/crates/db/queries/spend/insert_spend_logs.sql create mode 100644 litellm-rust/crates/db/src/spend/spend_logs.rs diff --git a/litellm-rust/crates/db/.sqlx/query-32f3c07ced96324b535bbc703c1acf6d06eb22facdf478f88107c9dccdac326b.json b/litellm-rust/crates/db/.sqlx/query-32f3c07ced96324b535bbc703c1acf6d06eb22facdf478f88107c9dccdac326b.json new file mode 100644 index 00000000000..c4eb1737d85 --- /dev/null +++ b/litellm-rust/crates/db/.sqlx/query-32f3c07ced96324b535bbc703c1acf6d06eb22facdf478f88107c9dccdac326b.json @@ -0,0 +1,40 @@ +{ + "db_name": "PostgreSQL", + "query": "INSERT INTO \"LiteLLM_SpendLogs\" (\n request_id, call_type, api_key, spend, total_tokens, prompt_tokens,\n completion_tokens, \"startTime\", \"endTime\", \"completionStartTime\",\n request_duration_ms, model, model_id, model_group, custom_llm_provider, api_base,\n \"user\", metadata, cache_hit, cache_key, request_tags, team_id, organization_id,\n end_user, requester_ip_address, messages, response, proxy_server_request,\n session_id, status, litellm_call_id\n)\nSELECT l.request_id, l.call_type, l.api_key, l.spend, l.total_tokens, l.prompt_tokens,\n l.completion_tokens, l.start_time::timestamp(3), l.end_time::timestamp(3),\n l.completion_start_time::timestamp(3), l.request_duration_ms, l.model,\n l.model_id, l.model_group, l.custom_llm_provider, l.api_base, l.user_id,\n l.metadata, l.cache_hit, l.cache_key, '[]'::jsonb, l.team_id,\n l.organization_id, l.end_user, l.requester_ip_address, '{}'::jsonb,\n '{}'::jsonb, '{}'::jsonb, l.session_id, l.status, l.litellm_call_id\nFROM UNNEST($1::text[], $2::text[], $3::text[], $4::float8[], $5::int4[], $6::int4[],\n $7::int4[], $8::timestamp[], $9::timestamp[], $10::timestamp[], $11::int4[], $12::text[],\n $13::text[], $14::text[], $15::text[], $16::text[], $17::text[],\n $18::jsonb[], $19::text[], $20::text[], $21::text[], $22::text[],\n $23::text[], $24::text[], $25::text[], $26::text[], $27::text[])\n AS l(request_id, call_type, api_key, spend, total_tokens, prompt_tokens,\n completion_tokens, start_time, end_time, completion_start_time,\n request_duration_ms, model, model_id, model_group, custom_llm_provider,\n api_base, user_id, metadata, cache_hit, cache_key, team_id, organization_id,\n end_user, requester_ip_address, session_id, status, litellm_call_id)\nON CONFLICT DO NOTHING\n", + "describe": { + "columns": [], + "parameters": { + "Left": [ + "TextArray", + "TextArray", + "TextArray", + "Float8Array", + "Int4Array", + "Int4Array", + "Int4Array", + "TimestampArray", + "TimestampArray", + "TimestampArray", + "Int4Array", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "JsonbArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray" + ] + }, + "nullable": [] + }, + "hash": "32f3c07ced96324b535bbc703c1acf6d06eb22facdf478f88107c9dccdac326b" +} diff --git a/litellm-rust/crates/db/queries/spend/insert_spend_logs.sql b/litellm-rust/crates/db/queries/spend/insert_spend_logs.sql new file mode 100644 index 00000000000..fcffee181a1 --- /dev/null +++ b/litellm-rust/crates/db/queries/spend/insert_spend_logs.sql @@ -0,0 +1,26 @@ +INSERT INTO "LiteLLM_SpendLogs" ( + request_id, call_type, api_key, spend, total_tokens, prompt_tokens, + completion_tokens, "startTime", "endTime", "completionStartTime", + request_duration_ms, model, model_id, model_group, custom_llm_provider, api_base, + "user", metadata, cache_hit, cache_key, request_tags, team_id, organization_id, + end_user, requester_ip_address, messages, response, proxy_server_request, + session_id, status, litellm_call_id +) +SELECT l.request_id, l.call_type, l.api_key, l.spend, l.total_tokens, l.prompt_tokens, + l.completion_tokens, l.start_time::timestamp(3), l.end_time::timestamp(3), + l.completion_start_time::timestamp(3), l.request_duration_ms, l.model, + l.model_id, l.model_group, l.custom_llm_provider, l.api_base, l.user_id, + l.metadata, l.cache_hit, l.cache_key, '[]'::jsonb, l.team_id, + l.organization_id, l.end_user, l.requester_ip_address, '{}'::jsonb, + '{}'::jsonb, '{}'::jsonb, l.session_id, l.status, l.litellm_call_id +FROM UNNEST($1::text[], $2::text[], $3::text[], $4::float8[], $5::int4[], $6::int4[], + $7::int4[], $8::timestamp[], $9::timestamp[], $10::timestamp[], $11::int4[], $12::text[], + $13::text[], $14::text[], $15::text[], $16::text[], $17::text[], + $18::jsonb[], $19::text[], $20::text[], $21::text[], $22::text[], + $23::text[], $24::text[], $25::text[], $26::text[], $27::text[]) + AS l(request_id, call_type, api_key, spend, total_tokens, prompt_tokens, + completion_tokens, start_time, end_time, completion_start_time, + request_duration_ms, model, model_id, model_group, custom_llm_provider, + api_base, user_id, metadata, cache_hit, cache_key, team_id, organization_id, + end_user, requester_ip_address, session_id, status, litellm_call_id) +ON CONFLICT DO NOTHING diff --git a/litellm-rust/crates/db/src/lib.rs b/litellm-rust/crates/db/src/lib.rs index afa962cff0e..511a4bd387a 100644 --- a/litellm-rust/crates/db/src/lib.rs +++ b/litellm-rust/crates/db/src/lib.rs @@ -19,6 +19,6 @@ pub use end_user::{EndUser, RateLimits, find_end_user}; pub use error::Error; pub use failure::DbFailure; pub use spend::{ - EntitySpend, TeamMemberSpend, add_end_user_spend, add_key_spend, add_team_member_spend, - add_team_spend, add_user_spend, begin, lock_team, + EntitySpend, SpendLog, SpendLogRow, TeamMemberSpend, add_end_user_spend, add_key_spend, + add_team_member_spend, add_team_spend, add_user_spend, begin, insert_spend_logs, lock_team, }; diff --git a/litellm-rust/crates/db/src/spend/mod.rs b/litellm-rust/crates/db/src/spend/mod.rs index 1acf629af4e..dcfcee41f83 100644 --- a/litellm-rust/crates/db/src/spend/mod.rs +++ b/litellm-rust/crates/db/src/spend/mod.rs @@ -1,5 +1,6 @@ mod end_user_spend; mod key_spend; +mod spend_logs; mod team_lock; mod team_member_spend; mod team_spend; @@ -7,6 +8,7 @@ mod user_spend; pub use end_user_spend::add_end_user_spend; pub use key_spend::{EntitySpend, add_key_spend}; +pub use spend_logs::{SpendLog, SpendLogRow, insert_spend_logs}; pub use team_lock::{begin, lock_team}; pub use team_member_spend::{TeamMemberSpend, add_team_member_spend}; pub use team_spend::add_team_spend; diff --git a/litellm-rust/crates/db/src/spend/spend_logs.rs b/litellm-rust/crates/db/src/spend/spend_logs.rs new file mode 100644 index 00000000000..57a9ff85301 --- /dev/null +++ b/litellm-rust/crates/db/src/spend/spend_logs.rs @@ -0,0 +1,517 @@ +use chrono::{DateTime, NaiveDateTime}; +use sqlx::PgExecutor; + +use crate::Error; + +#[macro_rules_attribute::apply(crate::db_input)] +#[derive(Default)] +pub struct SpendLog { + pub request_id: String, + pub call_type: String, + pub api_key: String, + pub spend: f64, + pub total_tokens: i32, + pub prompt_tokens: i32, + pub completion_tokens: i32, + pub start_time: String, + pub end_time: String, + pub completion_start_time: Option, + pub request_duration_ms: Option, + pub model: String, + pub model_id: String, + pub model_group: String, + pub custom_llm_provider: String, + pub api_base: String, + pub user: String, + pub metadata: serde_json::Value, + pub cache_hit: String, + pub cache_key: String, + pub team_id: String, + pub organization_id: String, + pub end_user: String, + pub requester_ip_address: Option, + pub session_id: Option, + pub status: String, + pub litellm_call_id: Option, +} + +#[macro_rules_attribute::apply(crate::db_row)] +pub struct SpendLogRow { + pub request_id: String, + pub call_type: String, + pub api_key: String, + pub spend: f64, + pub total_tokens: i32, + pub prompt_tokens: i32, + pub completion_tokens: i32, + #[sqlx(rename = "startTime")] + pub start_time: NaiveDateTime, + #[sqlx(rename = "endTime")] + pub end_time: NaiveDateTime, + #[sqlx(rename = "completionStartTime")] + pub completion_start_time: Option, + pub request_duration_ms: Option, + pub model: String, + pub model_id: Option, + pub model_group: Option, + pub custom_llm_provider: Option, + pub api_base: Option, + pub user: Option, + pub metadata: Option, + pub cache_hit: Option, + pub cache_key: Option, + pub request_tags: Option, + pub team_id: Option, + pub organization_id: Option, + pub end_user: Option, + pub requester_ip_address: Option, + pub messages: Option, + pub response: Option, + pub proxy_server_request: Option, + pub session_id: Option, + pub status: Option, + pub litellm_call_id: Option, +} + +fn parse_timestamp(value: &str) -> Result { + DateTime::parse_from_rfc3339(value) + .map(|timestamp| timestamp.naive_utc()) + .or_else(|_| NaiveDateTime::parse_from_str(value, "%Y-%m-%dT%H:%M:%S%.f")) + .or_else(|_| NaiveDateTime::parse_from_str(value, "%Y-%m-%d %H:%M:%S%.f")) +} + +pub async fn insert_spend_logs( + executor: impl PgExecutor<'_>, + logs: &[SpendLog], +) -> Result<(), Error> { + if logs.is_empty() { + return Ok(()); + } + let start_times = logs + .iter() + .map(|log| parse_timestamp(&log.start_time)) + .collect::, _>>()?; + let end_times = logs + .iter() + .map(|log| parse_timestamp(&log.end_time)) + .collect::, _>>()?; + let completion_start_times = logs + .iter() + .map(|log| { + log.completion_start_time + .as_deref() + .map(parse_timestamp) + .transpose() + }) + .collect::, _>>()?; + macro_rules! column { + ($field:ident) => { + logs.iter() + .map(|log| log.$field.clone()) + .collect::>() + }; + } + sqlx::query_file!( + "queries/spend/insert_spend_logs.sql", + &column!(request_id), + &column!(call_type), + &column!(api_key), + &column!(spend), + &column!(total_tokens), + &column!(prompt_tokens), + &column!(completion_tokens), + &start_times, + &end_times, + &completion_start_times as &[Option], + &column!(request_duration_ms) as &[Option], + &column!(model), + &column!(model_id), + &column!(model_group), + &column!(custom_llm_provider), + &column!(api_base), + &column!(user), + &column!(metadata), + &column!(cache_hit), + &column!(cache_key), + &column!(team_id), + &column!(organization_id), + &column!(end_user), + &column!(requester_ip_address) as &[Option], + &column!(session_id) as &[Option], + &column!(status), + &column!(litellm_call_id) as &[Option], + ) + .execute(executor) + .await?; + Ok(()) +} + +#[cfg(test)] +mod tests { + use std::error::Error as StdError; + + use super::{SpendLog, SpendLogRow, insert_spend_logs}; + use crate::test_support::database_pool; + use rstest::{fixture, rstest}; + use serde_json::json; + use sqlx::{Acquire, Connection, PgExecutor, PgPool, types::chrono::NaiveDateTime}; + + #[fixture] + fn logs() -> [SpendLog; 2] { + [ + SpendLog { + request_id: "spend-logs-a".into(), + call_type: "acompletion".into(), + api_key: "key-a".into(), + spend: 0.125, + total_tokens: 17, + prompt_tokens: 11, + completion_tokens: 6, + start_time: "2026-01-02 03:04:05.123".into(), + end_time: "2026-01-02 03:04:06.789".into(), + completion_start_time: Some("2026-01-02 03:04:05.456".into()), + request_duration_ms: Some(1666), + model: "model-a".into(), + model_id: "deployment-a".into(), + model_group: "group-a".into(), + custom_llm_provider: "provider-a".into(), + api_base: "https://a.example.test".into(), + user: "user-a".into(), + metadata: json!({"tenant": "a", "nested": {"tokens": 11}, "flag": false}), + cache_hit: "False".into(), + cache_key: "cache-a".into(), + team_id: "team-a".into(), + organization_id: "org-a".into(), + end_user: "end-user-a".into(), + requester_ip_address: Some("192.0.2.1".into()), + session_id: Some("session-a".into()), + status: "success".into(), + litellm_call_id: Some("call-a".into()), + }, + SpendLog { + request_id: "spend-logs-b".into(), + call_type: "aembedding".into(), + api_key: "key-b".into(), + spend: 2.75, + total_tokens: 43, + prompt_tokens: 29, + completion_tokens: 14, + start_time: "2026-02-03 14:15:16.234".into(), + end_time: "2026-02-03 14:15:18.567".into(), + completion_start_time: None, + request_duration_ms: None, + model: "model-b".into(), + model_id: "deployment-b".into(), + model_group: "group-b".into(), + custom_llm_provider: "provider-b".into(), + api_base: "https://b.example.test".into(), + user: "user-b".into(), + metadata: json!({"tenant": "b", "tags": ["distinct", 7], "nullable": null}), + cache_hit: "True".into(), + cache_key: "cache-b".into(), + team_id: "team-b".into(), + organization_id: "org-b".into(), + end_user: "end-user-b".into(), + requester_ip_address: None, + session_id: None, + status: "failure".into(), + litellm_call_id: None, + }, + ] + } + + async fn read_log( + executor: impl PgExecutor<'_>, + request_id: &str, + ) -> Result { + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + sqlx::query_as::<_, SpendLogRow>( + r#"SELECT * FROM "LiteLLM_SpendLogs" WHERE request_id = $1"#, + ) + .bind(request_id) + .fetch_one(executor) + .await + } + + fn expected_log(log: &SpendLog) -> Result { + Ok(SpendLogRow { + request_id: log.request_id.clone(), + call_type: log.call_type.clone(), + api_key: log.api_key.clone(), + spend: log.spend, + total_tokens: log.total_tokens, + prompt_tokens: log.prompt_tokens, + completion_tokens: log.completion_tokens, + start_time: log.start_time.replace(' ', "T").parse()?, + end_time: log.end_time.replace(' ', "T").parse()?, + completion_start_time: log + .completion_start_time + .as_ref() + .map(|value| value.replace(' ', "T").parse()) + .transpose()?, + request_duration_ms: log.request_duration_ms, + model: log.model.clone(), + model_id: Some(log.model_id.clone()), + model_group: Some(log.model_group.clone()), + custom_llm_provider: Some(log.custom_llm_provider.clone()), + api_base: Some(log.api_base.clone()), + user: Some(log.user.clone()), + metadata: Some(log.metadata.clone()), + cache_hit: Some(log.cache_hit.clone()), + cache_key: Some(log.cache_key.clone()), + request_tags: Some(json!([])), + team_id: Some(log.team_id.clone()), + organization_id: Some(log.organization_id.clone()), + end_user: Some(log.end_user.clone()), + requester_ip_address: log.requester_ip_address.clone(), + messages: Some(json!({})), + response: Some(json!({})), + proxy_server_request: Some(json!({})), + session_id: log.session_id.clone(), + status: Some(log.status.clone()), + litellm_call_id: log.litellm_call_id.clone(), + }) + } + + #[rstest] + #[case::all_columns_and_duplicate()] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn inserts_distinct_rows_without_replacing_duplicates( + logs: [SpendLog; 2], + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + insert_spend_logs(&mut *tx, &logs).await?; + let replacement = SpendLog { + request_id: logs[0].request_id.clone(), + ..logs[1].clone() + }; + insert_spend_logs(&mut *tx, &[replacement]).await?; + assert_eq!( + read_log(&mut *tx, &logs[0].request_id).await?, + expected_log(&logs[0])? + ); + assert_eq!( + read_log(&mut *tx, &logs[1].request_id).await?, + expected_log(&logs[1])? + ); + tx.rollback().await?; + Ok(()) + } + + #[rstest] + #[case::partitioned_duplicate()] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn inserts_into_partitioned_logs_without_replacing_duplicates( + logs: [SpendLog; 2], + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "The test creates a temporary partitioned table at runtime" + )] + sqlx::raw_sql( + r#"CREATE TEMP TABLE "LiteLLM_SpendLogs" ( + LIKE public."LiteLLM_SpendLogs" INCLUDING DEFAULTS INCLUDING GENERATED, + PRIMARY KEY (request_id, "startTime") + ) PARTITION BY RANGE ("startTime"); + CREATE TEMP TABLE spend_logs_default + PARTITION OF pg_temp."LiteLLM_SpendLogs" DEFAULT; + SET LOCAL search_path TO pg_temp, public;"#, + ) + .execute(&mut *tx) + .await?; + tx.clear_cached_statements().await?; + insert_spend_logs(&mut *tx, &logs).await?; + let replacement = SpendLog { + spend: 99.0, + ..logs[0].clone() + }; + insert_spend_logs(&mut *tx, &[replacement]).await?; + #[expect( + clippy::disallowed_methods, + reason = "The partitioned test fixture is created at runtime" + )] + let count: (i64,) = sqlx::query_as(r#"SELECT count(*) FROM pg_temp."LiteLLM_SpendLogs""#) + .fetch_one(&mut *tx) + .await?; + assert_eq!(count.0, 2); + assert_eq!( + read_log(&mut *tx, &logs[0].request_id).await?, + expected_log(&logs[0])? + ); + assert_eq!( + read_log(&mut *tx, &logs[1].request_id).await?, + expected_log(&logs[1])? + ); + let distinct_partition_key = SpendLog { + request_id: logs[0].request_id.clone(), + ..logs[1].clone() + }; + insert_spend_logs(&mut *tx, &[distinct_partition_key]).await?; + #[expect( + clippy::disallowed_methods, + reason = "The partitioned test fixture is created at runtime" + )] + let count: (i64,) = sqlx::query_as(r#"SELECT count(*) FROM pg_temp."LiteLLM_SpendLogs""#) + .fetch_one(&mut *tx) + .await?; + assert_eq!(count.0, 3); + tx.rollback().await?; + Ok(()) + } + + #[rstest] + #[case::positive_offset_across_midnight( + ["2026-01-02T00:04:05.1236+02:00", "2026-01-02T00:04:06.7894+02:00", "2026-01-02T00:04:05.4567+02:00"], + ["2026-01-01T22:04:05.124", "2026-01-01T22:04:06.789", "2026-01-01T22:04:05.457"] + )] + #[case::negative_offset_across_midnight( + ["2026-01-01T23:04:05-02:00", "2026-01-01T23:04:06-02:00", "2026-01-01T23:04:05.456-02:00"], + ["2026-01-02T01:04:05", "2026-01-02T01:04:06", "2026-01-02T01:04:05.456"] + )] + #[case::utc( + ["2026-01-02T03:04:05Z", "2026-01-02T03:04:06Z", "2026-01-02T03:04:05.456Z"], + ["2026-01-02T03:04:05", "2026-01-02T03:04:06", "2026-01-02T03:04:05.456"] + )] + #[case::naive_iso( + ["2026-01-02T03:04:05", "2026-01-02T03:04:06", "2026-01-02T03:04:05.456"], + ["2026-01-02T03:04:05", "2026-01-02T03:04:06", "2026-01-02T03:04:05.456"] + )] + #[case::naive_space( + ["2026-01-02 03:04:05", "2026-01-02 03:04:06", "2026-01-02 03:04:05.456"], + ["2026-01-02T03:04:05", "2026-01-02T03:04:06", "2026-01-02T03:04:05.456"] + )] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn stores_utc_timestamps( + #[case] input: [&str; 3], + #[case] expected: [&str; 3], + logs: [SpendLog; 2], + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "The test sets a transaction-local timezone to verify timestamp handling" + )] + sqlx::raw_sql("SET LOCAL TIME ZONE 'America/Los_Angeles'") + .execute(&mut *tx) + .await?; + let log = SpendLog { + start_time: input[0].into(), + end_time: input[1].into(), + completion_start_time: Some(input[2].into()), + ..logs[0].clone() + }; + insert_spend_logs(&mut *tx, std::slice::from_ref(&log)).await?; + let row = read_log(&mut *tx, &log.request_id).await?; + assert_eq!(row.start_time, expected[0].parse::()?); + assert_eq!(row.end_time, expected[1].parse::()?); + assert_eq!( + row.completion_start_time, + Some(expected[2].parse::()?) + ); + tx.rollback().await?; + Ok(()) + } + + #[rstest] + #[case::empty_batch()] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn empty_input_leaves_rows_unchanged( + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let before: (i64,) = sqlx::query_as(r#"SELECT count(*) FROM "LiteLLM_SpendLogs""#) + .fetch_one(&mut *tx) + .await?; + insert_spend_logs(&mut *tx, &[]).await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let after: (i64,) = sqlx::query_as(r#"SELECT count(*) FROM "LiteLLM_SpendLogs""#) + .fetch_one(&mut *tx) + .await?; + assert_eq!(before, after); + tx.rollback().await?; + Ok(()) + } + + #[rstest] + #[case::invalid_timestamp("not-a-timestamp", "2026-01-02T03:04:06", None)] + #[case::invalid_end("2026-01-02T03:04:05", "not-a-timestamp", None)] + #[case::invalid_completion( + "2026-01-02T03:04:05", + "2026-01-02T03:04:06", + Some("not-a-timestamp") + )] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn invalid_timestamp_allows_caller_rollback( + #[case] start_time: &str, + #[case] end_time: &str, + #[case] completion_start_time: Option<&str>, + logs: [SpendLog; 2], + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut outer = pool.begin().await?; + let mut tx = outer.begin().await?; + let valid = SpendLog { + request_id: "spend-logs-rollback-valid".into(), + ..logs[0].clone() + }; + let invalid = SpendLog { + request_id: "spend-logs-rollback-invalid".into(), + start_time: start_time.into(), + end_time: end_time.into(), + completion_start_time: completion_start_time.map(str::to_owned), + ..logs[1].clone() + }; + insert_spend_logs(&mut *tx, std::slice::from_ref(&valid)).await?; + let result = insert_spend_logs(&mut *tx, &[logs[0].clone(), invalid]).await; + assert!(matches!(result, Err(crate::Error::InvalidTimestamp(_)))); + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let partial_batch: (i64,) = sqlx::query_as( + r#"SELECT count(*) FROM "LiteLLM_SpendLogs" WHERE request_id = ANY($1)"#, + ) + .bind([logs[0].request_id.as_str(), "spend-logs-rollback-invalid"].as_slice()) + .fetch_one(&mut *tx) + .await?; + assert_eq!(partial_batch.0, 0); + tx.rollback().await?; + #[expect( + clippy::disallowed_methods, + reason = "Test assertions are outside the compile-checked query set" + )] + let remaining: (i64,) = sqlx::query_as( + r#"SELECT count(*) FROM "LiteLLM_SpendLogs" WHERE request_id = ANY($1)"#, + ) + .bind([valid.request_id.as_str(), "spend-logs-rollback-invalid"].as_slice()) + .fetch_one(&mut *outer) + .await?; + assert_eq!(remaining.0, 0); + outer.rollback().await?; + Ok(()) + } +} From 1b874ceb85313d5ff9a27e18db75e5cb90fcad81 Mon Sep 17 00:00:00 2001 From: yujonglee Date: Mon, 26 Oct 2026 17:05:07 -0700 Subject: [PATCH 015/262] feat(db): add typed daily user spend upsert (#48235) Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...8c2ebd7fc9fcbf19c1c25aa131a1053d96cfe.json | 31 ++ .../queries/spend/upsert_daily_user_spend.sql | 40 ++ litellm-rust/crates/db/src/lib.rs | 5 +- .../crates/db/src/spend/daily_user_spend.rs | 500 ++++++++++++++++++ litellm-rust/crates/db/src/spend/mod.rs | 2 + 5 files changed, 576 insertions(+), 2 deletions(-) create mode 100644 litellm-rust/crates/db/.sqlx/query-bec3b53762af021a118d63b841b8c2ebd7fc9fcbf19c1c25aa131a1053d96cfe.json create mode 100644 litellm-rust/crates/db/queries/spend/upsert_daily_user_spend.sql create mode 100644 litellm-rust/crates/db/src/spend/daily_user_spend.rs diff --git a/litellm-rust/crates/db/.sqlx/query-bec3b53762af021a118d63b841b8c2ebd7fc9fcbf19c1c25aa131a1053d96cfe.json b/litellm-rust/crates/db/.sqlx/query-bec3b53762af021a118d63b841b8c2ebd7fc9fcbf19c1c25aa131a1053d96cfe.json new file mode 100644 index 00000000000..6c56868e48e --- /dev/null +++ b/litellm-rust/crates/db/.sqlx/query-bec3b53762af021a118d63b841b8c2ebd7fc9fcbf19c1c25aa131a1053d96cfe.json @@ -0,0 +1,31 @@ +{ + "db_name": "PostgreSQL", + "query": "INSERT INTO \"LiteLLM_DailyUserSpend\" (\n id, user_id, date, api_key, model, custom_llm_provider,\n mcp_namespaced_tool_name, endpoint, model_group, prompt_tokens,\n completion_tokens, api_requests, successful_requests, failed_requests,\n cache_read_input_tokens, cache_creation_input_tokens, total_response_time_ms,\n timed_requests, spend, updated_at\n)\nSELECT gen_random_uuid()::text, r.entity_id, r.date, r.api_key, r.model,\n r.custom_llm_provider, r.mcp_namespaced_tool_name, r.endpoint, r.model_group, r.prompt_tokens,\n r.completion_tokens, r.api_requests, r.successful_requests,\n r.failed_requests, r.cache_read, r.cache_creation, r.response_time,\n r.timed_requests, r.spend, (NOW() AT TIME ZONE 'UTC')\nFROM UNNEST(\n $1::text[], $2::text[], $3::text[], $4::text[], $5::text[],\n $6::text[], $7::text[], $8::int8[], $9::int8[], $10::int8[],\n $11::int8[], $12::int8[], $13::int8[], $14::int8[], $15::int8[],\n $16::int8[], $17::float8[], $18::text[]\n) AS r(\n entity_id, date, api_key, model, custom_llm_provider, endpoint,\n model_group, prompt_tokens, completion_tokens, api_requests,\n successful_requests, failed_requests, cache_read, cache_creation,\n response_time, timed_requests, spend, mcp_namespaced_tool_name\n)\nORDER BY r.date, r.entity_id, r.api_key, r.model, r.custom_llm_provider,\n r.mcp_namespaced_tool_name, r.endpoint\nON CONFLICT (\n user_id, date, api_key, model, custom_llm_provider,\n mcp_namespaced_tool_name, endpoint\n) DO UPDATE SET\n prompt_tokens = \"LiteLLM_DailyUserSpend\".prompt_tokens + EXCLUDED.prompt_tokens,\n completion_tokens = \"LiteLLM_DailyUserSpend\".completion_tokens + EXCLUDED.completion_tokens,\n api_requests = \"LiteLLM_DailyUserSpend\".api_requests + EXCLUDED.api_requests,\n successful_requests = \"LiteLLM_DailyUserSpend\".successful_requests + EXCLUDED.successful_requests,\n failed_requests = \"LiteLLM_DailyUserSpend\".failed_requests + EXCLUDED.failed_requests,\n cache_read_input_tokens = \"LiteLLM_DailyUserSpend\".cache_read_input_tokens + EXCLUDED.cache_read_input_tokens,\n cache_creation_input_tokens = \"LiteLLM_DailyUserSpend\".cache_creation_input_tokens + EXCLUDED.cache_creation_input_tokens,\n total_response_time_ms = \"LiteLLM_DailyUserSpend\".total_response_time_ms + EXCLUDED.total_response_time_ms,\n timed_requests = \"LiteLLM_DailyUserSpend\".timed_requests + EXCLUDED.timed_requests,\n spend = \"LiteLLM_DailyUserSpend\".spend + EXCLUDED.spend,\n updated_at = (NOW() AT TIME ZONE 'UTC')\n", + "describe": { + "columns": [], + "parameters": { + "Left": [ + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Float8Array", + "TextArray" + ] + }, + "nullable": [] + }, + "hash": "bec3b53762af021a118d63b841b8c2ebd7fc9fcbf19c1c25aa131a1053d96cfe" +} diff --git a/litellm-rust/crates/db/queries/spend/upsert_daily_user_spend.sql b/litellm-rust/crates/db/queries/spend/upsert_daily_user_spend.sql new file mode 100644 index 00000000000..4a5db90dee2 --- /dev/null +++ b/litellm-rust/crates/db/queries/spend/upsert_daily_user_spend.sql @@ -0,0 +1,40 @@ +INSERT INTO "LiteLLM_DailyUserSpend" ( + id, user_id, date, api_key, model, custom_llm_provider, + mcp_namespaced_tool_name, endpoint, model_group, prompt_tokens, + completion_tokens, api_requests, successful_requests, failed_requests, + cache_read_input_tokens, cache_creation_input_tokens, total_response_time_ms, + timed_requests, spend, updated_at +) +SELECT gen_random_uuid()::text, r.entity_id, r.date, r.api_key, r.model, + r.custom_llm_provider, r.mcp_namespaced_tool_name, r.endpoint, r.model_group, r.prompt_tokens, + r.completion_tokens, r.api_requests, r.successful_requests, + r.failed_requests, r.cache_read, r.cache_creation, r.response_time, + r.timed_requests, r.spend, (NOW() AT TIME ZONE 'UTC') +FROM UNNEST( + $1::text[], $2::text[], $3::text[], $4::text[], $5::text[], + $6::text[], $7::text[], $8::int8[], $9::int8[], $10::int8[], + $11::int8[], $12::int8[], $13::int8[], $14::int8[], $15::int8[], + $16::int8[], $17::float8[], $18::text[] +) AS r( + entity_id, date, api_key, model, custom_llm_provider, endpoint, + model_group, prompt_tokens, completion_tokens, api_requests, + successful_requests, failed_requests, cache_read, cache_creation, + response_time, timed_requests, spend, mcp_namespaced_tool_name +) +ORDER BY r.date, r.entity_id, r.api_key, r.model, r.custom_llm_provider, + r.mcp_namespaced_tool_name, r.endpoint +ON CONFLICT ( + user_id, date, api_key, model, custom_llm_provider, + mcp_namespaced_tool_name, endpoint +) DO UPDATE SET + prompt_tokens = "LiteLLM_DailyUserSpend".prompt_tokens + EXCLUDED.prompt_tokens, + completion_tokens = "LiteLLM_DailyUserSpend".completion_tokens + EXCLUDED.completion_tokens, + api_requests = "LiteLLM_DailyUserSpend".api_requests + EXCLUDED.api_requests, + successful_requests = "LiteLLM_DailyUserSpend".successful_requests + EXCLUDED.successful_requests, + failed_requests = "LiteLLM_DailyUserSpend".failed_requests + EXCLUDED.failed_requests, + cache_read_input_tokens = "LiteLLM_DailyUserSpend".cache_read_input_tokens + EXCLUDED.cache_read_input_tokens, + cache_creation_input_tokens = "LiteLLM_DailyUserSpend".cache_creation_input_tokens + EXCLUDED.cache_creation_input_tokens, + total_response_time_ms = "LiteLLM_DailyUserSpend".total_response_time_ms + EXCLUDED.total_response_time_ms, + timed_requests = "LiteLLM_DailyUserSpend".timed_requests + EXCLUDED.timed_requests, + spend = "LiteLLM_DailyUserSpend".spend + EXCLUDED.spend, + updated_at = (NOW() AT TIME ZONE 'UTC') diff --git a/litellm-rust/crates/db/src/lib.rs b/litellm-rust/crates/db/src/lib.rs index 511a4bd387a..3bcd050440a 100644 --- a/litellm-rust/crates/db/src/lib.rs +++ b/litellm-rust/crates/db/src/lib.rs @@ -19,6 +19,7 @@ pub use end_user::{EndUser, RateLimits, find_end_user}; pub use error::Error; pub use failure::DbFailure; pub use spend::{ - EntitySpend, SpendLog, SpendLogRow, TeamMemberSpend, add_end_user_spend, add_key_spend, - add_team_member_spend, add_team_spend, add_user_spend, begin, insert_spend_logs, lock_team, + DailySpend, EntitySpend, SpendLog, SpendLogRow, TeamMemberSpend, add_end_user_spend, + add_key_spend, add_team_member_spend, add_team_spend, add_user_spend, begin, insert_spend_logs, + lock_team, upsert_daily_user_spend, }; diff --git a/litellm-rust/crates/db/src/spend/daily_user_spend.rs b/litellm-rust/crates/db/src/spend/daily_user_spend.rs new file mode 100644 index 00000000000..3530eb245c5 --- /dev/null +++ b/litellm-rust/crates/db/src/spend/daily_user_spend.rs @@ -0,0 +1,500 @@ +use sqlx::PgExecutor; + +use crate::Error; + +#[macro_rules_attribute::apply(crate::db_input)] +#[derive(Default)] +pub struct DailySpend { + pub entity_id: String, + pub date: String, + pub api_key: String, + pub model: String, + pub custom_llm_provider: String, + pub mcp_namespaced_tool_name: String, + pub endpoint: String, + pub model_group: Option, + pub prompt_tokens: i64, + pub completion_tokens: i64, + pub api_requests: i64, + pub successful_requests: i64, + pub failed_requests: i64, + pub cache_read_input_tokens: i64, + pub cache_creation_input_tokens: i64, + pub total_response_time_ms: i64, + pub timed_requests: i64, + pub spend: f64, +} + +pub async fn upsert_daily_user_spend( + executor: impl PgExecutor<'_>, + rows: &[DailySpend], +) -> Result<(), Error> { + if rows.is_empty() { + return Ok(()); + } + macro_rules! column { + ($field:ident) => { + rows.iter() + .map(|row| row.$field.clone()) + .collect::>() + }; + } + sqlx::query_file!( + "queries/spend/upsert_daily_user_spend.sql", + &column!(entity_id), + &column!(date), + &column!(api_key), + &column!(model), + &column!(custom_llm_provider), + &column!(endpoint), + &column!(model_group) as &[Option], + &column!(prompt_tokens), + &column!(completion_tokens), + &column!(api_requests), + &column!(successful_requests), + &column!(failed_requests), + &column!(cache_read_input_tokens), + &column!(cache_creation_input_tokens), + &column!(total_response_time_ms), + &column!(timed_requests), + &column!(spend), + &column!(mcp_namespaced_tool_name), + ) + .execute(executor) + .await?; + Ok(()) +} + +#[cfg(test)] +mod tests { + use std::error::Error as StdError; + + use super::{DailySpend, upsert_daily_user_spend}; + use crate::{DailyUserRow, test_support::database_pool}; + use rstest::rstest; + use sqlx::{PgPool, types::chrono::NaiveDateTime}; + + #[rstest] + #[case::distinct_tools("server/search", "server/write")] + #[case::default_empty_tool("", "server/search")] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn daily_user_spend_separates_tools_and_accumulates( + #[case] first_tool: &str, + #[case] second_tool: &str, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + let first = DailySpend { + entity_id: format!("daily-user-tools-{first_tool}"), + date: "2026-01-15".to_owned(), + api_key: "tool-key".to_owned(), + model: "tool-model".to_owned(), + custom_llm_provider: "tool-provider".to_owned(), + endpoint: "/mcp".to_owned(), + model_group: Some("tool-group".to_owned()), + mcp_namespaced_tool_name: first_tool.to_owned(), + prompt_tokens: 3, + api_requests: 1, + spend: 0.25, + ..Default::default() + }; + let second = DailySpend { + mcp_namespaced_tool_name: second_tool.to_owned(), + prompt_tokens: 7, + api_requests: 2, + spend: 0.5, + ..first.clone() + }; + upsert_daily_user_spend(&mut *tx, &[second.clone(), first.clone()]).await?; + upsert_daily_user_spend(&mut *tx, &[first.clone(), second]).await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test reads stored rows to verify tool attribution" + )] + let rows: Vec = sqlx::query_as( + r#"SELECT * FROM "LiteLLM_DailyUserSpend" + WHERE user_id = $1 + ORDER BY mcp_namespaced_tool_name, endpoint"#, + ) + .bind(&first.entity_id) + .fetch_all(&mut *tx) + .await?; + + assert_eq!(rows.len(), 2); + assert_eq!( + rows[0].mcp_namespaced_tool_name.as_deref(), + Some(first_tool) + ); + assert_eq!( + rows[1].mcp_namespaced_tool_name.as_deref(), + Some(second_tool) + ); + assert_eq!( + (rows[0].prompt_tokens, rows[0].api_requests, rows[0].spend), + (6, 2, 0.5) + ); + assert_eq!( + (rows[1].prompt_tokens, rows[1].api_requests, rows[1].spend), + (14, 4, 1.0) + ); + Ok(()) + } + + #[rstest] + #[case::full_keys( + "daily-user-base", + "daily-key-base", + "daily-model", + "daily-provider", + "/chat/completions", + Some("first-group") + )] + #[case::initial_model_group_none( + "daily-user-base", + "daily-key-base", + "daily-model", + "daily-provider", + "/chat/completions", + None + )] + #[case::empty_optional_keys("", "", "", "", "", Some(""))] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn daily_user_spend_upsert_preserves_keys_and_accumulates( + #[case] user_id: &'static str, + #[case] api_key: &'static str, + #[case] model: &'static str, + #[case] custom_llm_provider: &'static str, + #[case] endpoint: &'static str, + #[case] first_model_group: Option<&'static str>, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test exercises UTC timestamp behavior under a non-UTC session" + )] + sqlx::query("SET LOCAL TIME ZONE 'America/Los_Angeles'") + .execute(&mut *tx) + .await?; + + let first_batch = [ + DailySpend { + entity_id: user_id.to_owned(), + date: "2026-01-15".to_owned(), + api_key: api_key.to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: endpoint.to_owned(), + model_group: first_model_group.map(str::to_owned), + prompt_tokens: 1, + completion_tokens: 2, + api_requests: 3, + successful_requests: 4, + failed_requests: 5, + cache_read_input_tokens: 6, + cache_creation_input_tokens: 7, + total_response_time_ms: 8, + timed_requests: 9, + spend: 0.125, + }, + DailySpend { + entity_id: user_id.to_owned(), + date: "2026-01-15".to_owned(), + api_key: api_key.to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: "endpoint-sentinel".to_owned(), + model_group: Some("sentinel-endpoint-group".to_owned()), + prompt_tokens: 101, + completion_tokens: 102, + api_requests: 103, + successful_requests: 104, + failed_requests: 105, + cache_read_input_tokens: 106, + cache_creation_input_tokens: 107, + total_response_time_ms: 108, + timed_requests: 109, + spend: 1.25, + }, + DailySpend { + entity_id: user_id.to_owned(), + date: "2026-01-15".to_owned(), + api_key: "api-key-sentinel".to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: endpoint.to_owned(), + model_group: Some("sentinel-key-group".to_owned()), + prompt_tokens: 201, + completion_tokens: 202, + api_requests: 203, + successful_requests: 204, + failed_requests: 205, + cache_read_input_tokens: 206, + cache_creation_input_tokens: 207, + total_response_time_ms: 208, + timed_requests: 209, + spend: 2.5, + }, + DailySpend { + entity_id: "entity-sentinel".to_owned(), + date: "2026-01-15".to_owned(), + api_key: api_key.to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: endpoint.to_owned(), + model_group: Some("sentinel-entity-group".to_owned()), + prompt_tokens: 301, + completion_tokens: 302, + api_requests: 303, + successful_requests: 304, + failed_requests: 305, + cache_read_input_tokens: 306, + cache_creation_input_tokens: 307, + total_response_time_ms: 308, + timed_requests: 309, + spend: 3.75, + }, + ]; + upsert_daily_user_spend(&mut *tx, &first_batch).await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test captures the inserted row identity before conflict handling" + )] + let (initial_id, initial_created_at): (String, NaiveDateTime) = sqlx::query_as( + r#"SELECT id, created_at + FROM "LiteLLM_DailyUserSpend" + WHERE user_id = $1 AND date = $2 AND api_key = $3 AND model = $4 + AND custom_llm_provider = $5 AND endpoint = $6"#, + ) + .bind(user_id) + .bind("2026-01-15") + .bind(api_key) + .bind(model) + .bind(custom_llm_provider) + .bind(endpoint) + .fetch_one(&mut *tx) + .await?; + assert!(!initial_id.is_empty()); + + #[expect( + clippy::disallowed_methods, + reason = "The integration test seeds updated_at before exercising the conflict update" + )] + let seeded_updated_at: NaiveDateTime = sqlx::query_scalar( + r#"UPDATE "LiteLLM_DailyUserSpend" + SET updated_at = TIMESTAMP '2000-01-01' + WHERE id = $1 + RETURNING updated_at"#, + ) + .bind(&initial_id) + .fetch_one(&mut *tx) + .await?; + + let increment = [DailySpend { + entity_id: user_id.to_owned(), + date: "2026-01-15".to_owned(), + api_key: api_key.to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: endpoint.to_owned(), + model_group: Some("second-group".to_owned()), + prompt_tokens: 10, + completion_tokens: 20, + api_requests: 30, + successful_requests: 40, + failed_requests: 50, + cache_read_input_tokens: 60, + cache_creation_input_tokens: 70, + total_response_time_ms: 80, + timed_requests: 90, + spend: 0.625, + }]; + upsert_daily_user_spend(&mut *tx, &increment).await?; + upsert_daily_user_spend(&mut *tx, &[]).await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test captures the transaction timestamp for assertions" + )] + let expected_updated_at: NaiveDateTime = + sqlx::query_scalar("SELECT (NOW() AT TIME ZONE 'UTC')::timestamp(3)") + .fetch_one(&mut *tx) + .await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test reads all rows to verify attribution and accumulation" + )] + let rows: Vec = sqlx::query_as( + r#"SELECT id, user_id, api_key, model, custom_llm_provider, endpoint, + model_group, mcp_namespaced_tool_name, prompt_tokens, + completion_tokens, api_requests, successful_requests, + failed_requests, cache_read_input_tokens, + cache_creation_input_tokens, total_response_time_ms, + timed_requests, spend, date, created_at, updated_at + FROM "LiteLLM_DailyUserSpend" + WHERE date = $1 AND model = $2 AND custom_llm_provider = $3 + AND mcp_namespaced_tool_name = '' AND user_id = ANY($4) + ORDER BY CASE + WHEN user_id = $5 AND api_key = $6 AND endpoint = $7 THEN 0 + WHEN user_id = $5 AND api_key = $6 AND endpoint = $9 THEN 1 + WHEN user_id = $5 AND api_key = $8 AND endpoint = $7 THEN 2 + WHEN user_id = $10 AND api_key = $6 AND endpoint = $7 THEN 3 + ELSE 4 + END"#, + ) + .bind("2026-01-15") + .bind(model) + .bind(custom_llm_provider) + .bind(vec![user_id, "entity-sentinel"]) + .bind(user_id) + .bind(api_key) + .bind(endpoint) + .bind("api-key-sentinel") + .bind("endpoint-sentinel") + .bind("entity-sentinel") + .fetch_all(&mut *tx) + .await?; + + assert_eq!(rows.len(), 4); + assert_eq!(rows[0].id, initial_id); + assert_eq!(rows[0].user_id.as_deref(), Some(user_id)); + assert_eq!(rows[0].api_key, api_key); + assert_eq!(rows[0].model.as_deref(), Some(model)); + assert_eq!( + rows[0].custom_llm_provider.as_deref(), + Some(custom_llm_provider) + ); + assert_eq!(rows[0].endpoint.as_deref(), Some(endpoint)); + assert_eq!(rows[0].model_group.as_deref(), first_model_group); + assert_eq!(rows[0].mcp_namespaced_tool_name.as_deref(), Some("")); + assert_eq!( + ( + rows[0].prompt_tokens, + rows[0].completion_tokens, + rows[0].api_requests, + rows[0].successful_requests, + rows[0].failed_requests, + rows[0].cache_read_input_tokens, + rows[0].cache_creation_input_tokens, + rows[0].total_response_time_ms, + rows[0].timed_requests, + rows[0].spend + ), + (11, 22, 33, 44, 55, 66, 77, 88, 99, 0.75) + ); + assert_eq!(rows[0].date, "2026-01-15"); + assert_eq!(rows[0].created_at, initial_created_at); + assert!(rows[0].updated_at > seeded_updated_at); + assert_eq!(rows[0].updated_at, expected_updated_at); + + assert!(!rows[1].id.is_empty()); + assert_eq!(rows[1].user_id.as_deref(), Some(user_id)); + assert_eq!(rows[1].api_key, api_key); + assert_eq!(rows[1].model.as_deref(), Some(model)); + assert_eq!( + rows[1].custom_llm_provider.as_deref(), + Some(custom_llm_provider) + ); + assert_eq!(rows[1].endpoint.as_deref(), Some("endpoint-sentinel")); + assert_eq!( + rows[1].model_group.as_deref(), + Some("sentinel-endpoint-group") + ); + assert_eq!(rows[1].mcp_namespaced_tool_name.as_deref(), Some("")); + assert_eq!( + ( + rows[1].prompt_tokens, + rows[1].completion_tokens, + rows[1].api_requests, + rows[1].successful_requests, + rows[1].failed_requests, + rows[1].cache_read_input_tokens, + rows[1].cache_creation_input_tokens, + rows[1].total_response_time_ms, + rows[1].timed_requests, + rows[1].spend + ), + (101, 102, 103, 104, 105, 106, 107, 108, 109, 1.25) + ); + assert_eq!(rows[1].date, "2026-01-15"); + assert!(rows[1].updated_at > seeded_updated_at); + assert_eq!(rows[1].updated_at, expected_updated_at); + + assert!(!rows[2].id.is_empty()); + assert_eq!(rows[2].user_id.as_deref(), Some(user_id)); + assert_eq!(rows[2].api_key, "api-key-sentinel"); + assert_eq!(rows[2].model.as_deref(), Some(model)); + assert_eq!( + rows[2].custom_llm_provider.as_deref(), + Some(custom_llm_provider) + ); + assert_eq!(rows[2].endpoint.as_deref(), Some(endpoint)); + assert_eq!(rows[2].model_group.as_deref(), Some("sentinel-key-group")); + assert_eq!(rows[2].mcp_namespaced_tool_name.as_deref(), Some("")); + assert_eq!( + ( + rows[2].prompt_tokens, + rows[2].completion_tokens, + rows[2].api_requests, + rows[2].successful_requests, + rows[2].failed_requests, + rows[2].cache_read_input_tokens, + rows[2].cache_creation_input_tokens, + rows[2].total_response_time_ms, + rows[2].timed_requests, + rows[2].spend + ), + (201, 202, 203, 204, 205, 206, 207, 208, 209, 2.5) + ); + assert_eq!(rows[2].date, "2026-01-15"); + assert!(rows[2].updated_at > seeded_updated_at); + assert_eq!(rows[2].updated_at, expected_updated_at); + + assert!(!rows[3].id.is_empty()); + assert_eq!(rows[3].user_id.as_deref(), Some("entity-sentinel")); + assert_eq!(rows[3].api_key, api_key); + assert_eq!(rows[3].model.as_deref(), Some(model)); + assert_eq!( + rows[3].custom_llm_provider.as_deref(), + Some(custom_llm_provider) + ); + assert_eq!(rows[3].endpoint.as_deref(), Some(endpoint)); + assert_eq!( + rows[3].model_group.as_deref(), + Some("sentinel-entity-group") + ); + assert_eq!(rows[3].mcp_namespaced_tool_name.as_deref(), Some("")); + assert_eq!( + ( + rows[3].prompt_tokens, + rows[3].completion_tokens, + rows[3].api_requests, + rows[3].successful_requests, + rows[3].failed_requests, + rows[3].cache_read_input_tokens, + rows[3].cache_creation_input_tokens, + rows[3].total_response_time_ms, + rows[3].timed_requests, + rows[3].spend + ), + (301, 302, 303, 304, 305, 306, 307, 308, 309, 3.75) + ); + assert_eq!(rows[3].date, "2026-01-15"); + assert!(rows[3].updated_at > seeded_updated_at); + assert_eq!(rows[3].updated_at, expected_updated_at); + Ok(()) + } +} diff --git a/litellm-rust/crates/db/src/spend/mod.rs b/litellm-rust/crates/db/src/spend/mod.rs index dcfcee41f83..f50440e06de 100644 --- a/litellm-rust/crates/db/src/spend/mod.rs +++ b/litellm-rust/crates/db/src/spend/mod.rs @@ -1,3 +1,4 @@ +mod daily_user_spend; mod end_user_spend; mod key_spend; mod spend_logs; @@ -6,6 +7,7 @@ mod team_member_spend; mod team_spend; mod user_spend; +pub use daily_user_spend::{DailySpend, upsert_daily_user_spend}; pub use end_user_spend::add_end_user_spend; pub use key_spend::{EntitySpend, add_key_spend}; pub use spend_logs::{SpendLog, SpendLogRow, insert_spend_logs}; From a2545134f370696ae1dd2ba7102d0ac4da552968 Mon Sep 17 00:00:00 2001 From: yujonglee Date: Mon, 26 Oct 2026 17:05:07 -0700 Subject: [PATCH 016/262] feat(db): add typed daily team spend upsert (#48236) Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...74dca981ff954452b35ffbace3e022035b416.json | 31 ++ .../queries/spend/upsert_daily_team_spend.sql | 40 ++ litellm-rust/crates/db/src/lib.rs | 2 +- .../crates/db/src/spend/daily_team_spend.rs | 485 ++++++++++++++++++ litellm-rust/crates/db/src/spend/mod.rs | 2 + 5 files changed, 559 insertions(+), 1 deletion(-) create mode 100644 litellm-rust/crates/db/.sqlx/query-9c51401a8907f818e96da28050b74dca981ff954452b35ffbace3e022035b416.json create mode 100644 litellm-rust/crates/db/queries/spend/upsert_daily_team_spend.sql create mode 100644 litellm-rust/crates/db/src/spend/daily_team_spend.rs diff --git a/litellm-rust/crates/db/.sqlx/query-9c51401a8907f818e96da28050b74dca981ff954452b35ffbace3e022035b416.json b/litellm-rust/crates/db/.sqlx/query-9c51401a8907f818e96da28050b74dca981ff954452b35ffbace3e022035b416.json new file mode 100644 index 00000000000..9886a9505d8 --- /dev/null +++ b/litellm-rust/crates/db/.sqlx/query-9c51401a8907f818e96da28050b74dca981ff954452b35ffbace3e022035b416.json @@ -0,0 +1,31 @@ +{ + "db_name": "PostgreSQL", + "query": "INSERT INTO \"LiteLLM_DailyTeamSpend\" (\n id, team_id, date, api_key, model, custom_llm_provider,\n mcp_namespaced_tool_name, endpoint, model_group, prompt_tokens,\n completion_tokens, api_requests, successful_requests, failed_requests,\n cache_read_input_tokens, cache_creation_input_tokens, total_response_time_ms,\n timed_requests, spend, updated_at\n)\nSELECT gen_random_uuid()::text, r.entity_id, r.date, r.api_key, r.model,\n r.custom_llm_provider, r.mcp_namespaced_tool_name, r.endpoint, r.model_group, r.prompt_tokens,\n r.completion_tokens, r.api_requests, r.successful_requests,\n r.failed_requests, r.cache_read, r.cache_creation, r.response_time,\n r.timed_requests, r.spend, (NOW() AT TIME ZONE 'UTC')\nFROM UNNEST(\n $1::text[], $2::text[], $3::text[], $4::text[], $5::text[],\n $6::text[], $7::text[], $8::int8[], $9::int8[], $10::int8[],\n $11::int8[], $12::int8[], $13::int8[], $14::int8[], $15::int8[],\n $16::int8[], $17::float8[], $18::text[]\n) AS r(\n entity_id, date, api_key, model, custom_llm_provider, endpoint,\n model_group, prompt_tokens, completion_tokens, api_requests,\n successful_requests, failed_requests, cache_read, cache_creation,\n response_time, timed_requests, spend, mcp_namespaced_tool_name\n)\nORDER BY r.date, r.entity_id, r.api_key, r.model, r.custom_llm_provider,\n r.mcp_namespaced_tool_name, r.endpoint\nON CONFLICT (\n team_id, date, api_key, model, custom_llm_provider,\n mcp_namespaced_tool_name, endpoint\n) DO UPDATE SET\n prompt_tokens = \"LiteLLM_DailyTeamSpend\".prompt_tokens + EXCLUDED.prompt_tokens,\n completion_tokens = \"LiteLLM_DailyTeamSpend\".completion_tokens + EXCLUDED.completion_tokens,\n api_requests = \"LiteLLM_DailyTeamSpend\".api_requests + EXCLUDED.api_requests,\n successful_requests = \"LiteLLM_DailyTeamSpend\".successful_requests + EXCLUDED.successful_requests,\n failed_requests = \"LiteLLM_DailyTeamSpend\".failed_requests + EXCLUDED.failed_requests,\n cache_read_input_tokens = \"LiteLLM_DailyTeamSpend\".cache_read_input_tokens + EXCLUDED.cache_read_input_tokens,\n cache_creation_input_tokens = \"LiteLLM_DailyTeamSpend\".cache_creation_input_tokens + EXCLUDED.cache_creation_input_tokens,\n total_response_time_ms = \"LiteLLM_DailyTeamSpend\".total_response_time_ms + EXCLUDED.total_response_time_ms,\n timed_requests = \"LiteLLM_DailyTeamSpend\".timed_requests + EXCLUDED.timed_requests,\n spend = \"LiteLLM_DailyTeamSpend\".spend + EXCLUDED.spend,\n updated_at = (NOW() AT TIME ZONE 'UTC')\n", + "describe": { + "columns": [], + "parameters": { + "Left": [ + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Float8Array", + "TextArray" + ] + }, + "nullable": [] + }, + "hash": "9c51401a8907f818e96da28050b74dca981ff954452b35ffbace3e022035b416" +} diff --git a/litellm-rust/crates/db/queries/spend/upsert_daily_team_spend.sql b/litellm-rust/crates/db/queries/spend/upsert_daily_team_spend.sql new file mode 100644 index 00000000000..a9bdef34043 --- /dev/null +++ b/litellm-rust/crates/db/queries/spend/upsert_daily_team_spend.sql @@ -0,0 +1,40 @@ +INSERT INTO "LiteLLM_DailyTeamSpend" ( + id, team_id, date, api_key, model, custom_llm_provider, + mcp_namespaced_tool_name, endpoint, model_group, prompt_tokens, + completion_tokens, api_requests, successful_requests, failed_requests, + cache_read_input_tokens, cache_creation_input_tokens, total_response_time_ms, + timed_requests, spend, updated_at +) +SELECT gen_random_uuid()::text, r.entity_id, r.date, r.api_key, r.model, + r.custom_llm_provider, r.mcp_namespaced_tool_name, r.endpoint, r.model_group, r.prompt_tokens, + r.completion_tokens, r.api_requests, r.successful_requests, + r.failed_requests, r.cache_read, r.cache_creation, r.response_time, + r.timed_requests, r.spend, (NOW() AT TIME ZONE 'UTC') +FROM UNNEST( + $1::text[], $2::text[], $3::text[], $4::text[], $5::text[], + $6::text[], $7::text[], $8::int8[], $9::int8[], $10::int8[], + $11::int8[], $12::int8[], $13::int8[], $14::int8[], $15::int8[], + $16::int8[], $17::float8[], $18::text[] +) AS r( + entity_id, date, api_key, model, custom_llm_provider, endpoint, + model_group, prompt_tokens, completion_tokens, api_requests, + successful_requests, failed_requests, cache_read, cache_creation, + response_time, timed_requests, spend, mcp_namespaced_tool_name +) +ORDER BY r.date, r.entity_id, r.api_key, r.model, r.custom_llm_provider, + r.mcp_namespaced_tool_name, r.endpoint +ON CONFLICT ( + team_id, date, api_key, model, custom_llm_provider, + mcp_namespaced_tool_name, endpoint +) DO UPDATE SET + prompt_tokens = "LiteLLM_DailyTeamSpend".prompt_tokens + EXCLUDED.prompt_tokens, + completion_tokens = "LiteLLM_DailyTeamSpend".completion_tokens + EXCLUDED.completion_tokens, + api_requests = "LiteLLM_DailyTeamSpend".api_requests + EXCLUDED.api_requests, + successful_requests = "LiteLLM_DailyTeamSpend".successful_requests + EXCLUDED.successful_requests, + failed_requests = "LiteLLM_DailyTeamSpend".failed_requests + EXCLUDED.failed_requests, + cache_read_input_tokens = "LiteLLM_DailyTeamSpend".cache_read_input_tokens + EXCLUDED.cache_read_input_tokens, + cache_creation_input_tokens = "LiteLLM_DailyTeamSpend".cache_creation_input_tokens + EXCLUDED.cache_creation_input_tokens, + total_response_time_ms = "LiteLLM_DailyTeamSpend".total_response_time_ms + EXCLUDED.total_response_time_ms, + timed_requests = "LiteLLM_DailyTeamSpend".timed_requests + EXCLUDED.timed_requests, + spend = "LiteLLM_DailyTeamSpend".spend + EXCLUDED.spend, + updated_at = (NOW() AT TIME ZONE 'UTC') diff --git a/litellm-rust/crates/db/src/lib.rs b/litellm-rust/crates/db/src/lib.rs index 3bcd050440a..5b88bcabf32 100644 --- a/litellm-rust/crates/db/src/lib.rs +++ b/litellm-rust/crates/db/src/lib.rs @@ -21,5 +21,5 @@ pub use failure::DbFailure; pub use spend::{ DailySpend, EntitySpend, SpendLog, SpendLogRow, TeamMemberSpend, add_end_user_spend, add_key_spend, add_team_member_spend, add_team_spend, add_user_spend, begin, insert_spend_logs, - lock_team, upsert_daily_user_spend, + lock_team, upsert_daily_team_spend, upsert_daily_user_spend, }; diff --git a/litellm-rust/crates/db/src/spend/daily_team_spend.rs b/litellm-rust/crates/db/src/spend/daily_team_spend.rs new file mode 100644 index 00000000000..f2acd23f468 --- /dev/null +++ b/litellm-rust/crates/db/src/spend/daily_team_spend.rs @@ -0,0 +1,485 @@ +use sqlx::PgExecutor; + +use super::DailySpend; +use crate::Error; + +pub async fn upsert_daily_team_spend( + executor: impl PgExecutor<'_>, + rows: &[DailySpend], +) -> Result<(), Error> { + if rows.is_empty() { + return Ok(()); + } + macro_rules! column { + ($field:ident) => { + rows.iter() + .map(|row| row.$field.clone()) + .collect::>() + }; + } + sqlx::query_file!( + "queries/spend/upsert_daily_team_spend.sql", + &column!(entity_id), + &column!(date), + &column!(api_key), + &column!(model), + &column!(custom_llm_provider), + &column!(endpoint), + &column!(model_group) as &[Option], + &column!(prompt_tokens), + &column!(completion_tokens), + &column!(api_requests), + &column!(successful_requests), + &column!(failed_requests), + &column!(cache_read_input_tokens), + &column!(cache_creation_input_tokens), + &column!(total_response_time_ms), + &column!(timed_requests), + &column!(spend), + &column!(mcp_namespaced_tool_name), + ) + .execute(executor) + .await?; + Ok(()) +} + +#[cfg(test)] +mod tests { + use std::error::Error as StdError; + + use super::{DailySpend, upsert_daily_team_spend}; + use crate::{DailyTeamRow, test_support::database_pool}; + use rstest::rstest; + use sqlx::{PgPool, types::chrono::NaiveDateTime}; + + #[rstest] + #[case::distinct_tools("server.fetch", "server.search")] + #[case::default_and_named_tool("", "server.search")] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn daily_team_spend_separates_tools_and_accumulates( + #[case] first_tool: &str, + #[case] second_tool: &str, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + let first = DailySpend { + entity_id: "daily-team-tools".to_owned(), + date: "2026-01-15".to_owned(), + api_key: "daily-key-tools".to_owned(), + model: "daily-model".to_owned(), + custom_llm_provider: "daily-provider".to_owned(), + endpoint: "/mcp".to_owned(), + mcp_namespaced_tool_name: first_tool.to_owned(), + api_requests: 1, + spend: 0.125, + ..Default::default() + }; + let second = DailySpend { + mcp_namespaced_tool_name: second_tool.to_owned(), + api_requests: 2, + spend: 0.25, + ..first.clone() + }; + upsert_daily_team_spend(&mut *tx, &[second.clone(), first.clone()]).await?; + upsert_daily_team_spend( + &mut *tx, + &[ + DailySpend { + api_requests: 3, + spend: 0.5, + ..first + }, + DailySpend { + api_requests: 5, + spend: 1.0, + ..second + }, + ], + ) + .await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test reads stored tool attribution and counters" + )] + let rows = sqlx::query_as::<_, DailyTeamRow>( + r#"SELECT * FROM "LiteLLM_DailyTeamSpend" + WHERE team_id = $1 AND date = $2 + ORDER BY mcp_namespaced_tool_name"#, + ) + .bind("daily-team-tools") + .bind("2026-01-15") + .fetch_all(&mut *tx) + .await?; + + assert_eq!(rows.len(), 2); + assert_eq!( + rows[0].mcp_namespaced_tool_name.as_deref(), + Some(first_tool) + ); + assert_eq!( + rows[1].mcp_namespaced_tool_name.as_deref(), + Some(second_tool) + ); + assert_eq!((rows[0].api_requests, rows[0].spend), (4, 0.625)); + assert_eq!((rows[1].api_requests, rows[1].spend), (7, 1.25)); + Ok(()) + } + + #[rstest] + #[case::full_keys( + "daily-team-base", + "daily-key-base", + "daily-model", + "daily-provider", + "/chat/completions", + Some("first-group") + )] + #[case::initial_model_group_none( + "daily-team-base", + "daily-key-base", + "daily-model", + "daily-provider", + "/chat/completions", + None + )] + #[case::empty_optional_keys("", "", "", "", "", Some(""))] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn daily_team_spend_upsert_preserves_keys_and_accumulates( + #[case] team_id: &'static str, + #[case] api_key: &'static str, + #[case] model: &'static str, + #[case] custom_llm_provider: &'static str, + #[case] endpoint: &'static str, + #[case] first_model_group: Option<&'static str>, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test exercises UTC timestamp behavior under a non-UTC session" + )] + sqlx::query("SET LOCAL TIME ZONE 'America/Los_Angeles'") + .execute(&mut *tx) + .await?; + + let first_batch = [ + DailySpend { + entity_id: team_id.to_owned(), + date: "2026-01-15".to_owned(), + api_key: api_key.to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: endpoint.to_owned(), + model_group: first_model_group.map(str::to_owned), + prompt_tokens: 1, + completion_tokens: 2, + api_requests: 3, + successful_requests: 4, + failed_requests: 5, + cache_read_input_tokens: 6, + cache_creation_input_tokens: 7, + total_response_time_ms: 8, + timed_requests: 9, + spend: 0.125, + }, + DailySpend { + entity_id: team_id.to_owned(), + date: "2026-01-15".to_owned(), + api_key: api_key.to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: "endpoint-sentinel".to_owned(), + model_group: Some("sentinel-endpoint-group".to_owned()), + prompt_tokens: 101, + completion_tokens: 102, + api_requests: 103, + successful_requests: 104, + failed_requests: 105, + cache_read_input_tokens: 106, + cache_creation_input_tokens: 107, + total_response_time_ms: 108, + timed_requests: 109, + spend: 1.25, + }, + DailySpend { + entity_id: team_id.to_owned(), + date: "2026-01-15".to_owned(), + api_key: "api-key-sentinel".to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: endpoint.to_owned(), + model_group: Some("sentinel-key-group".to_owned()), + prompt_tokens: 201, + completion_tokens: 202, + api_requests: 203, + successful_requests: 204, + failed_requests: 205, + cache_read_input_tokens: 206, + cache_creation_input_tokens: 207, + total_response_time_ms: 208, + timed_requests: 209, + spend: 2.5, + }, + DailySpend { + entity_id: "entity-sentinel".to_owned(), + date: "2026-01-15".to_owned(), + api_key: api_key.to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: endpoint.to_owned(), + model_group: Some("sentinel-entity-group".to_owned()), + prompt_tokens: 301, + completion_tokens: 302, + api_requests: 303, + successful_requests: 304, + failed_requests: 305, + cache_read_input_tokens: 306, + cache_creation_input_tokens: 307, + total_response_time_ms: 308, + timed_requests: 309, + spend: 3.75, + }, + ]; + upsert_daily_team_spend(&mut *tx, &first_batch).await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test captures the inserted row identity before conflict handling" + )] + let (initial_id, initial_created_at): (String, NaiveDateTime) = sqlx::query_as( + r#"SELECT id, created_at + FROM "LiteLLM_DailyTeamSpend" + WHERE team_id = $1 AND date = $2 AND api_key = $3 AND model = $4 + AND custom_llm_provider = $5 AND endpoint = $6"#, + ) + .bind(team_id) + .bind("2026-01-15") + .bind(api_key) + .bind(model) + .bind(custom_llm_provider) + .bind(endpoint) + .fetch_one(&mut *tx) + .await?; + assert!(!initial_id.is_empty()); + + #[expect( + clippy::disallowed_methods, + reason = "The integration test seeds updated_at before exercising the conflict update" + )] + let seeded_updated_at: NaiveDateTime = sqlx::query_scalar( + r#"UPDATE "LiteLLM_DailyTeamSpend" + SET updated_at = TIMESTAMP '2000-01-01' + WHERE id = $1 + RETURNING updated_at"#, + ) + .bind(&initial_id) + .fetch_one(&mut *tx) + .await?; + + let increment = [DailySpend { + entity_id: team_id.to_owned(), + date: "2026-01-15".to_owned(), + api_key: api_key.to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: endpoint.to_owned(), + model_group: Some("second-group".to_owned()), + prompt_tokens: 10, + completion_tokens: 20, + api_requests: 30, + successful_requests: 40, + failed_requests: 50, + cache_read_input_tokens: 60, + cache_creation_input_tokens: 70, + total_response_time_ms: 80, + timed_requests: 90, + spend: 0.625, + }]; + upsert_daily_team_spend(&mut *tx, &increment).await?; + upsert_daily_team_spend(&mut *tx, &[]).await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test captures the transaction timestamp for assertions" + )] + let expected_updated_at: NaiveDateTime = + sqlx::query_scalar("SELECT (NOW() AT TIME ZONE 'UTC')::timestamp(3)") + .fetch_one(&mut *tx) + .await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test reads all rows to verify attribution and accumulation" + )] + let rows: Vec = sqlx::query_as( + r#"SELECT id, team_id, api_key, model, custom_llm_provider, endpoint, + model_group, mcp_namespaced_tool_name, prompt_tokens, + completion_tokens, api_requests, successful_requests, + failed_requests, cache_read_input_tokens, + cache_creation_input_tokens, total_response_time_ms, + timed_requests, spend, date, created_at, updated_at + FROM "LiteLLM_DailyTeamSpend" + WHERE date = $1 AND model = $2 AND custom_llm_provider = $3 + AND mcp_namespaced_tool_name = '' AND team_id = ANY($4) + ORDER BY CASE + WHEN team_id = $5 AND api_key = $6 AND endpoint = $7 THEN 0 + WHEN team_id = $5 AND api_key = $6 AND endpoint = $9 THEN 1 + WHEN team_id = $5 AND api_key = $8 AND endpoint = $7 THEN 2 + WHEN team_id = $10 AND api_key = $6 AND endpoint = $7 THEN 3 + ELSE 4 + END"#, + ) + .bind("2026-01-15") + .bind(model) + .bind(custom_llm_provider) + .bind(vec![team_id, "entity-sentinel"]) + .bind(team_id) + .bind(api_key) + .bind(endpoint) + .bind("api-key-sentinel") + .bind("endpoint-sentinel") + .bind("entity-sentinel") + .fetch_all(&mut *tx) + .await?; + + assert_eq!(rows.len(), 4); + assert_eq!(rows[0].id, initial_id); + assert_eq!(rows[0].team_id.as_deref(), Some(team_id)); + assert_eq!(rows[0].api_key, api_key); + assert_eq!(rows[0].model.as_deref(), Some(model)); + assert_eq!( + rows[0].custom_llm_provider.as_deref(), + Some(custom_llm_provider) + ); + assert_eq!(rows[0].endpoint.as_deref(), Some(endpoint)); + assert_eq!(rows[0].model_group.as_deref(), first_model_group); + assert_eq!(rows[0].mcp_namespaced_tool_name.as_deref(), Some("")); + assert_eq!( + ( + rows[0].prompt_tokens, + rows[0].completion_tokens, + rows[0].api_requests, + rows[0].successful_requests, + rows[0].failed_requests, + rows[0].cache_read_input_tokens, + rows[0].cache_creation_input_tokens, + rows[0].total_response_time_ms, + rows[0].timed_requests, + rows[0].spend + ), + (11, 22, 33, 44, 55, 66, 77, 88, 99, 0.75) + ); + assert_eq!(rows[0].date, "2026-01-15"); + assert_eq!(rows[0].created_at, initial_created_at); + assert!(rows[0].updated_at > seeded_updated_at); + assert_eq!(rows[0].updated_at, expected_updated_at); + + assert!(!rows[1].id.is_empty()); + assert_eq!(rows[1].team_id.as_deref(), Some(team_id)); + assert_eq!(rows[1].api_key, api_key); + assert_eq!(rows[1].model.as_deref(), Some(model)); + assert_eq!( + rows[1].custom_llm_provider.as_deref(), + Some(custom_llm_provider) + ); + assert_eq!(rows[1].endpoint.as_deref(), Some("endpoint-sentinel")); + assert_eq!( + rows[1].model_group.as_deref(), + Some("sentinel-endpoint-group") + ); + assert_eq!(rows[1].mcp_namespaced_tool_name.as_deref(), Some("")); + assert_eq!( + ( + rows[1].prompt_tokens, + rows[1].completion_tokens, + rows[1].api_requests, + rows[1].successful_requests, + rows[1].failed_requests, + rows[1].cache_read_input_tokens, + rows[1].cache_creation_input_tokens, + rows[1].total_response_time_ms, + rows[1].timed_requests, + rows[1].spend + ), + (101, 102, 103, 104, 105, 106, 107, 108, 109, 1.25) + ); + assert_eq!(rows[1].date, "2026-01-15"); + assert!(rows[1].updated_at > seeded_updated_at); + assert_eq!(rows[1].updated_at, expected_updated_at); + + assert!(!rows[2].id.is_empty()); + assert_eq!(rows[2].team_id.as_deref(), Some(team_id)); + assert_eq!(rows[2].api_key, "api-key-sentinel"); + assert_eq!(rows[2].model.as_deref(), Some(model)); + assert_eq!( + rows[2].custom_llm_provider.as_deref(), + Some(custom_llm_provider) + ); + assert_eq!(rows[2].endpoint.as_deref(), Some(endpoint)); + assert_eq!(rows[2].model_group.as_deref(), Some("sentinel-key-group")); + assert_eq!(rows[2].mcp_namespaced_tool_name.as_deref(), Some("")); + assert_eq!( + ( + rows[2].prompt_tokens, + rows[2].completion_tokens, + rows[2].api_requests, + rows[2].successful_requests, + rows[2].failed_requests, + rows[2].cache_read_input_tokens, + rows[2].cache_creation_input_tokens, + rows[2].total_response_time_ms, + rows[2].timed_requests, + rows[2].spend + ), + (201, 202, 203, 204, 205, 206, 207, 208, 209, 2.5) + ); + assert_eq!(rows[2].date, "2026-01-15"); + assert!(rows[2].updated_at > seeded_updated_at); + assert_eq!(rows[2].updated_at, expected_updated_at); + + assert!(!rows[3].id.is_empty()); + assert_eq!(rows[3].team_id.as_deref(), Some("entity-sentinel")); + assert_eq!(rows[3].api_key, api_key); + assert_eq!(rows[3].model.as_deref(), Some(model)); + assert_eq!( + rows[3].custom_llm_provider.as_deref(), + Some(custom_llm_provider) + ); + assert_eq!(rows[3].endpoint.as_deref(), Some(endpoint)); + assert_eq!( + rows[3].model_group.as_deref(), + Some("sentinel-entity-group") + ); + assert_eq!(rows[3].mcp_namespaced_tool_name.as_deref(), Some("")); + assert_eq!( + ( + rows[3].prompt_tokens, + rows[3].completion_tokens, + rows[3].api_requests, + rows[3].successful_requests, + rows[3].failed_requests, + rows[3].cache_read_input_tokens, + rows[3].cache_creation_input_tokens, + rows[3].total_response_time_ms, + rows[3].timed_requests, + rows[3].spend + ), + (301, 302, 303, 304, 305, 306, 307, 308, 309, 3.75) + ); + assert_eq!(rows[3].date, "2026-01-15"); + assert!(rows[3].updated_at > seeded_updated_at); + assert_eq!(rows[3].updated_at, expected_updated_at); + Ok(()) + } +} diff --git a/litellm-rust/crates/db/src/spend/mod.rs b/litellm-rust/crates/db/src/spend/mod.rs index f50440e06de..3f71ae4bf9f 100644 --- a/litellm-rust/crates/db/src/spend/mod.rs +++ b/litellm-rust/crates/db/src/spend/mod.rs @@ -1,3 +1,4 @@ +mod daily_team_spend; mod daily_user_spend; mod end_user_spend; mod key_spend; @@ -7,6 +8,7 @@ mod team_member_spend; mod team_spend; mod user_spend; +pub use daily_team_spend::upsert_daily_team_spend; pub use daily_user_spend::{DailySpend, upsert_daily_user_spend}; pub use end_user_spend::add_end_user_spend; pub use key_spend::{EntitySpend, add_key_spend}; From a783f8e78b87b3c61e834725592c665f7124f7ac Mon Sep 17 00:00:00 2001 From: yujonglee Date: Mon, 26 Oct 2026 17:05:08 -0700 Subject: [PATCH 017/262] feat(db): add typed daily end-user spend upsert (#48237) Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm-rust/Cargo.lock | 1 + ...3bcab69ff6ad3555a3926537586f5d81d933d.json | 31 + litellm-rust/crates/db/Cargo.toml | 1 + .../spend/upsert_daily_end_user_spend.sql | 40 ++ litellm-rust/crates/db/src/lib.rs | 7 +- .../db/src/spend/daily_end_user_spend.rs | 584 ++++++++++++++++++ litellm-rust/crates/db/src/spend/mod.rs | 2 + 7 files changed, 663 insertions(+), 3 deletions(-) create mode 100644 litellm-rust/crates/db/.sqlx/query-f207ff0f5310dea0833361d55993bcab69ff6ad3555a3926537586f5d81d933d.json create mode 100644 litellm-rust/crates/db/queries/spend/upsert_daily_end_user_spend.sql create mode 100644 litellm-rust/crates/db/src/spend/daily_end_user_spend.rs diff --git a/litellm-rust/Cargo.lock b/litellm-rust/Cargo.lock index d0757ebbd2c..32ae431f863 100644 --- a/litellm-rust/Cargo.lock +++ b/litellm-rust/Cargo.lock @@ -3701,6 +3701,7 @@ dependencies = [ "serde", "serde_json", "sqlx", + "strum", "thiserror 2.0.19", "tokio", ] diff --git a/litellm-rust/crates/db/.sqlx/query-f207ff0f5310dea0833361d55993bcab69ff6ad3555a3926537586f5d81d933d.json b/litellm-rust/crates/db/.sqlx/query-f207ff0f5310dea0833361d55993bcab69ff6ad3555a3926537586f5d81d933d.json new file mode 100644 index 00000000000..b2635c549ac --- /dev/null +++ b/litellm-rust/crates/db/.sqlx/query-f207ff0f5310dea0833361d55993bcab69ff6ad3555a3926537586f5d81d933d.json @@ -0,0 +1,31 @@ +{ + "db_name": "PostgreSQL", + "query": "INSERT INTO \"LiteLLM_DailyEndUserSpend\" (\n id, end_user_id, date, api_key, model, custom_llm_provider,\n mcp_namespaced_tool_name, endpoint, model_group, prompt_tokens,\n completion_tokens, api_requests, successful_requests, failed_requests,\n cache_read_input_tokens, cache_creation_input_tokens, total_response_time_ms,\n timed_requests, spend, updated_at\n)\nSELECT gen_random_uuid()::text, r.entity_id, r.date, r.api_key, r.model,\n r.custom_llm_provider, r.mcp_namespaced_tool_name, r.endpoint, r.model_group, r.prompt_tokens,\n r.completion_tokens, r.api_requests, r.successful_requests,\n r.failed_requests, r.cache_read, r.cache_creation, r.response_time,\n r.timed_requests, r.spend, (NOW() AT TIME ZONE 'UTC')\nFROM UNNEST(\n $1::text[], $2::text[], $3::text[], $4::text[], $5::text[],\n $6::text[], $7::text[], $8::int8[], $9::int8[], $10::int8[],\n $11::int8[], $12::int8[], $13::int8[], $14::int8[], $15::int8[],\n $16::int8[], $17::float8[], $18::text[]\n) AS r(\n entity_id, date, api_key, model, custom_llm_provider, endpoint,\n model_group, prompt_tokens, completion_tokens, api_requests,\n successful_requests, failed_requests, cache_read, cache_creation,\n response_time, timed_requests, spend, mcp_namespaced_tool_name\n)\nORDER BY r.date, r.entity_id, r.api_key, r.model, r.custom_llm_provider,\n r.mcp_namespaced_tool_name, r.endpoint\nON CONFLICT (\n end_user_id, date, api_key, model, custom_llm_provider,\n mcp_namespaced_tool_name, endpoint\n) DO UPDATE SET\n prompt_tokens = \"LiteLLM_DailyEndUserSpend\".prompt_tokens + EXCLUDED.prompt_tokens,\n completion_tokens = \"LiteLLM_DailyEndUserSpend\".completion_tokens + EXCLUDED.completion_tokens,\n api_requests = \"LiteLLM_DailyEndUserSpend\".api_requests + EXCLUDED.api_requests,\n successful_requests = \"LiteLLM_DailyEndUserSpend\".successful_requests + EXCLUDED.successful_requests,\n failed_requests = \"LiteLLM_DailyEndUserSpend\".failed_requests + EXCLUDED.failed_requests,\n cache_read_input_tokens = \"LiteLLM_DailyEndUserSpend\".cache_read_input_tokens + EXCLUDED.cache_read_input_tokens,\n cache_creation_input_tokens = \"LiteLLM_DailyEndUserSpend\".cache_creation_input_tokens + EXCLUDED.cache_creation_input_tokens,\n total_response_time_ms = \"LiteLLM_DailyEndUserSpend\".total_response_time_ms + EXCLUDED.total_response_time_ms,\n timed_requests = \"LiteLLM_DailyEndUserSpend\".timed_requests + EXCLUDED.timed_requests,\n spend = \"LiteLLM_DailyEndUserSpend\".spend + EXCLUDED.spend,\n updated_at = (NOW() AT TIME ZONE 'UTC')\n", + "describe": { + "columns": [], + "parameters": { + "Left": [ + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "TextArray", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Int8Array", + "Float8Array", + "TextArray" + ] + }, + "nullable": [] + }, + "hash": "f207ff0f5310dea0833361d55993bcab69ff6ad3555a3926537586f5d81d933d" +} diff --git a/litellm-rust/crates/db/Cargo.toml b/litellm-rust/crates/db/Cargo.toml index 8c1a35c7535..4f8fe4e28e2 100644 --- a/litellm-rust/crates/db/Cargo.toml +++ b/litellm-rust/crates/db/Cargo.toml @@ -11,6 +11,7 @@ macro_rules_attribute.workspace = true serde.workspace = true serde_json.workspace = true sqlx.workspace = true +strum.workspace = true thiserror.workspace = true [dev-dependencies] diff --git a/litellm-rust/crates/db/queries/spend/upsert_daily_end_user_spend.sql b/litellm-rust/crates/db/queries/spend/upsert_daily_end_user_spend.sql new file mode 100644 index 00000000000..8c4936e1a7a --- /dev/null +++ b/litellm-rust/crates/db/queries/spend/upsert_daily_end_user_spend.sql @@ -0,0 +1,40 @@ +INSERT INTO "LiteLLM_DailyEndUserSpend" ( + id, end_user_id, date, api_key, model, custom_llm_provider, + mcp_namespaced_tool_name, endpoint, model_group, prompt_tokens, + completion_tokens, api_requests, successful_requests, failed_requests, + cache_read_input_tokens, cache_creation_input_tokens, total_response_time_ms, + timed_requests, spend, updated_at +) +SELECT gen_random_uuid()::text, r.entity_id, r.date, r.api_key, r.model, + r.custom_llm_provider, r.mcp_namespaced_tool_name, r.endpoint, r.model_group, r.prompt_tokens, + r.completion_tokens, r.api_requests, r.successful_requests, + r.failed_requests, r.cache_read, r.cache_creation, r.response_time, + r.timed_requests, r.spend, (NOW() AT TIME ZONE 'UTC') +FROM UNNEST( + $1::text[], $2::text[], $3::text[], $4::text[], $5::text[], + $6::text[], $7::text[], $8::int8[], $9::int8[], $10::int8[], + $11::int8[], $12::int8[], $13::int8[], $14::int8[], $15::int8[], + $16::int8[], $17::float8[], $18::text[] +) AS r( + entity_id, date, api_key, model, custom_llm_provider, endpoint, + model_group, prompt_tokens, completion_tokens, api_requests, + successful_requests, failed_requests, cache_read, cache_creation, + response_time, timed_requests, spend, mcp_namespaced_tool_name +) +ORDER BY r.date, r.entity_id, r.api_key, r.model, r.custom_llm_provider, + r.mcp_namespaced_tool_name, r.endpoint +ON CONFLICT ( + end_user_id, date, api_key, model, custom_llm_provider, + mcp_namespaced_tool_name, endpoint +) DO UPDATE SET + prompt_tokens = "LiteLLM_DailyEndUserSpend".prompt_tokens + EXCLUDED.prompt_tokens, + completion_tokens = "LiteLLM_DailyEndUserSpend".completion_tokens + EXCLUDED.completion_tokens, + api_requests = "LiteLLM_DailyEndUserSpend".api_requests + EXCLUDED.api_requests, + successful_requests = "LiteLLM_DailyEndUserSpend".successful_requests + EXCLUDED.successful_requests, + failed_requests = "LiteLLM_DailyEndUserSpend".failed_requests + EXCLUDED.failed_requests, + cache_read_input_tokens = "LiteLLM_DailyEndUserSpend".cache_read_input_tokens + EXCLUDED.cache_read_input_tokens, + cache_creation_input_tokens = "LiteLLM_DailyEndUserSpend".cache_creation_input_tokens + EXCLUDED.cache_creation_input_tokens, + total_response_time_ms = "LiteLLM_DailyEndUserSpend".total_response_time_ms + EXCLUDED.total_response_time_ms, + timed_requests = "LiteLLM_DailyEndUserSpend".timed_requests + EXCLUDED.timed_requests, + spend = "LiteLLM_DailyEndUserSpend".spend + EXCLUDED.spend, + updated_at = (NOW() AT TIME ZONE 'UTC') diff --git a/litellm-rust/crates/db/src/lib.rs b/litellm-rust/crates/db/src/lib.rs index 5b88bcabf32..541f97c7db9 100644 --- a/litellm-rust/crates/db/src/lib.rs +++ b/litellm-rust/crates/db/src/lib.rs @@ -19,7 +19,8 @@ pub use end_user::{EndUser, RateLimits, find_end_user}; pub use error::Error; pub use failure::DbFailure; pub use spend::{ - DailySpend, EntitySpend, SpendLog, SpendLogRow, TeamMemberSpend, add_end_user_spend, - add_key_spend, add_team_member_spend, add_team_spend, add_user_spend, begin, insert_spend_logs, - lock_team, upsert_daily_team_spend, upsert_daily_user_spend, + DailySpend, DailyTable, EntitySpend, SpendLog, SpendLogRow, TeamMemberSpend, + add_end_user_spend, add_key_spend, add_team_member_spend, add_team_spend, add_user_spend, + begin, insert_spend_logs, lock_team, upsert_daily_end_user_spend, upsert_daily_spend, + upsert_daily_team_spend, upsert_daily_user_spend, }; diff --git a/litellm-rust/crates/db/src/spend/daily_end_user_spend.rs b/litellm-rust/crates/db/src/spend/daily_end_user_spend.rs new file mode 100644 index 00000000000..6c88d47cdcc --- /dev/null +++ b/litellm-rust/crates/db/src/spend/daily_end_user_spend.rs @@ -0,0 +1,584 @@ +use sqlx::PgExecutor; + +use super::{DailySpend, upsert_daily_team_spend, upsert_daily_user_spend}; +use crate::Error; + +pub async fn upsert_daily_end_user_spend( + executor: impl PgExecutor<'_>, + rows: &[DailySpend], +) -> Result<(), Error> { + if rows.is_empty() { + return Ok(()); + } + macro_rules! column { + ($field:ident) => { + rows.iter() + .map(|row| row.$field.clone()) + .collect::>() + }; + } + sqlx::query_file!( + "queries/spend/upsert_daily_end_user_spend.sql", + &column!(entity_id), + &column!(date), + &column!(api_key), + &column!(model), + &column!(custom_llm_provider), + &column!(endpoint), + &column!(model_group) as &[Option], + &column!(prompt_tokens), + &column!(completion_tokens), + &column!(api_requests), + &column!(successful_requests), + &column!(failed_requests), + &column!(cache_read_input_tokens), + &column!(cache_creation_input_tokens), + &column!(total_response_time_ms), + &column!(timed_requests), + &column!(spend), + &column!(mcp_namespaced_tool_name), + ) + .execute(executor) + .await?; + Ok(()) +} + +#[derive(Clone, Copy, Debug, Eq, Hash, PartialEq, strum::VariantArray)] +pub enum DailyTable { + User, + Team, + EndUser, +} + +pub async fn upsert_daily_spend( + executor: impl PgExecutor<'_>, + table: DailyTable, + rows: &[DailySpend], +) -> Result<(), Error> { + match table { + DailyTable::User => upsert_daily_user_spend(executor, rows).await, + DailyTable::Team => upsert_daily_team_spend(executor, rows).await, + DailyTable::EndUser => upsert_daily_end_user_spend(executor, rows).await, + } +} + +#[cfg(test)] +mod tests { + use std::error::Error as StdError; + + use super::{DailySpend, DailyTable, upsert_daily_end_user_spend, upsert_daily_spend}; + use crate::{DailyEndUserRow, test_support::database_pool}; + use rstest::rstest; + use sqlx::{PgPool, types::chrono::NaiveDateTime}; + + #[rstest] + #[case::full_keys( + "daily-end-user-base", + "daily-key-base", + "daily-model", + "daily-provider", + "/chat/completions", + Some("first-group") + )] + #[case::initial_model_group_none( + "daily-end-user-base", + "daily-key-base", + "daily-model", + "daily-provider", + "/chat/completions", + None + )] + #[case::empty_optional_keys("", "", "", "", "", Some(""))] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn daily_end_user_spend_upsert_preserves_keys_and_accumulates( + #[case] end_user_id: &'static str, + #[case] api_key: &'static str, + #[case] model: &'static str, + #[case] custom_llm_provider: &'static str, + #[case] endpoint: &'static str, + #[case] first_model_group: Option<&'static str>, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test exercises UTC timestamp behavior under a non-UTC session" + )] + sqlx::query("SET LOCAL TIME ZONE 'America/Los_Angeles'") + .execute(&mut *tx) + .await?; + + let first_batch = [ + DailySpend { + entity_id: end_user_id.to_owned(), + date: "2026-01-15".to_owned(), + api_key: api_key.to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: endpoint.to_owned(), + model_group: first_model_group.map(str::to_owned), + prompt_tokens: 1, + completion_tokens: 2, + api_requests: 3, + successful_requests: 4, + failed_requests: 5, + cache_read_input_tokens: 6, + cache_creation_input_tokens: 7, + total_response_time_ms: 8, + timed_requests: 9, + spend: 0.125, + }, + DailySpend { + entity_id: end_user_id.to_owned(), + date: "2026-01-15".to_owned(), + api_key: api_key.to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: "endpoint-sentinel".to_owned(), + model_group: Some("sentinel-endpoint-group".to_owned()), + prompt_tokens: 101, + completion_tokens: 102, + api_requests: 103, + successful_requests: 104, + failed_requests: 105, + cache_read_input_tokens: 106, + cache_creation_input_tokens: 107, + total_response_time_ms: 108, + timed_requests: 109, + spend: 1.25, + }, + DailySpend { + entity_id: end_user_id.to_owned(), + date: "2026-01-15".to_owned(), + api_key: "api-key-sentinel".to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: endpoint.to_owned(), + model_group: Some("sentinel-key-group".to_owned()), + prompt_tokens: 201, + completion_tokens: 202, + api_requests: 203, + successful_requests: 204, + failed_requests: 205, + cache_read_input_tokens: 206, + cache_creation_input_tokens: 207, + total_response_time_ms: 208, + timed_requests: 209, + spend: 2.5, + }, + DailySpend { + entity_id: "entity-sentinel".to_owned(), + date: "2026-01-15".to_owned(), + api_key: api_key.to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: endpoint.to_owned(), + model_group: Some("sentinel-entity-group".to_owned()), + prompt_tokens: 301, + completion_tokens: 302, + api_requests: 303, + successful_requests: 304, + failed_requests: 305, + cache_read_input_tokens: 306, + cache_creation_input_tokens: 307, + total_response_time_ms: 308, + timed_requests: 309, + spend: 3.75, + }, + ]; + upsert_daily_end_user_spend(&mut *tx, &first_batch).await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test captures the inserted row identity before conflict handling" + )] + let (initial_id, initial_created_at): (String, NaiveDateTime) = sqlx::query_as( + r#"SELECT id, created_at + FROM "LiteLLM_DailyEndUserSpend" + WHERE end_user_id = $1 AND date = $2 AND api_key = $3 AND model = $4 + AND custom_llm_provider = $5 AND endpoint = $6"#, + ) + .bind(end_user_id) + .bind("2026-01-15") + .bind(api_key) + .bind(model) + .bind(custom_llm_provider) + .bind(endpoint) + .fetch_one(&mut *tx) + .await?; + assert!(!initial_id.is_empty()); + + #[expect( + clippy::disallowed_methods, + reason = "The integration test seeds updated_at before exercising the conflict update" + )] + let seeded_updated_at: NaiveDateTime = sqlx::query_scalar( + r#"UPDATE "LiteLLM_DailyEndUserSpend" + SET updated_at = TIMESTAMP '2000-01-01' + WHERE id = $1 + RETURNING updated_at"#, + ) + .bind(&initial_id) + .fetch_one(&mut *tx) + .await?; + + let increment = [DailySpend { + entity_id: end_user_id.to_owned(), + date: "2026-01-15".to_owned(), + api_key: api_key.to_owned(), + model: model.to_owned(), + custom_llm_provider: custom_llm_provider.to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: endpoint.to_owned(), + model_group: Some("second-group".to_owned()), + prompt_tokens: 10, + completion_tokens: 20, + api_requests: 30, + successful_requests: 40, + failed_requests: 50, + cache_read_input_tokens: 60, + cache_creation_input_tokens: 70, + total_response_time_ms: 80, + timed_requests: 90, + spend: 0.625, + }]; + upsert_daily_end_user_spend(&mut *tx, &increment).await?; + upsert_daily_end_user_spend(&mut *tx, &[]).await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test captures the transaction timestamp for assertions" + )] + let expected_updated_at: NaiveDateTime = + sqlx::query_scalar("SELECT (NOW() AT TIME ZONE 'UTC')::timestamp(3)") + .fetch_one(&mut *tx) + .await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test reads all rows to verify attribution and accumulation" + )] + let rows: Vec = sqlx::query_as( + r#"SELECT id, end_user_id, api_key, model, custom_llm_provider, endpoint, + model_group, mcp_namespaced_tool_name, prompt_tokens, + completion_tokens, api_requests, successful_requests, + failed_requests, cache_read_input_tokens, + cache_creation_input_tokens, total_response_time_ms, + timed_requests, spend, date, created_at, updated_at + FROM "LiteLLM_DailyEndUserSpend" + WHERE date = $1 AND model = $2 AND custom_llm_provider = $3 + AND mcp_namespaced_tool_name = '' AND end_user_id = ANY($4) + ORDER BY CASE + WHEN end_user_id = $5 AND api_key = $6 AND endpoint = $7 THEN 0 + WHEN end_user_id = $5 AND api_key = $6 AND endpoint = $9 THEN 1 + WHEN end_user_id = $5 AND api_key = $8 AND endpoint = $7 THEN 2 + WHEN end_user_id = $10 AND api_key = $6 AND endpoint = $7 THEN 3 + ELSE 4 + END"#, + ) + .bind("2026-01-15") + .bind(model) + .bind(custom_llm_provider) + .bind(vec![end_user_id, "entity-sentinel"]) + .bind(end_user_id) + .bind(api_key) + .bind(endpoint) + .bind("api-key-sentinel") + .bind("endpoint-sentinel") + .bind("entity-sentinel") + .fetch_all(&mut *tx) + .await?; + + assert_eq!(rows.len(), 4); + assert_eq!(rows[0].id, initial_id); + assert_eq!(rows[0].end_user_id.as_deref(), Some(end_user_id)); + assert_eq!(rows[0].api_key, api_key); + assert_eq!(rows[0].model.as_deref(), Some(model)); + assert_eq!( + rows[0].custom_llm_provider.as_deref(), + Some(custom_llm_provider) + ); + assert_eq!(rows[0].endpoint.as_deref(), Some(endpoint)); + assert_eq!(rows[0].model_group.as_deref(), first_model_group); + assert_eq!(rows[0].mcp_namespaced_tool_name.as_deref(), Some("")); + assert_eq!( + ( + rows[0].prompt_tokens, + rows[0].completion_tokens, + rows[0].api_requests, + rows[0].successful_requests, + rows[0].failed_requests, + rows[0].cache_read_input_tokens, + rows[0].cache_creation_input_tokens, + rows[0].total_response_time_ms, + rows[0].timed_requests, + rows[0].spend + ), + (11, 22, 33, 44, 55, 66, 77, 88, 99, 0.75) + ); + assert_eq!(rows[0].date, "2026-01-15"); + assert_eq!(rows[0].created_at, initial_created_at); + assert!(rows[0].updated_at > seeded_updated_at); + assert_eq!(rows[0].updated_at, expected_updated_at); + + assert!(!rows[1].id.is_empty()); + assert_eq!(rows[1].end_user_id.as_deref(), Some(end_user_id)); + assert_eq!(rows[1].api_key, api_key); + assert_eq!(rows[1].model.as_deref(), Some(model)); + assert_eq!( + rows[1].custom_llm_provider.as_deref(), + Some(custom_llm_provider) + ); + assert_eq!(rows[1].endpoint.as_deref(), Some("endpoint-sentinel")); + assert_eq!( + rows[1].model_group.as_deref(), + Some("sentinel-endpoint-group") + ); + assert_eq!(rows[1].mcp_namespaced_tool_name.as_deref(), Some("")); + assert_eq!( + ( + rows[1].prompt_tokens, + rows[1].completion_tokens, + rows[1].api_requests, + rows[1].successful_requests, + rows[1].failed_requests, + rows[1].cache_read_input_tokens, + rows[1].cache_creation_input_tokens, + rows[1].total_response_time_ms, + rows[1].timed_requests, + rows[1].spend + ), + (101, 102, 103, 104, 105, 106, 107, 108, 109, 1.25) + ); + assert_eq!(rows[1].date, "2026-01-15"); + assert!(rows[1].updated_at > seeded_updated_at); + assert_eq!(rows[1].updated_at, expected_updated_at); + + assert!(!rows[2].id.is_empty()); + assert_eq!(rows[2].end_user_id.as_deref(), Some(end_user_id)); + assert_eq!(rows[2].api_key, "api-key-sentinel"); + assert_eq!(rows[2].model.as_deref(), Some(model)); + assert_eq!( + rows[2].custom_llm_provider.as_deref(), + Some(custom_llm_provider) + ); + assert_eq!(rows[2].endpoint.as_deref(), Some(endpoint)); + assert_eq!(rows[2].model_group.as_deref(), Some("sentinel-key-group")); + assert_eq!(rows[2].mcp_namespaced_tool_name.as_deref(), Some("")); + assert_eq!( + ( + rows[2].prompt_tokens, + rows[2].completion_tokens, + rows[2].api_requests, + rows[2].successful_requests, + rows[2].failed_requests, + rows[2].cache_read_input_tokens, + rows[2].cache_creation_input_tokens, + rows[2].total_response_time_ms, + rows[2].timed_requests, + rows[2].spend + ), + (201, 202, 203, 204, 205, 206, 207, 208, 209, 2.5) + ); + assert_eq!(rows[2].date, "2026-01-15"); + assert!(rows[2].updated_at > seeded_updated_at); + assert_eq!(rows[2].updated_at, expected_updated_at); + + assert!(!rows[3].id.is_empty()); + assert_eq!(rows[3].end_user_id.as_deref(), Some("entity-sentinel")); + assert_eq!(rows[3].api_key, api_key); + assert_eq!(rows[3].model.as_deref(), Some(model)); + assert_eq!( + rows[3].custom_llm_provider.as_deref(), + Some(custom_llm_provider) + ); + assert_eq!(rows[3].endpoint.as_deref(), Some(endpoint)); + assert_eq!( + rows[3].model_group.as_deref(), + Some("sentinel-entity-group") + ); + assert_eq!(rows[3].mcp_namespaced_tool_name.as_deref(), Some("")); + assert_eq!( + ( + rows[3].prompt_tokens, + rows[3].completion_tokens, + rows[3].api_requests, + rows[3].successful_requests, + rows[3].failed_requests, + rows[3].cache_read_input_tokens, + rows[3].cache_creation_input_tokens, + rows[3].total_response_time_ms, + rows[3].timed_requests, + rows[3].spend + ), + (301, 302, 303, 304, 305, 306, 307, 308, 309, 3.75) + ); + assert_eq!(rows[3].date, "2026-01-15"); + assert!(rows[3].updated_at > seeded_updated_at); + assert_eq!(rows[3].updated_at, expected_updated_at); + Ok(()) + } + + #[rstest] + #[case::distinct_tools("server/tool-a", "server/tool-b")] + #[case::empty_and_named_tool("", "server/tool-b")] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn daily_end_user_spend_preserves_tool_attribution( + #[case] first_tool: &str, + #[case] second_tool: &str, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + let first = DailySpend { + entity_id: "daily-end-user-tools".to_owned(), + date: "2026-02-21".to_owned(), + api_key: "tool-key".to_owned(), + model: "tool-model".to_owned(), + custom_llm_provider: "tool-provider".to_owned(), + endpoint: "/mcp".to_owned(), + mcp_namespaced_tool_name: first_tool.to_owned(), + prompt_tokens: 2, + spend: 0.25, + ..Default::default() + }; + let second = DailySpend { + mcp_namespaced_tool_name: second_tool.to_owned(), + prompt_tokens: 5, + spend: 0.5, + ..first.clone() + }; + upsert_daily_end_user_spend(&mut *tx, &[second, first.clone()]).await?; + upsert_daily_end_user_spend(&mut *tx, &[first]).await?; + + #[expect( + clippy::disallowed_methods, + reason = "The integration test reads stored tool attribution and counters" + )] + let rows: Vec = sqlx::query_as( + r#"SELECT * FROM "LiteLLM_DailyEndUserSpend" + WHERE end_user_id = $1 AND date = $2 AND api_key = $3 + ORDER BY mcp_namespaced_tool_name"#, + ) + .bind("daily-end-user-tools") + .bind("2026-02-21") + .bind("tool-key") + .fetch_all(&mut *tx) + .await?; + + assert_eq!(rows.len(), 2); + assert_eq!( + rows[0].mcp_namespaced_tool_name.as_deref(), + Some(first_tool) + ); + assert_eq!( + rows[1].mcp_namespaced_tool_name.as_deref(), + Some(second_tool) + ); + assert_eq!((rows[0].prompt_tokens, rows[0].spend), (4, 0.5)); + assert_eq!((rows[1].prompt_tokens, rows[1].spend), (5, 0.5)); + assert_ne!(rows[0].id, rows[1].id); + Ok(()) + } + + #[rstest] + #[case::user(DailyTable::User, "daily-dispatch-user")] + #[case::team(DailyTable::Team, "daily-dispatch-team")] + #[case::end_user(DailyTable::EndUser, "daily-dispatch-end-user")] + #[tokio::test] + #[ignore = "requires DATABASE_URL pointing to a Prisma-migrated PostgreSQL database"] + async fn daily_spend_dispatches_to_selected_table( + #[case] table: DailyTable, + #[case] entity_id: &'static str, + #[future(awt)] database_pool: Result>, + ) -> Result<(), Box> { + let pool = database_pool?; + let mut tx = pool.begin().await?; + let api_key = format!("{entity_id}-key"); + let rows = [DailySpend { + entity_id: entity_id.to_owned(), + date: "2026-02-20".to_owned(), + api_key: api_key.clone(), + model: "dispatcher-model".to_owned(), + custom_llm_provider: "dispatcher-provider".to_owned(), + mcp_namespaced_tool_name: String::new(), + endpoint: "/dispatcher".to_owned(), + model_group: Some("dispatcher-group".to_owned()), + prompt_tokens: 1, + completion_tokens: 2, + api_requests: 3, + successful_requests: 4, + failed_requests: 5, + cache_read_input_tokens: 6, + cache_creation_input_tokens: 7, + total_response_time_ms: 8, + timed_requests: 9, + spend: 0.125, + }]; + upsert_daily_spend(&mut *tx, table, &rows).await?; + + let count: i64 = match table { + DailyTable::User => + { + #[expect( + clippy::disallowed_methods, + reason = "The integration test checks the user-table dispatcher route" + )] + sqlx::query_scalar( + r#"SELECT COUNT(*) FROM "LiteLLM_DailyUserSpend" + WHERE user_id = $1 AND date = $2 AND api_key = $3 AND model = $4"#, + ) + .bind(entity_id) + .bind("2026-02-20") + .bind(&api_key) + .bind("dispatcher-model") + .fetch_one(&mut *tx) + .await? + } + DailyTable::Team => + { + #[expect( + clippy::disallowed_methods, + reason = "The integration test checks the team-table dispatcher route" + )] + sqlx::query_scalar( + r#"SELECT COUNT(*) FROM "LiteLLM_DailyTeamSpend" + WHERE team_id = $1 AND date = $2 AND api_key = $3 AND model = $4"#, + ) + .bind(entity_id) + .bind("2026-02-20") + .bind(&api_key) + .bind("dispatcher-model") + .fetch_one(&mut *tx) + .await? + } + DailyTable::EndUser => + { + #[expect( + clippy::disallowed_methods, + reason = "The integration test checks the end-user-table dispatcher route" + )] + sqlx::query_scalar( + r#"SELECT COUNT(*) FROM "LiteLLM_DailyEndUserSpend" + WHERE end_user_id = $1 AND date = $2 AND api_key = $3 AND model = $4"#, + ) + .bind(entity_id) + .bind("2026-02-20") + .bind(&api_key) + .bind("dispatcher-model") + .fetch_one(&mut *tx) + .await? + } + }; + assert_eq!(count, 1); + Ok(()) + } +} diff --git a/litellm-rust/crates/db/src/spend/mod.rs b/litellm-rust/crates/db/src/spend/mod.rs index 3f71ae4bf9f..da255843547 100644 --- a/litellm-rust/crates/db/src/spend/mod.rs +++ b/litellm-rust/crates/db/src/spend/mod.rs @@ -1,3 +1,4 @@ +mod daily_end_user_spend; mod daily_team_spend; mod daily_user_spend; mod end_user_spend; @@ -8,6 +9,7 @@ mod team_member_spend; mod team_spend; mod user_spend; +pub use daily_end_user_spend::{DailyTable, upsert_daily_end_user_spend, upsert_daily_spend}; pub use daily_team_spend::upsert_daily_team_spend; pub use daily_user_spend::{DailySpend, upsert_daily_user_spend}; pub use end_user_spend::add_end_user_spend; From b9825e1f87aecd13c87f53851f3fd0d4cb16bfef Mon Sep 17 00:00:00 2001 From: yujonglee Date: Mon, 26 Oct 2026 17:05:08 -0700 Subject: [PATCH 018/262] docs: document incremental database access migration (#48476) * docs(rust): document incremental database access migration * docs(rust): organize database guidance by task * docs: move database access skill to repository root --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .agents/skills/database-access/SKILL.md | 52 +++++++++++++++++++++++++ 1 file changed, 52 insertions(+) create mode 100644 .agents/skills/database-access/SKILL.md diff --git a/.agents/skills/database-access/SKILL.md b/.agents/skills/database-access/SKILL.md new file mode 100644 index 00000000000..796dfafe4f6 --- /dev/null +++ b/.agents/skills/database-access/SKILL.md @@ -0,0 +1,52 @@ +--- +name: database-access +description: Add database queries, extract existing Prisma calls into repositories, or explicitly port queries to Rust and SQLx without expanding migration scope +--- + +# Database access + +## Adding new database access + +- Put Python database access behind an operation in `litellm/repositories` +- Give callers typed inputs and outputs, not Prisma clients, models, or query dictionaries +- Keep query execution and backend selection inside the repository +- Prisma is fine for the implementation, adding a query does not require a Rust port +- Native Rust callers use `litellm-rust/crates/db` directly + +## Asked to move existing access behind a repository + +- Identify the calls being moved and their transaction boundary +- Move the existing Prisma implementation into the relevant repository +- Replace those direct database calls with repository operations +- Preserve return values, errors, and transaction behavior, with focused regression tests +- Keep this an extraction, not a backend migration or unrelated cleanup + +## An equivalent Rust or SQLx query already exists + +- Leave it and the current backend selection unchanged unless integration is explicitly requested +- Its existence alone does not justify switching a Prisma caller to Rust +- Repository extraction can keep using Prisma even when the Rust query is available + +## Asked to port a Prisma query to Rust or SQLx + +- Identify the existing inputs, outputs, errors, and transaction boundary +- Check `litellm-rust/crates/db` for an equivalent query and reuse it if its behavior matches +- Otherwise follow `litellm-rust/crates/db/AGENTS.md` + - Put static SQL in `queries/` and compile-check it with SQLx + - Keep typed inputs and reusable row projections in `src/` + - Refresh SQLx query metadata after SQL changes +- Keep Python conversion in the Python bridge, not in `litellm-rust/crates/db` +- When caller integration is requested, expose the Rust operation through the bridge and call it from the repository + - A query-only port can land without switching callers +- Verify behavior against real PostgreSQL before switching callers + - Check relevant null handling, conflicts, ordering, errors, and transaction semantics +- Remove the old implementation only when no callers need it + +## Migration context and boundaries + +- Long-term direction is to centralize Python database access in repositories, then replace their Prisma implementations incrementally with Rust APIs +- Mixed Prisma and Rust implementations are expected during the transition, unrelated existing calls can stay as they are +- Both backends may have separate pools through PgBouncer, size them together and verify pooling-mode compatibility +- PgBouncer does not share transactions between Prisma and SQLx, keep each atomic unit of work on one backend and transaction +- Never retry a failed Rust write through Prisma when it may already have committed +- Prisma owns schema migrations today, eventual SQLx migration ownership and Prisma removal are separate planned steps, not part of a query port From 1263f70ab63dc662ce043687a85cece965d76c46 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Mon, 26 Oct 2026 17:05:37 -0700 Subject: [PATCH 019/262] feat(ui): budget period tooltip on key, team, user and org spend tiles (#48487) * feat(ui): budget period tooltip on key, team, user and org spend tiles Adds a shared BudgetPeriodTooltip to the four detail-view spend tiles showing the current budget period, max budget, reset interval and spend so far, and makes organization create schedule budget_reset_at and organization info return it Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(ui): give the budget period tooltip trigger its own aria label The default SimpleTooltip trigger shares the question-circle label with InheritedBudgetHint, which broke the key budget display tests that count that icon Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(ui): match the proxy's budget window rules in the period tooltip 30d and Nmo now span calendar months like get_budget_window_start, the arithmetic runs in UTC so a viewer's DST change cannot shift the start, the hourly/daily/weekly/monthly aliases the proxy accepts are normalized before parsing, and spend without a duration reads as lifetime spend Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: joshua Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/proxy/_types.py | 2 +- .../organization_endpoints.py | 3 +- .../test_organization_endpoints.py | 65 +++++++++++++++ .../_components/view_users/user_info_view.tsx | 11 ++- .../organization/organization_view.tsx | 11 ++- .../shared/BudgetPeriodTooltip.test.tsx | 83 +++++++++++++++++++ .../components/shared/BudgetPeriodTooltip.tsx | 65 +++++++++++++++ .../src/components/team/TeamInfo.tsx | 11 ++- .../components/templates/key_info_view.tsx | 11 ++- ui/litellm-dashboard/src/lib/http/schema.d.ts | 2 +- .../src/utils/budgetUtils.test.ts | 40 ++++++++- ui/litellm-dashboard/src/utils/budgetUtils.ts | 41 +++++++++ 12 files changed, 336 insertions(+), 9 deletions(-) create mode 100644 ui/litellm-dashboard/src/components/shared/BudgetPeriodTooltip.test.tsx create mode 100644 ui/litellm-dashboard/src/components/shared/BudgetPeriodTooltip.tsx diff --git a/litellm/proxy/_types.py b/litellm/proxy/_types.py index 6280e2caf87..49d23d82aa9 100644 --- a/litellm/proxy/_types.py +++ b/litellm/proxy/_types.py @@ -3277,7 +3277,7 @@ class LiteLLM_OrganizationTableWithMembers(LiteLLM_OrganizationTable): members: list[LiteLLM_OrganizationMembershipTable] = [] teams: list[LiteLLM_TeamTable] = [] - litellm_budget_table: LiteLLM_BudgetTable | None = None + litellm_budget_table: LiteLLM_BudgetTableFull | None = None created_at: datetime updated_at: datetime diff --git a/litellm/proxy/management_endpoints/organization_endpoints.py b/litellm/proxy/management_endpoints/organization_endpoints.py index d7a44cdd0b8..e1d19d8efae 100644 --- a/litellm/proxy/management_endpoints/organization_endpoints.py +++ b/litellm/proxy/management_endpoints/organization_endpoints.py @@ -504,9 +504,8 @@ async def new_organization( _budget: Final = await _table(BudgetRepository(prisma_client)).create( data={ - **new_budget, + **build_budget_write_data(new_budget, user_api_key_dict.user_id or litellm_proxy_admin_name), "created_by": user_api_key_dict.user_id or litellm_proxy_admin_name, - "updated_by": user_api_key_dict.user_id or litellm_proxy_admin_name, } ) diff --git a/tests/unit/proxy/management_endpoints/test_organization_endpoints.py b/tests/unit/proxy/management_endpoints/test_organization_endpoints.py index a5cae02ea10..16c59aa20b9 100644 --- a/tests/unit/proxy/management_endpoints/test_organization_endpoints.py +++ b/tests/unit/proxy/management_endpoints/test_organization_endpoints.py @@ -1615,3 +1615,68 @@ async def test_delete_organization_is_refused_while_one_of_its_teams_holds_a_ptu prisma_client.db.litellm_teamtable.delete_many.assert_not_called() prisma_client.db.litellm_verificationtoken.delete_many.assert_not_called() prisma_client.db.litellm_organizationtable.delete.assert_not_called() + + +@pytest.mark.asyncio +@pytest.mark.parametrize("budget_duration", ["30d", None]) +async def test_new_organization_schedules_budget_reset_from_duration(monkeypatch, budget_duration): + """/organization/new with an inline budget_duration must write budget_reset_at on the auto-created + budget row, the way team create and /budget/new do, or the org budget never resets and the UI + cannot show the current budget period.""" + from datetime import datetime + + from litellm.proxy._types import LitellmUserRoles, NewOrganizationRequest, UserAPIKeyAuth + from litellm.proxy.management_endpoints.organization_endpoints import new_organization + from litellm.proxy.utils import PrismaClient + + prisma_client = MagicMock() + prisma_client.jsonify_object = MagicMock(side_effect=lambda data: PrismaClient.jsonify_object(prisma_client, data)) + prisma_client.db.litellm_usertable.find_unique = AsyncMock(return_value=None) + prisma_client.db.litellm_budgettable.create = AsyncMock(return_value=MagicMock(budget_id="budget-1")) + prisma_client.db.litellm_organizationtable.create = AsyncMock(return_value={"organization_id": "org-1"}) + monkeypatch.setattr("litellm.proxy.proxy_server.prisma_client", prisma_client) + monkeypatch.setattr("litellm.proxy.proxy_server.llm_router", MagicMock()) + monkeypatch.setattr("litellm.proxy.proxy_server.premium_user", True, raising=False) + + await new_organization( + data=NewOrganizationRequest(organization_alias="org", max_budget=100, budget_duration=budget_duration), + user_api_key_dict=UserAPIKeyAuth(user_id="admin", user_role=LitellmUserRoles.PROXY_ADMIN), + ) + + budget_write = prisma_client.db.litellm_budgettable.create.await_args.kwargs["data"] + if budget_duration is None: + assert "budget_reset_at" not in budget_write, budget_write + return + reset_at = budget_write["budget_reset_at"] + assert isinstance(reset_at, datetime) and reset_at.tzinfo is not None, budget_write + assert budget_write["budget_duration"] == budget_duration + + +def test_organization_info_response_keeps_budget_reset_at(): + """/organization/info must return the budget row's budget_reset_at so the dashboard can show + which budget period the org's spend covers.""" + from datetime import datetime, timezone + + from litellm.proxy._types import LiteLLM_OrganizationTableWithMembers + + reset_at = datetime(2026, 11, 1, tzinfo=timezone.utc) + created_at = datetime(2026, 10, 1, tzinfo=timezone.utc) + response = LiteLLM_OrganizationTableWithMembers( + organization_id="org-1", + organization_alias="org", + budget_id="budget-1", + models=[], + created_by="admin", + updated_by="admin", + created_at=created_at, + updated_at=created_at, + litellm_budget_table={ + "budget_id": "budget-1", + "max_budget": 100.0, + "budget_duration": "30d", + "budget_reset_at": reset_at, + "created_at": created_at, + }, + ) + + assert response.model_dump()["litellm_budget_table"]["budget_reset_at"] == reset_at diff --git a/ui/litellm-dashboard/src/app/(dashboard)/users/_components/view_users/user_info_view.tsx b/ui/litellm-dashboard/src/app/(dashboard)/users/_components/view_users/user_info_view.tsx index 2056142b50a..476c043a258 100644 --- a/ui/litellm-dashboard/src/app/(dashboard)/users/_components/view_users/user_info_view.tsx +++ b/ui/litellm-dashboard/src/app/(dashboard)/users/_components/view_users/user_info_view.tsx @@ -47,6 +47,7 @@ import { Dialog, DialogContent, DialogHeader, DialogTitle } from "@/components/u import ScopedSavingsTab from "@/components/shared/ScopedSavingsTab"; import { AutoRouterUsageView } from "@/app/(dashboard)/cost-optimization/_components/AutoRouterBenchmarksTab"; import { useActivityDateRange } from "@/app/(dashboard)/cost-optimization/_components/useDailyActivityRange"; +import { BudgetPeriodTooltip } from "@/components/shared/BudgetPeriodTooltip"; interface UserInfoViewProps { userId: string; @@ -507,7 +508,15 @@ export default function UserInfoView({
-

Spend

+

+ Spend + +

${formatNumberWithCommas(userData.spend || 0, 2)}

diff --git a/ui/litellm-dashboard/src/components/organization/organization_view.tsx b/ui/litellm-dashboard/src/components/organization/organization_view.tsx index f325e92d2b5..2be549261c3 100644 --- a/ui/litellm-dashboard/src/components/organization/organization_view.tsx +++ b/ui/litellm-dashboard/src/components/organization/organization_view.tsx @@ -27,6 +27,7 @@ import ObjectPermissionsView from "../object_permissions_view"; import MemberModal from "../team/EditMembership"; import { OrgSettingsForm } from "./org-settings/OrgSettingsForm"; import { ORGANIZATION_TAB_URL_KEY, ORGANIZATION_TABS, type OrganizationTab } from "./organizationTabs"; +import { BudgetPeriodTooltip } from "@/components/shared/BudgetPeriodTooltip"; interface OrganizationInfoProps { organizationId: string; @@ -193,7 +194,15 @@ const OrganizationInfoView: React.FC = ({ -

Budget Status

+

+ Budget Status + +

${formatNumberWithCommas(orgData.spend, 4)}

diff --git a/ui/litellm-dashboard/src/components/shared/BudgetPeriodTooltip.test.tsx b/ui/litellm-dashboard/src/components/shared/BudgetPeriodTooltip.test.tsx new file mode 100644 index 00000000000..4d77218a776 --- /dev/null +++ b/ui/litellm-dashboard/src/components/shared/BudgetPeriodTooltip.test.tsx @@ -0,0 +1,83 @@ +import { render, screen } from "@testing-library/react"; +import userEvent from "@testing-library/user-event"; +import { afterEach, describe, expect, it } from "vitest"; + +import { BudgetPeriodTooltip, budgetPeriodLines } from "./BudgetPeriodTooltip"; + +const originalTimezone: string | undefined = process.env.TZ; + +afterEach(() => { + if (originalTimezone === undefined) { + delete process.env.TZ; + return; + } + process.env.TZ = originalTimezone; +}); + +const scheduled = { spend: 12.5, maxBudget: 100, budgetDuration: "30d", budgetResetAt: "2026-04-01T00:00:00Z" }; +const unparseableDuration = { ...scheduled, spend: 0, budgetDuration: "fortnight" }; +const unscheduled = { spend: 0, maxBudget: 100, budgetDuration: "30d", budgetResetAt: null }; +const lifetime = { spend: 3, maxBudget: 50, budgetDuration: null, budgetResetAt: null }; +const noBudget = { spend: null, maxBudget: null, budgetDuration: "30d", budgetResetAt: null }; +const noBudgetNoDuration = { spend: 2, maxBudget: null, budgetDuration: null, budgetResetAt: null }; + +describe("budgetPeriodLines", () => { + it("describes the current period, max budget, interval and spend when a reset is scheduled", () => { + process.env.TZ = "UTC"; + expect(budgetPeriodLines(scheduled)).toEqual([ + "Budget period: Mar 1, 2026 00:00 to Apr 1, 2026 00:00 (UTC)", + "Max budget: $100.00", + "Reset interval: monthly", + "Spend this period: $12.5000", + ]); + }); + + it("falls back to the next reset when the duration cannot be parsed", () => { + process.env.TZ = "UTC"; + expect(budgetPeriodLines(unparseableDuration)).toEqual([ + "Next reset: Apr 1, 2026 00:00 (UTC)", + "Max budget: $100.00", + "Reset interval: fortnight", + "Spend this period: $0.0000", + ]); + }); + + it("omits the period line when no reset has been scheduled yet", () => { + expect(budgetPeriodLines(unscheduled)).toEqual([ + "Max budget: $100.00", + "Reset interval: monthly", + "Spend this period: $0.0000", + ]); + }); + + it("reports a lifetime budget when there is no duration", () => { + expect(budgetPeriodLines(lifetime)).toEqual([ + "Lifetime budget, never resets", + "Max budget: $50.00", + "Spend so far: $3.0000", + ]); + }); + + it("reports no budget when max budget is unset", () => { + expect(budgetPeriodLines(noBudget)).toEqual(["No budget set", "Spend this period: $0.0000"]); + }); + + it("uses lifetime wording when there is neither a budget nor a duration", () => { + expect(budgetPeriodLines(noBudgetNoDuration)).toEqual(["No budget set", "Spend so far: $2.0000"]); + }); +}); + +describe("BudgetPeriodTooltip", () => { + it("shows the budget period details on hover", async () => { + const user = userEvent.setup(); + render(); + + await user.hover(screen.getByLabelText("budget-period-details")); + + const tooltip = await screen.findByTestId("budget-period-tooltip"); + expect(tooltip).toHaveTextContent("Max budget: $10.00"); + expect(tooltip).toHaveTextContent("Reset interval: 1d"); + expect(tooltip).toHaveTextContent("Spend this period: $1.0000"); + expect(tooltip).not.toHaveTextContent("Invalid Date"); + }); +}); diff --git a/ui/litellm-dashboard/src/components/shared/BudgetPeriodTooltip.tsx b/ui/litellm-dashboard/src/components/shared/BudgetPeriodTooltip.tsx new file mode 100644 index 00000000000..56c0667b2a5 --- /dev/null +++ b/ui/litellm-dashboard/src/components/shared/BudgetPeriodTooltip.tsx @@ -0,0 +1,65 @@ +"use client"; + +import dayjs from "dayjs"; +import { CircleHelp } from "lucide-react"; + +import { getBudgetDurationLabel } from "@/components/common_components/budget_duration_dropdown"; +import { SimpleTooltip } from "@/components/ui/tooltip"; +import { budgetPeriodRange } from "@/utils/budgetUtils"; +import { formatNumberWithCommas } from "@/utils/dataUtils"; + +export interface BudgetPeriodTooltipProps { + spend: number | null | undefined; + maxBudget: number | null | undefined; + budgetDuration: string | null | undefined; + budgetResetAt: string | null | undefined; +} + +const formatPeriodDate = (iso: string): string => dayjs(iso).format("MMM D, YYYY HH:mm"); + +const describePeriod = (budgetDuration: string, budgetResetAt: string | null | undefined): string | null => { + const timeZone = Intl.DateTimeFormat().resolvedOptions().timeZone; + const period = budgetPeriodRange(budgetDuration, budgetResetAt); + if (period) { + return `Budget period: ${formatPeriodDate(period.start)} to ${formatPeriodDate(period.end)} (${timeZone})`; + } + if (budgetResetAt && dayjs(budgetResetAt).isValid()) { + return `Next reset: ${formatPeriodDate(budgetResetAt)} (${timeZone})`; + } + return null; +}; + +export const budgetPeriodLines = ({ + spend, + maxBudget, + budgetDuration, + budgetResetAt, +}: BudgetPeriodTooltipProps): readonly string[] => { + const spendLine = `${budgetDuration ? "Spend this period" : "Spend so far"}: $${formatNumberWithCommas(spend ?? 0, 4)}`; + if (maxBudget == null) return ["No budget set", spendLine]; + const maxBudgetLine = `Max budget: $${formatNumberWithCommas(maxBudget, 2)}`; + if (!budgetDuration) return ["Lifetime budget, never resets", maxBudgetLine, spendLine]; + const periodLine = describePeriod(budgetDuration, budgetResetAt); + return [ + ...(periodLine ? [periodLine] : []), + maxBudgetLine, + `Reset interval: ${getBudgetDurationLabel(budgetDuration)}`, + spendLine, + ]; +}; + +export function BudgetPeriodTooltip(props: BudgetPeriodTooltipProps) { + return ( + + {budgetPeriodLines(props).map((line) => ( + {line} + ))} +

+ } + > + + + ); +} diff --git a/ui/litellm-dashboard/src/components/team/TeamInfo.tsx b/ui/litellm-dashboard/src/components/team/TeamInfo.tsx index 0d63f5d0833..0d20d160283 100644 --- a/ui/litellm-dashboard/src/components/team/TeamInfo.tsx +++ b/ui/litellm-dashboard/src/components/team/TeamInfo.tsx @@ -135,6 +135,7 @@ import ResetMemberBudgetsDialog from "./ResetMemberBudgetsDialog"; import { customBudgetMemberUserIds, shouldPromptMemberBudgetReset } from "./memberBudgetReset"; import { useMemberBudgetReset } from "./useMemberBudgetReset"; import { fetchClient } from "@/lib/http/api"; +import { BudgetPeriodTooltip } from "@/components/shared/BudgetPeriodTooltip"; const UI_MANAGED_METADATA_KEYS: ReadonlySet = new Set([ "logging", @@ -1375,7 +1376,15 @@ const TeamInfoView: React.FC = ({ children: (
-

Budget Status

+

+ Budget Status + +

${formatNumberWithCommas(info.spend, 2)}

of {info.max_budget === null ? "Unlimited" : `$${formatNumberWithCommas(info.max_budget, 2)}`}

diff --git a/ui/litellm-dashboard/src/components/templates/key_info_view.tsx b/ui/litellm-dashboard/src/components/templates/key_info_view.tsx index 7b924243fb5..4680368943a 100644 --- a/ui/litellm-dashboard/src/components/templates/key_info_view.tsx +++ b/ui/litellm-dashboard/src/components/templates/key_info_view.tsx @@ -57,6 +57,7 @@ import { } from "../shared/InheritedBudgetHint"; import { KeyEditView } from "./key_edit_view"; import { isTeamAdminEditingMemberKey, teamAdminMemberKeyPayload } from "./teamAdminMemberKeyPayload"; +import { BudgetPeriodTooltip } from "@/components/shared/BudgetPeriodTooltip"; export function needsLifetimeSpendBackfill(spend: number, totalSpend: number | null | undefined): boolean { return (totalSpend ?? 0) < spend; @@ -722,7 +723,15 @@ export default function KeyInfoView({
-

Spend

+

+ Spend + +

${formatNumberWithCommas(currentKeyData.spend, 4)}

diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts index d3c1e0422df..ababe4507b8 100644 --- a/ui/litellm-dashboard/src/lib/http/schema.d.ts +++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts @@ -35066,7 +35066,7 @@ export interface components { created_at: string; /** Created By */ created_by: string; - litellm_budget_table?: components["schemas"]["LiteLLM_BudgetTable"] | null; + litellm_budget_table?: components["schemas"]["LiteLLM_BudgetTableFull"] | null; /** * Members * @default [] diff --git a/ui/litellm-dashboard/src/utils/budgetUtils.test.ts b/ui/litellm-dashboard/src/utils/budgetUtils.test.ts index a3b5f4da00a..e33c779bb65 100644 --- a/ui/litellm-dashboard/src/utils/budgetUtils.test.ts +++ b/ui/litellm-dashboard/src/utils/budgetUtils.test.ts @@ -1,6 +1,6 @@ import { afterEach, describe, expect, it } from "vitest"; -import { describeBudgetResetSchedule, formatBudgetReset, formatBudgetResetUtc } from "./budgetUtils"; +import { budgetPeriodRange, describeBudgetResetSchedule, formatBudgetReset, formatBudgetResetUtc } from "./budgetUtils"; const originalTimezone: string | undefined = process.env.TZ; @@ -44,3 +44,41 @@ describe("describeBudgetResetSchedule", () => { expect(schedule.tooltip).toContain("carries into the next cycle"); }); }); + +describe("budgetPeriodRange", () => { + const resetAt = "2026-04-01T00:00:00Z"; + + it.each([ + ["30d", "2026-03-01T00:00:00.000Z"], + ["monthly", "2026-03-01T00:00:00.000Z"], + ["1mo", "2026-03-01T00:00:00.000Z"], + ["2mo", "2026-02-01T00:00:00.000Z"], + ["7d", "2026-03-25T00:00:00.000Z"], + ["weekly", "2026-03-25T00:00:00.000Z"], + ["1w", "2026-03-25T00:00:00.000Z"], + ["15d", "2026-03-17T00:00:00.000Z"], + ["24h", "2026-03-31T00:00:00.000Z"], + ["daily", "2026-03-31T00:00:00.000Z"], + ["1h", "2026-03-31T23:00:00.000Z"], + ["hourly", "2026-03-31T23:00:00.000Z"], + ])("computes the period start for %s the way the proxy does", (duration, start) => { + expect(budgetPeriodRange(duration, resetAt)).toEqual({ start, end: "2026-04-01T00:00:00.000Z" }); + }); + + it("spans a calendar month for 30d even when the viewer is in a DST-shifting timezone", () => { + process.env.TZ = "America/New_York"; + expect(budgetPeriodRange("30d", "2026-04-01T00:00:00Z")?.start).toBe("2026-03-01T00:00:00.000Z"); + expect(budgetPeriodRange("30d", "2026-03-01T00:00:00Z")?.start).toBe("2026-02-01T00:00:00.000Z"); + }); + + it.each([ + ["bogus", resetAt], + ["0d", resetAt], + ["30d", "not-a-date"], + ["30d", null], + [null, resetAt], + ["", resetAt], + ])("returns null for duration %s and reset %s instead of an invalid date", (duration, reset) => { + expect(budgetPeriodRange(duration, reset)).toBeNull(); + }); +}); diff --git a/ui/litellm-dashboard/src/utils/budgetUtils.ts b/ui/litellm-dashboard/src/utils/budgetUtils.ts index 171ce5818f7..23af15eb539 100644 --- a/ui/litellm-dashboard/src/utils/budgetUtils.ts +++ b/ui/litellm-dashboard/src/utils/budgetUtils.ts @@ -54,3 +54,44 @@ export function describeBudgetResetSchedule( tooltip: `Resets every ${budgetDuration}, but the next reset time has not been scheduled yet. ${ROLLOVER_NOTE}`, }; } + +const BUDGET_DURATION_WORD_ALIASES: Record = { + hourly: "1h", + daily: "24h", + weekly: "7d", + monthly: "30d", +}; + +const BUDGET_DURATION_UNITS: Record = { + s: "second", + m: "minute", + h: "hour", + d: "day", + w: "week", + mo: "month", +}; + +export interface BudgetPeriod { + start: string; + end: string; +} + +/** Mirrors the proxy's get_budget_window_start: `30d` and `Nmo` span calendar months, the rest are fixed deltas. */ +export function budgetPeriodRange( + budgetDuration: string | null | undefined, + budgetResetAt: string | null | undefined, +): BudgetPeriod | null { + if (!budgetDuration || !budgetResetAt) return null; + const end = dayjs.utc(budgetResetAt); + if (!end.isValid()) return null; + const normalized = budgetDuration.trim().toLowerCase(); + const match = /^(\d+)(mo|s|m|h|d|w)$/.exec(BUDGET_DURATION_WORD_ALIASES[normalized] ?? normalized); + if (!match) return null; + const amount = Number(match[1]); + if (amount <= 0) return null; + const start = + match[2] === "d" && amount === 30 + ? end.subtract(1, "month") + : end.subtract(amount, BUDGET_DURATION_UNITS[match[2]]); + return { start: start.toISOString(), end: end.toISOString() }; +} From 76d001a7c06d5dbf93f9191b247db0ef981b6c66 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Mon, 26 Oct 2026 17:06:09 -0700 Subject: [PATCH 020/262] fix(router): serve a team's wildcard deployment before a proxy-wide wildcard (#48490) * fix(router): serve a team's wildcard deployment before a proxy-wide wildcard Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(router): keep the wildcard precedence helpers free of partially typed locals Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(router): call each pattern router once in the wildcard precedence helpers Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(ptu): a team's wildcard reservation serves beside a proxy-wide catch-all Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: joshua Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/router.py | 20 +++++------ .../test_ptu_consumption.py | 16 +++------ tests/unit/test_router/test_router.py | 36 ++++++++++++++++++- 3 files changed, 50 insertions(+), 22 deletions(-) diff --git a/litellm/router.py b/litellm/router.py index 548df8e6721..ddb4b9bc075 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -13788,21 +13788,21 @@ class Router: return [{**DeploymentTypedDict(**m), "model_name": model_name} for m in matches] def wildcard_route_deployments(self, model: str, team_id: str | None) -> Sequence[Mapping[str, object]]: - """The deployments routing serves ``model`` from through a wildcard: the most specific - proxy-wide pattern matching it, else ``team_id``'s own pattern, never both.""" - proxy_wide: Final[Sequence[Mapping[str, object]]] = self.pattern_router.get_deployments_by_pattern(model=model) + """The deployments routing serves ``model`` from through a wildcard: ``team_id``'s own pattern + matching it, else the most specific proxy-wide pattern, never both.""" team_router: Final = self.team_pattern_routers.get(team_id) if team_id is not None else None - if proxy_wide or team_router is None: - return proxy_wide - return team_router.get_deployments_by_pattern(model=model) + team_owned: Final[Sequence[Mapping[str, object]]] = ( + team_router.get_deployments_by_pattern(model=model) if team_router is not None else () + ) + return team_owned or self.pattern_router.get_deployments_by_pattern(model=model) def wildcard_routed_models(self, model: str, team_id: str | None) -> frozenset[str]: """The models wildcard_route_deployments would route ``model`` to, without copying the deployments.""" - proxy_wide: Final = self.pattern_router.get_models_by_pattern(model=model) team_router: Final = self.team_pattern_routers.get(team_id) if team_id is not None else None - if proxy_wide or team_router is None: - return proxy_wide - return team_router.get_models_by_pattern(model=model) + team_owned: Final = ( + team_router.get_models_by_pattern(model=model) if team_router is not None else frozenset[str]() + ) + return team_owned or self.pattern_router.get_models_by_pattern(model=model) def team_ptu_ceiling(self, team_id: str, model_group: str) -> PTUTeamCeiling | None: """The per-minute ceiling ``team_id``'s PTU shares set on the group serving ``model_group``, diff --git a/tests/unit/proxy/management_endpoints/test_ptu_consumption.py b/tests/unit/proxy/management_endpoints/test_ptu_consumption.py index a446afbd809..065ec93dcd0 100644 --- a/tests/unit/proxy/management_endpoints/test_ptu_consumption.py +++ b/tests/unit/proxy/management_endpoints/test_ptu_consumption.py @@ -232,14 +232,10 @@ def test_rows_keyed_by_a_name_a_wildcard_route_serves_are_sized_by_its_shared_de assert attached.results[0].breakdown.model_groups["ptu-chat"].metrics.ptu_hours == pytest.approx(1.0) -@pytest.mark.parametrize( - ("catch_all_routes", "expected_ptu_hours"), [(False, 1.0), (True, 0.0)], ids=["team-wildcard", "behind-catch-all"] -) -def test_a_teams_wildcard_reservation_reads_ptu_hours_only_while_the_router_serves_from_it( - monkeypatch, catch_all_routes, expected_ptu_hours -): - """The router tries the proxy-wide wildcards before a team's own, so a team's `ptu-*` - reservation behind an open `*` route never serves `ptu-chat`, and its row reads no PTU-hours.""" +@pytest.mark.parametrize("catch_all_routes", [False, True], ids=["team-wildcard", "beside-catch-all"]) +def test_a_teams_wildcard_reservation_reads_ptu_hours_even_beside_a_proxy_wide_catch_all(monkeypatch, catch_all_routes): + """The router tries a team's own wildcard before the proxy-wide ones, so a team's `ptu-*` + reservation serves `ptu-chat` whether or not an open `*` route exists, and its row reads its PTU-hours.""" monkeypatch.setenv("LITELLM_ENABLE_PTU_COST_ATTRIBUTION", "True") reservation: Final = { "model_name": "ptu-team-r", @@ -264,9 +260,7 @@ def test_a_teams_wildcard_reservation_reads_ptu_hours_only_while_the_router_serv attached: Final = with_ptu_consumption(_response(_day("2026-09-23", {"ptu-chat": one_hour})), router, "team-r") - assert attached.results[0].breakdown.model_groups["ptu-chat"].metrics.ptu_hours == pytest.approx( - expected_ptu_hours - ) + assert attached.results[0].breakdown.model_groups["ptu-chat"].metrics.ptu_hours == pytest.approx(1.0) def _mixed_ptu_router() -> Router: diff --git a/tests/unit/test_router/test_router.py b/tests/unit/test_router/test_router.py index 55628cb0c34..3004f83b1df 100644 --- a/tests/unit/test_router/test_router.py +++ b/tests/unit/test_router/test_router.py @@ -8885,7 +8885,8 @@ def test_get_wildcard_deployment_usable_by_team_prefers_the_team_pattern(): pytest.param(False, "rwild-chat", "team-r", ("team-r-wildcard",), id="team-pattern-when-no-proxy-wide-match"), pytest.param(False, "rwild-chat", "team-b", (), id="another-teams-pattern-never-serves"), pytest.param(False, "rwild-chat", None, (), id="no-team-no-team-pattern"), - pytest.param(True, "rwild-chat", "team-r", ("catch-all",), id="proxy-wide-pattern-beats-the-team-pattern"), + pytest.param(True, "rwild-chat", "team-r", ("team-r-wildcard",), id="team-pattern-beats-the-proxy-wide-pattern"), + pytest.param(True, "rwild-chat", "team-b", ("catch-all",), id="another-team-falls-through-to-proxy-wide"), pytest.param(True, "ptu-chat", "team-r", ("ptu-wildcard",), id="only-the-most-specific-proxy-wide-pattern"), ], ) @@ -8924,6 +8925,39 @@ def test_wildcard_route_deployments_is_the_one_pattern_routing_serves_from( ) +@pytest.mark.parametrize( + ("team_id", "expected_id"), + [ + pytest.param("team-a", "team-a-byok", id="team-key-uses-its-own-byok-wildcard"), + pytest.param("team-b", "shared-openrouter", id="team-without-byok-uses-the-shared-wildcard"), + pytest.param(None, "shared-openrouter", id="key-without-team-uses-the-shared-wildcard"), + ], +) +def test_team_byok_wildcard_is_served_before_a_proxy_wide_wildcard_of_the_same_name( + team_id: str | None, expected_id: str +): + """Regression: a proxy-wide openrouter/* shadowed a team's own openrouter/* BYOK deployment for that team's keys.""" + router: Final = litellm.Router( + model_list=[ + { + "model_name": "model_name_team-a_internal", + "litellm_params": {"model": "openrouter/*", "api_key": "sk-team-a"}, + "model_info": {"id": "team-a-byok", "team_id": "team-a", "team_public_model_name": "openrouter/*"}, + }, + { + "model_name": "openrouter/*", + "litellm_params": {"model": "openrouter/*", "api_key": "sk-shared"}, + "model_info": {"id": "shared-openrouter"}, + }, + ] + ) + requested: Final = "openrouter/openai/gpt-5-nano" + + served: Final = router.wildcard_route_deployments(requested, team_id) + + assert tuple(Deployment.model_validate(d).model_info.id for d in served) == (expected_id,) + + def test_get_deployment_credentials_with_provider_aws_bedrock_runtime_endpoint(): """ Test that get_deployment_credentials_with_provider correctly copies From 9873128b42165e8b016afc6cdc0dc1c6ae23f961 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Mon, 26 Oct 2026 17:13:56 -0700 Subject: [PATCH 021/262] fix(team): keep the team reset schedule when a temp budget increase is set on a member inheriting the team default (#48495) * fix(team): keep the team reset schedule when a temp budget increase is set on a member inheriting the team default Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(integration): expect the temp-only member row to carry the team default cap Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: joshua Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../management_endpoints/common_utils.py | 21 ++-- .../spend/test_team_member_spend.py | 106 +++++++++++++++++- .../test_upsert_budget_membership.py | 17 ++- 3 files changed, 127 insertions(+), 17 deletions(-) diff --git a/litellm/proxy/management_endpoints/common_utils.py b/litellm/proxy/management_endpoints/common_utils.py index adf89c29279..983c3d24513 100644 --- a/litellm/proxy/management_endpoints/common_utils.py +++ b/litellm/proxy/management_endpoints/common_utils.py @@ -569,8 +569,8 @@ _TEAM_MEMBER_BUDGET_LIMIT_FIELDS: Final = ( "temp_budget_expiry", ) -_TEMP_BUDGET_FIELDS: Final = frozenset({"temp_budget_increase", "temp_budget_expiry"}) +_BUDGET_COLUMNS: Final = TypeAdapter(dict[str, object]) MEMBER_BUDGET_PATCH_FIELDS: Final = MappingProxyType( { @@ -653,8 +653,8 @@ async def upsert_budget_and_membership( ``shared_budget_ids`` extends that protection to any other row more than one membership points at, which a caller patching several members at once has already counted; a row listed there is cloned rather than written in place. - A patch that only touches the temporary budget pair never copies permanent - limits into a new row, so the member keeps inheriting the live team default. + A patch whose every field already matches the shared row changes nothing and + is a no-op rather than a clone. """ ignore_default_model_budget_clear: Final = ( existing_budget_id is not None @@ -685,7 +685,6 @@ async def upsert_budget_and_membership( is_shared_default: Final = existing_budget_id is not None and ( existing_budget_id == team_default_budget_id or existing_budget_id in (shared_budget_ids or frozenset()) ) - temp_only: Final = frozenset(write_data) <= _TEMP_BUDGET_FIELDS async def _disconnect(): await tx.litellm_teammembership.update( @@ -707,11 +706,15 @@ async def upsert_budget_and_membership( return source_row: Final = ( - await tx.litellm_budgettable.find_unique(where={"budget_id": existing_budget_id}) - if is_shared_default and not temp_only - else None + await tx.litellm_budgettable.find_unique(where={"budget_id": existing_budget_id}) if is_shared_default else None ) - source: Final[Mapping[str, object]] = source_row.model_dump() if source_row is not None else MappingProxyType({}) + source: Final[Mapping[str, object]] = ( + MappingProxyType(_BUDGET_COLUMNS.validate_python(source_row.model_dump())) + if source_row is not None + else MappingProxyType({}) + ) + if is_shared_default and all(source.get(field) == value for field, value in effective_patch.items()): + return create_data: Final[dict[str, object]] = { # mutable-ok: Prisma create payloads are dict-shaped "created_by": user_api_key_dict.user_id or "", @@ -740,7 +743,7 @@ async def upsert_budget_and_membership( create_data.pop("budget_reset_at", None) if not _has_meaningful_budget_limit(create_data): - if existing_budget_id is not None and not temp_only: + if existing_budget_id is not None: await _disconnect() return diff --git a/tests/integration/spend/test_team_member_spend.py b/tests/integration/spend/test_team_member_spend.py index 306138e2bb1..c11dc9db4bf 100644 --- a/tests/integration/spend/test_team_member_spend.py +++ b/tests/integration/spend/test_team_member_spend.py @@ -1,3 +1,4 @@ +import asyncio import os import uuid from collections.abc import Callable, Iterator @@ -7,10 +8,14 @@ from typing import Final import httpx import pytest from integration._support.client import Gateway, Scenario, eventually, object_value, string_value -from integration._support.database import read_rows +from integration._support.database import read_rows, write_rows from pydantic import BaseModel, JsonValue from redis import Redis +from litellm.proxy.common_utils.reset_budget_job import ResetBudgetJob +from litellm.proxy.common_utils.user_api_key_cache import UserApiKeyCache +from litellm.proxy.utils import PrismaClient, ProxyLogging + def _python_isoformat(value: datetime) -> str: return value.isoformat() @@ -444,9 +449,7 @@ def test_member_update_temp_budget_increase_readmits_a_blocked_member( ) assert added.status_code == 200, added.text default_budget_id: Final = _team_default_budget_id(team) if budget_source == "team-default" else None - default_budget_before: Final = ( - _budget_record(default_budget_id) if default_budget_id is not None else () - ) + default_budget_before: Final = _budget_record(default_budget_id) if default_budget_id is not None else () if default_budget_id is not None: assert len(default_budget_before) == 1, repr(default_budget_before) assert default_budget_before[0].max_budget == 0.05, default_budget_before @@ -503,7 +506,7 @@ def test_member_update_temp_budget_increase_readmits_a_blocked_member( else: assert default_budget_id is not None assert state[0].budget_id != default_budget_id, state - assert state[0].max_budget is None, state + assert state[0].max_budget == 0.05, state default_budget_after: Final = _budget_record(default_budget_id) assert default_budget_after == default_budget_before, repr(default_budget_after) assert default_budget_after[0].max_budget == 0.05, default_budget_after @@ -1024,3 +1027,96 @@ def test_bulk_update_restores_team_default_when_last_member_limit_is_cleared( assert first_observations + second_observations == (provider_model, provider_model), repr( (first_observations, second_observations) ) + + +def _budget_reset_at(budget_id: str) -> str: + rows: Final = read_rows( + 'SELECT budget_reset_at::text AS budget_reset_at FROM "LiteLLM_BudgetTable" WHERE budget_id = %s', (budget_id,) + ) + assert len(rows) == 1, rows + return string_value(rows[0]["budget_reset_at"]) + + +async def _run_scheduled_budget_reset() -> None: + client: Final = PrismaClient( + database_url=os.environ["DATABASE_URL"], proxy_logging_obj=ProxyLogging(user_api_key_cache=UserApiKeyCache()) + ) + await client.connect() + try: + await ResetBudgetJob( + ProxyLogging(user_api_key_cache=UserApiKeyCache()), client + ).reset_budget_for_litellm_budget_table() + finally: + await client.db.disconnect() + + +def test_temp_budget_increase_on_a_team_default_member_keeps_the_team_reset_schedule( + gateway: Gateway, upstream: httpx.Client +) -> None: + with gateway.scenario() as scenario: + model, provider_model = _priced_model(scenario) + team: Final = scenario.team(models=[model], team_member_budget=5, team_member_budget_duration="30d") + topped_up: Final = scenario.user() + untouched: Final = scenario.user() + for user in (topped_up, untouched): + added = gateway.request( + "POST", "/team/member_add", {"team_id": team, "member": {"user_id": user, "role": "user"}} + ) + assert added.status_code == 200, added.text + default_budget_id: Final = _team_default_budget_id(team) + for user in (topped_up, untouched): + key = scenario.key(team_id=team, user_id=user) + chat = _chat(gateway, model, key, f"spend before top-up {uuid.uuid4().hex}") + assert chat.status_code == 200, chat.text + observed: Final = _observed_models(upstream) + assert observed == (provider_model, provider_model), repr(observed) + for user in (topped_up, untouched): + accrued = eventually( + lambda user=user: _budget_state(team, user), + lambda values: len(values) == 1 and values[0].spend is not None and values[0].spend > 0, + seconds=70, + ) + assert accrued[0].budget_id == default_budget_id, accrued + + expiry: Final = datetime.now(timezone.utc) + timedelta(days=30) + granted: Final = _member_update( + gateway, + { + "team_id": team, + "user_id": topped_up, + "temp_budget_increase": 1, + "temp_budget_expiry": expiry.isoformat(), + }, + ) + assert granted.temp_budget_increase == 1, granted + topped_up_state: Final = _budget_state(team, topped_up) + assert len(topped_up_state) == 1, topped_up_state + topped_up_budget_id: Final = topped_up_state[0].budget_id + assert topped_up_budget_id is not None and topped_up_budget_id != default_budget_id, topped_up_state + assert topped_up_state[0].max_budget == 5, topped_up_state + assert topped_up_state[0].budget_duration == "30d", topped_up_state + assert topped_up_state[0].temp_budget_increase == 1, topped_up_state + assert _budget_reset_at(topped_up_budget_id) == _budget_reset_at(default_budget_id), topped_up_state + assert _budget_state(team, untouched)[0].budget_id == default_budget_id + + write_rows( + "UPDATE \"LiteLLM_BudgetTable\" SET budget_reset_at = NOW() - INTERVAL '1 hour' WHERE budget_id IN (%s, %s)", + (default_budget_id, topped_up_budget_id), + ) + asyncio.run(_run_scheduled_budget_reset()) + for user in (topped_up, untouched): + after_reset = _budget_state(team, user) + assert len(after_reset) == 1 and after_reset[0].spend == 0, (user, after_reset) + assert _budget_reset_at(topped_up_budget_id) == _budget_reset_at(default_budget_id) + + cleared: Final = _member_update( + gateway, + {"team_id": team, "user_id": topped_up, "temp_budget_increase": None, "temp_budget_expiry": None}, + ) + assert cleared.temp_budget_increase is None, cleared + final_state: Final = _budget_state(team, topped_up) + assert len(final_state) == 1, final_state + assert final_state[0].budget_id == topped_up_budget_id, final_state + assert final_state[0].budget_duration == "30d", final_state + assert final_state[0].max_budget == 5, final_state + assert final_state[0].temp_budget_increase is None, final_state diff --git a/tests/unit/proxy/common_utils/test_upsert_budget_membership.py b/tests/unit/proxy/common_utils/test_upsert_budget_membership.py index 1f7154f0a74..4aa1a7f7cb1 100644 --- a/tests/unit/proxy/common_utils/test_upsert_budget_membership.py +++ b/tests/unit/proxy/common_utils/test_upsert_budget_membership.py @@ -267,10 +267,17 @@ async def test_create_from_temp_pair_never_snapshots_team_default(mock_tx, fake_ @pytest.mark.asyncio -async def test_temp_pair_on_shared_default_member_creates_bare_row(mock_tx, fake_user): +async def test_temp_pair_on_shared_default_member_clones_default_with_its_reset_schedule(mock_tx, fake_user): expiry = datetime(2100, 1, 1, tzinfo=timezone.utc) + default_reset_at = datetime(2026, 11, 1, tzinfo=timezone.utc) mock_tx.litellm_budgettable.find_unique = AsyncMock( - return_value=budget_row(budget_id="team-default-budget-1", max_budget=0.4, rpm_limit=10) + return_value=budget_row( + budget_id="team-default-budget-1", + max_budget=0.4, + rpm_limit=10, + budget_duration="30d", + budget_reset_at=default_reset_at, + ) ) await upsert_budget_and_membership( mock_tx, @@ -282,10 +289,14 @@ async def test_temp_pair_on_shared_default_member_creates_bare_row(mock_tx, fake team_default_budget_id="team-default-budget-1", ) - mock_tx.litellm_budgettable.find_unique.assert_not_awaited() mock_tx.litellm_budgettable.update.assert_not_called() + mock_tx.litellm_teammembership.update.assert_not_called() assert stored_budget_row(mock_tx) == { "model_max_budget": "{}", + "max_budget": 0.4, + "rpm_limit": 10, + "budget_duration": "30d", + "budget_reset_at": default_reset_at, "temp_budget_increase": 1.0, "temp_budget_expiry": expiry, } From 833d82bb4ee4886a9d9058a219fddf0d09e700b3 Mon Sep 17 00:00:00 2001 From: tin-berri Date: Mon, 26 Oct 2026 20:14:57 -0400 Subject: [PATCH 022/262] fix(mcp): reject revoked browser sessions during gateway authorization (#48494) --- .../mcp_server/discoverable_endpoints.py | 24 +- .../mcp_server/test_discoverable_endpoints.py | 271 ++++++++++++++---- 2 files changed, 228 insertions(+), 67 deletions(-) diff --git a/litellm/proxy/_experimental/mcp_server/discoverable_endpoints.py b/litellm/proxy/_experimental/mcp_server/discoverable_endpoints.py index f5c54451006..ca7ad9e3384 100644 --- a/litellm/proxy/_experimental/mcp_server/discoverable_endpoints.py +++ b/litellm/proxy/_experimental/mcp_server/discoverable_endpoints.py @@ -472,15 +472,15 @@ def redeem_passthrough_authorization_code( return sealed -def _session_cookie_user_id(request: Request) -> str | None: +async def _session_cookie_user_id(request: Request) -> str | None: """The signed-in litellm user for a browser request, or ``None``. Thin wrapper so the aggregate DCR flow's verbs receive the identity as a plain value instead of parsing cookies themselves.""" from litellm.proxy._experimental.mcp_server.byok_oauth_endpoints import ( # noqa: PLC0415 # circular import at module load - user_id_from_session_cookie, + get_authenticated_browser_user_id, ) - return user_id_from_session_cookie(request) + return await get_authenticated_browser_user_id(request) def _redirect_to_litellm_login(request: Request) -> RedirectResponse: @@ -996,17 +996,13 @@ async def _resolve_oauth_authorization_user( enforce_binding: bool, ) -> str | RedirectResponse: """Resolve the authorization subject without replacing denied credentials with cookie grants.""" - from litellm.proxy._experimental.mcp_server.byok_oauth_endpoints import ( # noqa: PLC0415 # proxy import cycle - user_id_from_session_cookie, - ) - use_gateway_credential: Final = enforce_binding and await oauth_authorization_uses_gateway_credential(request) request_user_id: Final = ( await authorize_oauth_credential_request(request, mcp_server.server_id) if use_gateway_credential else None ) if use_gateway_credential and request_user_id is None: return _bridge_access_denied_redirect(redirect_uri, state, mcp_server) - user_id: Final = request_user_id or user_id_from_session_cookie(request) + user_id: Final = request_user_id or await _session_cookie_user_id(request) if user_id is None: return _redirect_to_litellm_login(request) if not await _user_can_reach_mcp_server(user_id, mcp_server.server_id): @@ -1024,7 +1020,7 @@ async def _managed_authorization_scope( request ) session_user: Final = ( - _session_cookie_user_id(request) if authorized_user_id is None and not gateway_credential else None + await _session_cookie_user_id(request) if authorized_user_id is None and not gateway_credential else None ) scope_user_id: Final = authorized_user_id or ( await authorize_oauth_credential_request(request, server.server_id) @@ -2359,7 +2355,7 @@ async def authorize_mcp_session( code_challenge=code_challenge, code_challenge_method=code_challenge_method, response_type=response_type, - session_user_id=_session_cookie_user_id(request), + session_user_id=await _session_cookie_user_id(request), resource=resource, scope=scope, ) @@ -2391,7 +2387,7 @@ async def authorize( code_challenge=code_challenge, code_challenge_method=code_challenge_method, response_type=response_type, - session_user_id=_session_cookie_user_id(request), + session_user_id=await _session_cookie_user_id(request), lookup_consent_teams=lookup_consent_teams, ) return aggregate_authorize( @@ -2402,7 +2398,7 @@ async def authorize( code_challenge=code_challenge, code_challenge_method=code_challenge_method, response_type=response_type, - session_user_id=_session_cookie_user_id(request), + session_user_id=await _session_cookie_user_id(request), resource=resource, scope=scope, ) @@ -2560,7 +2556,7 @@ async def authorize_flow(request: Request, flow: str) -> Response: return await describe_connect_flow( request=request, flow_handle=flow, - session_user_id=_session_cookie_user_id(request), + session_user_id=await _session_cookie_user_id(request), lookup_vendor_credential=_vendor_credential_state, lookup_server_reachability=_user_can_reach_mcp_server, ) @@ -2586,7 +2582,7 @@ async def authorize_complete( return await complete_connect_flow( request=request, flow_handle=flow, - session_user_id=_session_cookie_user_id(request), + session_user_id=await _session_cookie_user_id(request), cache=user_api_key_cache, delivery=delivery, team_id=team_id, diff --git a/tests/unit/proxy/_experimental/mcp_server/test_discoverable_endpoints.py b/tests/unit/proxy/_experimental/mcp_server/test_discoverable_endpoints.py index a43dacaf100..cedfa296515 100644 --- a/tests/unit/proxy/_experimental/mcp_server/test_discoverable_endpoints.py +++ b/tests/unit/proxy/_experimental/mcp_server/test_discoverable_endpoints.py @@ -5599,12 +5599,13 @@ def _bridge_server(**overrides): return MCPServer(**fields) -def _bridge_mock_request(): +def _bridge_mock_request(cookie: str | None = None) -> MagicMock: from fastapi import Request - mock_request = MagicMock(spec=Request) + mock_request: Final = MagicMock(spec=Request) mock_request.base_url = "https://litellm.example.com/" mock_request.headers = {} + mock_request.cookies = {"token": cookie} if cookie else {} return mock_request @@ -6524,7 +6525,7 @@ async def test_interactive_bridge_gateway_code_for_another_server_is_rejected_40 @pytest.mark.asyncio -async def test_interactive_bridge_authorize_seals_sso_user_into_state(): +async def test_interactive_bridge_authorize_seals_sso_user_into_state(monkeypatch: pytest.MonkeyPatch) -> None: """On the short-circuit bridge oauth_delegate arm, authorize captures the SSO user from the UI session cookie and seals it (and the target server) into the encrypted OAuth state, so the callback can later mint a user-bound gateway code; it still proceeds to the upstream redirect. @@ -6540,16 +6541,13 @@ async def test_interactive_bridge_authorize_seals_sso_user_into_state(): admitted = UserAPIKeyAuth(user_id="sso-user-42") admitted.mcp_admitted_user_subject = True captured: dict = {} + cookie: Final = _browser_session_cookie(monkeypatch, "sso-user-42") def _capture(**kwargs): captured.update(kwargs) return "mocked_encrypted_state" with ( - patch( - "litellm.proxy._experimental.mcp_server.byok_oauth_endpoints.user_id_from_session_cookie", - return_value="sso-user-42", - ), patch( "litellm.proxy._experimental.mcp_server.auth.user_api_key_auth_mcp.MCPRequestHandler.reload_admitted_user", new=AsyncMock(return_value=admitted), @@ -6565,7 +6563,7 @@ async def test_interactive_bridge_authorize_seals_sso_user_into_state(): ), ): response = await authorize_with_server( - request=_bridge_mock_request(), + request=_bridge_mock_request(cookie), mcp_server=server, client_id="ignored", redirect_uri="http://127.0.0.1:60108/callback", @@ -6581,7 +6579,9 @@ async def test_interactive_bridge_authorize_seals_sso_user_into_state(): @pytest.mark.asyncio @pytest.mark.parametrize("user_can_reach_server", [True, False]) -async def test_bridge_authorize_gates_on_the_egress_server_access_resolver(user_can_reach_server): +async def test_bridge_authorize_gates_on_the_egress_server_access_resolver( + monkeypatch: pytest.MonkeyPatch, user_can_reach_server: bool +) -> None: """The interactive dcr_bridge oauth_delegate authorize admits the signed-in user the way MCP egress will and refuses with an RFC 6749 access_denied redirect when that admitted subject cannot reach the target server, instead of minting an envelope whose every tool request would @@ -6607,14 +6607,11 @@ async def test_bridge_authorize_gates_on_the_egress_server_access_resolver(user_ mock_request = MagicMock(spec=Request) mock_request.base_url = "https://litellm.example.com/" mock_request.headers = {} + mock_request.cookies = {"token": _browser_session_cookie(monkeypatch, "bridge-user-1")} client_redirect = "http://127.0.0.1:60108/callback" try: with ( - patch( - "litellm.proxy._experimental.mcp_server.byok_oauth_endpoints.user_id_from_session_cookie", - return_value="bridge-user-1", - ), patch( "litellm.proxy._experimental.mcp_server.auth.user_api_key_auth_mcp.MCPRequestHandler.reload_admitted_user", new=AsyncMock(return_value=admitted), @@ -6660,7 +6657,9 @@ async def test_bridge_authorize_gates_on_the_egress_server_access_resolver(user_ @pytest.mark.asyncio @pytest.mark.parametrize("reload_status,expect_denial", [(401, True), (500, False), (503, False)]) -async def test_bridge_authorize_reload_failure_denies_or_stays_retryable(reload_status, expect_denial): +async def test_bridge_authorize_reload_failure_denies_or_stays_retryable( + monkeypatch: pytest.MonkeyPatch, reload_status: int, expect_denial: bool +) -> None: """An unknown or deactivated signed-in user denies like a missing grant (fail closed); a DB outage keeps its retryable 503 instead of masquerading as an access denial.""" from urllib.parse import parse_qs, urlparse @@ -6679,13 +6678,10 @@ async def test_bridge_authorize_reload_failure_denies_or_stays_retryable(reload_ mock_request = MagicMock(spec=Request) mock_request.base_url = "https://litellm.example.com/" mock_request.headers = {} + mock_request.cookies = {"token": _browser_session_cookie(monkeypatch, "bridge-user-1")} try: with ( - patch( - "litellm.proxy._experimental.mcp_server.byok_oauth_endpoints.user_id_from_session_cookie", - return_value="bridge-user-1", - ), patch( "litellm.proxy._experimental.mcp_server.auth.user_api_key_auth_mcp.MCPRequestHandler.reload_admitted_user", new=AsyncMock(side_effect=HTTPException(status_code=reload_status, detail="x")), @@ -6728,19 +6724,15 @@ async def test_interactive_bridge_authorize_without_session_redirects_to_login() from litellm.types.mcp import MCPAuth server = _bridge_server(auth_type=MCPAuth.oauth_delegate, client_id="admin-client", registration_url=None) - with patch( - "litellm.proxy._experimental.mcp_server.byok_oauth_endpoints.user_id_from_session_cookie", - return_value=None, - ): - response = await authorize_with_server( - request=_bridge_mock_request(), - mcp_server=server, - client_id="ignored", - redirect_uri="http://127.0.0.1:60108/callback", - state="s", - code_challenge="chal", - code_challenge_method="S256", - ) + response = await authorize_with_server( + request=_bridge_mock_request(), + mcp_server=server, + client_id="ignored", + redirect_uri="http://127.0.0.1:60108/callback", + state="s", + code_challenge="chal", + code_challenge_method="S256", + ) assert "/sso/key/generate" in response.headers["location"] @@ -11997,10 +11989,97 @@ def _s256(verifier: str) -> str: _NATIVE_CLIENT_MASTER_KEY = "sk-test-salt-for-LIT-5874" +def _browser_session_cookie( + monkeypatch: pytest.MonkeyPatch, + user_id: str, + *, + signing_key: str = _NATIVE_CLIENT_MASTER_KEY, + session_key: str | None = None, + expired_session: bool = False, + expired_cookie: bool = False, +) -> str: + import jwt + + from litellm.proxy import proxy_server + from litellm.proxy._types import UserAPIKeyAuth + from litellm.proxy.auth.auth_checks import LITELLM_SESSION_TOKEN_PREFIX + from litellm.proxy.common_utils.encrypt_decrypt_utils import encrypt_bearer_token + + monkeypatch.setattr(proxy_server, "master_key", signing_key) + if proxy_server.prisma_client is None: + monkeypatch.setattr(proxy_server, "prisma_client", object()) + monkeypatch.setattr(proxy_server, "general_settings", {**proxy_server.general_settings, "supported_db_objects": []}) + session: Final = UserAPIKeyAuth( + user_id=user_id, + expires=datetime(2000 if expired_session else 2099, 1, 1, tzinfo=timezone.utc), + ) + key: Final = ( + encrypt_bearer_token(session.model_dump_json(exclude_none=True), LITELLM_SESSION_TOKEN_PREFIX) + if session_key is None + else session_key + ) + return jwt.encode( + {"user_id": user_id, "key": key, "login_method": "sso", "exp": 946684800 if expired_cookie else 9999999999}, + signing_key, + algorithm="HS256", + ) + + +class _BrowserSessionDatabase: + def __init__(self) -> None: + from litellm.proxy._types import UserAPIKeyAuth, hash_token + + self.row: UserAPIKeyAuth | None = UserAPIKeyAuth( + token=hash_token("sk-browser-session"), + user_id="u1", + expires=datetime(2099, 1, 1, tzinfo=timezone.utc), + ) + self.litellm_deprecatedverificationtoken = self + + def __call__(self, **kwargs: object) -> "_BrowserSessionDatabase": + return self + + async def query_first(self, query: str, *args: object) -> dict[str, object] | None: + if self.row is None: + return None + return { + **self.row.model_dump(exclude={"last_refreshed_at"}), + "team_models": None, + "team_blocked": None, + "team_members_with_roles": None, + } + + async def find_first(self, **kwargs: object) -> None: + return None + + +@pytest.fixture +def browser_session_database(monkeypatch: pytest.MonkeyPatch) -> _BrowserSessionDatabase: + import prisma + + from litellm.proxy import proxy_server + from litellm.proxy._types import hash_token + from litellm.proxy.common_utils.user_api_key_cache import UserApiKeyCache + from litellm.proxy.utils import PrismaClient + + database: Final = _BrowserSessionDatabase() + monkeypatch.setattr(prisma, "Prisma", database) + for name in ("DATABASE_URL_READ_REPLICA", "IAM_TOKEN_DB_AUTH", "AZURE_POSTGRESQL_AUTH"): + monkeypatch.delenv(name, raising=False) + monkeypatch.setattr( + proxy_server, + "prisma_client", + PrismaClient("postgresql://local-test@localhost/browser-session", proxy_server.proxy_logging_obj), + ) + cache: Final = UserApiKeyCache() + cache.set_cache(hash_token("sk-browser-session"), database.row) + monkeypatch.setattr(proxy_server, "user_api_key_cache", cache) + return database + + def _native_client_app(monkeypatch): """The unauthenticated discoverable router served over TestClient with a signed UI session cookie available, plus fakes for the two database-backed hooks the native-client flow calls.""" - import jwt from fastapi import FastAPI from fastapi.testclient import TestClient @@ -12029,14 +12108,108 @@ def _native_client_app(monkeypatch): app = FastAPI() app.include_router(router) client = TestClient(app) - session_cookie = jwt.encode( - {"user_id": "u1", "login_method": "username_password", "exp": int(time.time()) + 600}, - _NATIVE_CLIENT_MASTER_KEY, - algorithm="HS256", - ) + session_cookie: Final = _browser_session_cookie(monkeypatch, "u1") return client, session_cookie, minted +@pytest.mark.parametrize( + "authorize_path,resource", + [("/authorize", None), ("/authorize/mcp-session", None), ("/authorize", "http://testserver")], +) +@pytest.mark.parametrize( + "session_state", ["valid", "revoked", "blocked", "expired", "wrong_owner", "missing_key", "no_database"] +) +def test_gateway_authorize_requires_live_browser_session( + monkeypatch: pytest.MonkeyPatch, + browser_session_database: _BrowserSessionDatabase, + authorize_path: str, + resource: str | None, + session_state: str, +) -> None: + from urllib.parse import urlparse + + from litellm.proxy import proxy_server + + client, _, _ = _native_client_app(monkeypatch) + database: Final = browser_session_database + assert database.row is not None + database.row = None if session_state == "revoked" else database.row.model_copy( + update={ + "blocked": session_state == "blocked", + "expires": datetime(2000 if session_state == "expired" else 2099, 1, 1, tzinfo=timezone.utc), + "user_id": "another-user" if session_state == "wrong_owner" else "u1", + } + ) + cookie: Final = _browser_session_cookie( + monkeypatch, "u1", session_key="" if session_state == "missing_key" else "sk-browser-session" + ) + client.cookies.set("token", cookie) + if session_state == "no_database": + monkeypatch.setattr(proxy_server, "prisma_client", None) + registered: Final = client.post("/register", json={"redirect_uris": ["http://127.0.0.1/callback"]}) + assert registered.status_code == 201, registered.text + response: Final = client.get( + authorize_path, + params={ + "client_id": registered.json()["client_id"], + "redirect_uri": "http://127.0.0.1/callback", + "response_type": "code", + "code_challenge": _s256("v" * 43), + "code_challenge_method": "S256", + **({"resource": resource} if resource else {}), + }, + follow_redirects=False, + ) + if session_state == "valid" and resource: + assert response.status_code == 200 and 'name="decision"' in response.text, response.text + else: + assert response.status_code == 303, response.text + assert urlparse(response.headers["location"]).path == ( + "/ui/connect" if session_state == "valid" else "/sso/key/generate" + ) + + +@pytest.mark.parametrize("endpoint", ["flow", "complete"]) +@pytest.mark.parametrize("revoked", [False, True]) +def test_gateway_connect_rechecks_session_after_authorize( + monkeypatch: pytest.MonkeyPatch, + browser_session_database: _BrowserSessionDatabase, + endpoint: str, + revoked: bool, +) -> None: + from urllib.parse import parse_qs, urlparse + + client, _, _ = _native_client_app(monkeypatch) + client.cookies.set("token", _browser_session_cookie(monkeypatch, "u1", session_key="sk-browser-session")) + registered: Final = client.post("/register", json={"redirect_uris": ["http://127.0.0.1/callback"]}) + assert registered.status_code == 201, registered.text + authorized: Final = client.get( + "/authorize/mcp-session", + params={ + "client_id": registered.json()["client_id"], + "redirect_uri": "http://127.0.0.1/callback", + "response_type": "code", + "code_challenge": _s256("v" * 43), + "code_challenge_method": "S256", + }, + follow_redirects=False, + ) + flow: Final = parse_qs(urlparse(authorized.headers["location"]).query)["connect_flow"][0] + if revoked: + browser_session_database.row = None + response: Final = ( + client.get("/authorize/flow", params={"flow": flow}) + if endpoint == "flow" + else client.post("/authorize/complete", data={"flow": flow}, follow_redirects=False) + ) + assert response.status_code == (401 if revoked else 200 if endpoint == "flow" else 303), response.text + if revoked: + assert response.json()["error"] == "login_required" + assert "location" not in response.headers + elif endpoint == "complete": + assert parse_qs(urlparse(response.headers["location"]).query)["code"] + + @pytest.mark.parametrize("authorize_path", ["/authorize/mcp-session", "/authorize"]) def test_gateway_authorize_routes_forward_server_scope(monkeypatch: pytest.MonkeyPatch, authorize_path: str) -> None: from http.cookies import SimpleCookie @@ -13605,11 +13778,7 @@ async def test_identity_bound_authorize_preserves_presented_jwt_permissions( else "https://idp.example.test", ) ) - cookie: Final = jwt.encode( - {"user_id": "cookie-owner", "login_method": "sso", "exp": int(time.time()) + 300}, - master, - algorithm="HS256", - ) + cookie: Final = _browser_session_cookie(monkeypatch, "cookie-owner", signing_key=master) response: Final = await discoverable_endpoints.authorize_with_server( request=_token_request( { @@ -13645,7 +13814,7 @@ async def test_identity_bound_authorize_preserves_presented_jwt_permissions( @pytest.mark.asyncio @pytest.mark.parametrize("credential", ["none", "opaque", "foreign_jwt"]) -@pytest.mark.parametrize("cookie_state", ["allowed", "server_denied", "expired", "missing"]) +@pytest.mark.parametrize("cookie_state", ["allowed", "server_denied", "expired", "missing", "session_expired"]) async def test_identity_bound_authorize_unrelated_bearer_uses_browser_session( jwt_oauth_identity: tuple["JWTHandler", "RSAPrivateKey"], monkeypatch: pytest.MonkeyPatch, @@ -13654,8 +13823,6 @@ async def test_identity_bound_authorize_unrelated_bearer_uses_browser_session( ) -> None: from urllib.parse import parse_qs, urlparse - import jwt - from litellm.models.user import LiteLLM_UserTable from litellm.proxy import proxy_server from litellm.proxy._experimental.mcp_server import discoverable_endpoints, mcp_server_manager @@ -13694,14 +13861,12 @@ async def test_identity_bound_authorize_unrelated_bearer_uses_browser_session( if credential == "foreign_jwt" else "unrelated-upstream-bearer" ) - cookie: Final = jwt.encode( - { - "user_id": "cookie-owner", - "login_method": "sso", - "exp": int(time.time()) + (-60 if cookie_state == "expired" else 300), - }, - master, - algorithm="HS256", + cookie: Final = _browser_session_cookie( + monkeypatch, + "cookie-owner", + signing_key=master, + expired_cookie=cookie_state == "expired", + expired_session=cookie_state == "session_expired", ) response: Final = await discoverable_endpoints.authorize_with_server( request=_token_request( From 549e6d4f465ec9cf4ca80d3d7e2541ff61ea29ef Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Mon, 26 Oct 2026 17:17:52 -0700 Subject: [PATCH 023/262] fix(router): keep DB-only deployments priced across price data reloads (#48486) * fix(router): track every router for price data reloads so DB-only deployments keep custom pricing Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(router): register the router for reload replay only once model_list exists, and type the regression test Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: joshua Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/router.py | 7 +++-- .../unit/test_router_model_cost_isolation.py | 30 +++++++++++++++++++ 2 files changed, 34 insertions(+), 3 deletions(-) diff --git a/litellm/router.py b/litellm/router.py index ddb4b9bc075..8d95e3e91d4 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -1483,15 +1483,16 @@ class Router: if model_list is not None: # set_model_list will build indices automatically self.set_model_list(model_list) - # Track this router so a price data reload can rebuild its deployments' - # cost-map entries from the list it is serving at that moment. - _live_routers.add(self) self.healthy_deployments: list = self.model_list for m in model_list: if "model" in m["litellm_params"]: self.deployment_latency_map[m["litellm_params"]["model"]] = 0 else: self.model_list: list = [] # initialize an empty list - to allow _add_deployment and delete_deployment to work + # Track this router so a price data reload can rebuild its deployments' + # cost-map entries from the list it is serving at that moment, whether + # those deployments came from model_list or were added later from the DB. + _live_routers.add(self) if allowed_fails is not None: self.allowed_fails = allowed_fails diff --git a/tests/unit/test_router_model_cost_isolation.py b/tests/unit/test_router_model_cost_isolation.py index f001008ee2c..20b0055f729 100644 --- a/tests/unit/test_router_model_cost_isolation.py +++ b/tests/unit/test_router_model_cost_isolation.py @@ -3081,6 +3081,36 @@ def test_reload_keeps_custom_pricing_configured_on_litellm_params_for_a_db_model _invalidate_model_cost_lowercase_map() +def test_reload_keeps_custom_pricing_of_a_db_model_on_a_router_built_without_a_model_list( + monkeypatch: pytest.MonkeyPatch, +) -> None: + """ + A proxy whose config.yaml has no model_list builds its router without one and + takes every deployment from the DB afterwards. A price data reload must restore + that deployment's custom pricing exactly as it does for a config router. + """ + fetched_catalog: Final = copy.deepcopy(litellm.model_cost) + router: Final = Router() + router.add_deployment( + deployment=Deployment( + model_name="db-only-priced", + litellm_params=LiteLLM_Params( + model="openai/gpt-4o", + api_key="sk-fake", + input_cost_per_token=0.000123, + output_cost_per_token=0.000456, + ), + model_info=ModelInfo(id="db-only-priced-id"), + ) + ) + assert litellm.model_cost["db-only-priced-id"]["input_cost_per_token"] == 0.000123 + + _simulate_price_data_reload_with_provider_sets(monkeypatch, fetched_catalog) + + assert litellm.model_cost["db-only-priced-id"]["input_cost_per_token"] == 0.000123 + assert litellm.model_cost["db-only-priced-id"]["output_cost_per_token"] == 0.000456 + + def test_replay_live_router_model_cost_rebuilds_every_live_router(): """ A process can hold more than one Router, so the rebuild has to fan out across From 100529391a249e2f6c24bdc2c198afb0d57e59cf Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Mon, 26 Oct 2026 17:24:44 -0700 Subject: [PATCH 024/262] fix(ui): show the budget period date range instead of "cycle" on team member spend (#48488) * fix(ui): show the budget period date range instead of "cycle" on team member spend Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(ui): derive the budget period start in UTC before showing it in local time Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(ui): keep clock times on sub-day budget periods and restore the total spend lower bound wording Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: joshua Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../src/components/team/MyUserTab.test.tsx | 6 +- .../src/components/team/MyUserTab.tsx | 16 ++-- .../components/team/TeamMemberTab.test.tsx | 29 ++++++- .../src/components/team/TeamMemberTab.tsx | 41 ++++++---- .../src/utils/budgetUtils.test.ts | 77 ++++++++++++++++++- ui/litellm-dashboard/src/utils/budgetUtils.ts | 64 +++++++++++++-- 6 files changed, 198 insertions(+), 35 deletions(-) diff --git a/ui/litellm-dashboard/src/components/team/MyUserTab.test.tsx b/ui/litellm-dashboard/src/components/team/MyUserTab.test.tsx index 24ce626ecb7..eee9fcdadd1 100644 --- a/ui/litellm-dashboard/src/components/team/MyUserTab.test.tsx +++ b/ui/litellm-dashboard/src/components/team/MyUserTab.test.tsx @@ -48,7 +48,7 @@ describe("MyUserTab", () => { expect(screen.getByText("Never resets")).toBeInTheDocument(); }); - it("shows the next reset time when the member budget has a reset window", () => { + it("shows the budget period and next reset when the member budget has a reset window", () => { vi.mocked(useMyTeamMember).mockReturnValue({ data: { user_id: "user-1", @@ -69,6 +69,8 @@ describe("MyUserTab", () => { renderWithProviders(); - expect(screen.getByText("Resets Jul 15, 2026 12:00")).toBeInTheDocument(); + expect(screen.getByText("Current Period Spend (USD)")).toBeInTheDocument(); + expect(screen.getByText("Jun 15 - Jul 15, 2026 (resets Jul 15, 2026 12:00)")).toBeInTheDocument(); + expect(screen.queryByText(/cycle/i)).not.toBeInTheDocument(); }); }); diff --git a/ui/litellm-dashboard/src/components/team/MyUserTab.tsx b/ui/litellm-dashboard/src/components/team/MyUserTab.tsx index bf1a2c2c242..8d7583c51e4 100644 --- a/ui/litellm-dashboard/src/components/team/MyUserTab.tsx +++ b/ui/litellm-dashboard/src/components/team/MyUserTab.tsx @@ -1,4 +1,4 @@ -import { describeBudgetResetSchedule } from "@/utils/budgetUtils"; +import { BudgetResetSchedule, describeBudgetResetSchedule } from "@/utils/budgetUtils"; import { formatNumberWithCommas } from "@/utils/dataUtils"; import { SimpleTooltip } from "@/components/ui/tooltip"; import { Badge } from "@/components/ui/badge"; @@ -30,6 +30,12 @@ const formatRateLimit = (value: number | null | undefined): string => { return formatNumberWithCommas(value, 0); }; +function describePeriodLine(schedule: BudgetResetSchedule): string { + if (schedule.period) return `${schedule.period} (resets ${schedule.label})`; + if (schedule.resetAt) return `Resets ${schedule.label}`; + return schedule.label; +} + export default function MyUserTab({ teamId }: MyUserTabProps) { const { data, isLoading, error } = useMyTeamMember(teamId); @@ -93,16 +99,14 @@ export default function MyUserTab({ teamId }: MyUserTabProps) {

- {labelWithTooltip("Current Cycle Spend (USD)", budgetReset.tooltip)} + {labelWithTooltip("Current Period Spend (USD)", budgetReset.tooltip)}

${formatNumber(spend, 4)}

of {maxBudget === null ? "Unlimited" : `$${formatNumber(maxBudget, 4)}`}
-
- {budgetReset.resetAt ? `Resets ${budgetReset.label}` : budgetReset.label} -
+
{describePeriodLine(budgetReset)}
@@ -121,7 +125,7 @@ export default function MyUserTab({ teamId }: MyUserTabProps) { {labelWithTooltip( "Total Spend (USD)", - "Cumulative spend across budget cycles within this team. This is a lower bound: lifetime tracking began 2026-04-21, so cycles completed before then are not included. It is never less than Current Cycle Spend.", + "Cumulative spend within this team across budget periods. This is a lower bound: lifetime tracking began 2026-04-21, so periods that reset before then are not included. It is never less than Current Period Spend.", )}

${formatNumber(totalSpend, 4)}

diff --git a/ui/litellm-dashboard/src/components/team/TeamMemberTab.test.tsx b/ui/litellm-dashboard/src/components/team/TeamMemberTab.test.tsx index 38a8e4f97d5..9350de8a8fc 100644 --- a/ui/litellm-dashboard/src/components/team/TeamMemberTab.test.tsx +++ b/ui/litellm-dashboard/src/components/team/TeamMemberTab.test.tsx @@ -316,6 +316,29 @@ describe("TeamMembersComponent", () => { expect(screen.getByText("Jul 15, 2026 12:00")).toBeInTheDocument(); }); + it("shows the budget period date range instead of a bare reset date when the duration is known", () => { + const teamData = createMockTeamData(); + teamData.team_memberships[0].litellm_budget_table!.budget_duration = "30d"; + renderWithProviders( + , + ); + + expect(screen.getByRole("columnheader", { name: /^Budget Period/ })).toBeInTheDocument(); + expect(screen.getByRole("columnheader", { name: /^Current Period Spend \(USD\)/ })).toBeInTheDocument(); + expect(screen.getByText("Jun 15 - Jul 15, 2026")).toBeInTheDocument(); + expect(screen.queryByText("Jul 15, 2026 12:00")).not.toBeInTheDocument(); + expect(screen.queryByText(/cycle/i)).not.toBeInTheDocument(); + }); + it("shows Never resets for a member whose budget has no reset window", () => { const teamData = createMockTeamData(); teamData.team_memberships[0].litellm_budget_table!.budget_reset_at = null; @@ -696,7 +719,7 @@ describe("TeamMembersComponent", () => { />, ); - it("resets the member's current cycle spend to $0 after confirming, then refreshes the team", async () => { + it("resets the member's current period spend to $0 after confirming, then refreshes the team", async () => { const user = userEvent.setup(); POST.mockResolvedValue({ data: {} }); renderEditableTab(); @@ -745,7 +768,7 @@ describe("TeamMembersComponent", () => { expect(POST).not.toHaveBeenCalled(); }); - it("disables the reset with a reason on members that have no current cycle spend", async () => { + it("disables the reset with a reason on members that have no current period spend", async () => { const user = userEvent.setup(); renderEditableTab(); @@ -753,7 +776,7 @@ describe("TeamMembersComponent", () => { "reset-member-spend", ); await user.hover(resetButton); - expect(await screen.findByText("No current cycle spend to reset")).toBeInTheDocument(); + expect(await screen.findByText("No current period spend to reset")).toBeInTheDocument(); await user.click(resetButton); expect(screen.queryByRole("dialog")).not.toBeInTheDocument(); diff --git a/ui/litellm-dashboard/src/components/team/TeamMemberTab.tsx b/ui/litellm-dashboard/src/components/team/TeamMemberTab.tsx index 319f8c973f6..1ff77f565a5 100644 --- a/ui/litellm-dashboard/src/components/team/TeamMemberTab.tsx +++ b/ui/litellm-dashboard/src/components/team/TeamMemberTab.tsx @@ -102,7 +102,7 @@ export default function TeamMemberTab({ return "0"; }; - const getUserCurrentCycleSpend = (userId: string | null): number => { + const getUserCurrentPeriodSpend = (userId: string | null): number => { if (!userId) return 0; return findMembership(userId)?.spend ?? 0; }; @@ -153,12 +153,16 @@ export default function TeamMemberTab({ return findMembership(userId)?.litellm_budget_table?.budget_reset_at ?? null; }; - const renderBudgetReset = (userId: string | null) => { + const getUserBudgetSchedule = (userId: string | null) => { const budget = findMembership(userId)?.litellm_budget_table; - const schedule = describeBudgetResetSchedule(budget?.budget_duration ?? null, budget?.budget_reset_at ?? null); + return describeBudgetResetSchedule(budget?.budget_duration ?? null, budget?.budget_reset_at ?? null); + }; + + const renderBudgetPeriod = (userId: string | null) => { + const schedule = getUserBudgetSchedule(userId); return ( - {schedule.label} + {schedule.period ?? schedule.label} ); }; @@ -200,22 +204,22 @@ export default function TeamMemberTab({ { title: ( - Current Cycle Spend (USD) - - + Current Period Spend (USD) + + ), key: "spend", numeric: true, - sortValue: (record: Member) => getUserCurrentCycleSpend(record.user_id), - render: (record: Member) => , + sortValue: (record: Member) => getUserCurrentPeriodSpend(record.user_id), + render: (record: Member) => , }, { title: ( Total Spend (USD) - + @@ -263,10 +267,10 @@ export default function TeamMemberTab({ }, }, { - title: "Budget Reset", + title: "Budget Period", key: "budget_reset", sortValue: (record: Member) => getUserBudgetReset(record.user_id), - render: (record: Member) => renderBudgetReset(record.user_id), + render: (record: Member) => renderBudgetPeriod(record.user_id), }, { title: ( @@ -314,10 +318,12 @@ export default function TeamMemberTab({ const resetSpendDisabledReason = (member: Member): string | null => { if (!isProxyAdmin && member.user_id === userId) return "Ask a proxy admin to reset your own spend"; - if (getUserCurrentCycleSpend(member.user_id) <= 0) return "No current cycle spend to reset"; + if (getUserCurrentPeriodSpend(member.user_id) <= 0) return "No current period spend to reset"; return null; }; + const resetSpendPeriod = getUserBudgetSchedule(memberToResetSpend?.user_id ?? null).period; + return ( <> Reset Team Member Spend

- Reset current cycle spend for{" "} + Reset current period spend for{" "} {memberToResetSpend?.user_email || memberToResetSpend?.user_id} in this team to{" "} $0?

- Current cycle spend:{" "} - ${formatNumberWithCommas(getUserCurrentCycleSpend(memberToResetSpend?.user_id ?? null), 4)} + Current period spend + {resetSpendPeriod ? ` (${resetSpendPeriod})` : ""}:{" "} + + ${formatNumberWithCommas(getUserCurrentPeriodSpend(memberToResetSpend?.user_id ?? null), 4)} + . This is the value checked against the member's budget. Total spend and logs are preserved.

diff --git a/ui/litellm-dashboard/src/utils/budgetUtils.test.ts b/ui/litellm-dashboard/src/utils/budgetUtils.test.ts index e33c779bb65..11339d08bc5 100644 --- a/ui/litellm-dashboard/src/utils/budgetUtils.test.ts +++ b/ui/litellm-dashboard/src/utils/budgetUtils.test.ts @@ -2,6 +2,9 @@ import { afterEach, describe, expect, it } from "vitest"; import { budgetPeriodRange, describeBudgetResetSchedule, formatBudgetReset, formatBudgetResetUtc } from "./budgetUtils"; +const localIso = (year: number, monthIndex: number, day: number, hour = 12): string => + new Date(year, monthIndex, day, hour, 0, 0).toISOString(); + const originalTimezone: string | undefined = process.env.TZ; afterEach(() => { @@ -23,15 +26,18 @@ describe("formatBudgetResetUtc", () => { }); describe("describeBudgetResetSchedule", () => { - it("reports Never resets when the budget has no duration and no scheduled reset", () => { + it("reports lifetime spend with no period when the budget has no duration and no scheduled reset", () => { const schedule = describeBudgetResetSchedule(null, null); expect(schedule.label).toBe("Never resets"); expect(schedule.resetAt).toBeNull(); + expect(schedule.period).toBeNull(); + expect(schedule.tooltip).toContain("lifetime spend"); }); it("reports Unknown when a duration is set but no reset has been scheduled yet", () => { const schedule = describeBudgetResetSchedule("30d", null); expect(schedule.label).toBe("Unknown"); + expect(schedule.period).toBeNull(); expect(schedule.tooltip).toContain("every 30d"); }); @@ -41,7 +47,74 @@ describe("describeBudgetResetSchedule", () => { expect(schedule.label).toBe("Jul 15, 2026 12:00"); expect(schedule.resetAt).toBe(resetAt.toISOString()); expect(schedule.tooltip).toContain(Intl.DateTimeFormat().resolvedOptions().timeZone); - expect(schedule.tooltip).toContain("carries into the next cycle"); + expect(schedule.tooltip).toContain("carries into the next period"); + }); + + it("treats 30d as one calendar month back from the reset, like the proxy does", () => { + const schedule = describeBudgetResetSchedule("30d", localIso(2026, 10, 1, 0)); + expect(schedule.period).toBe("Oct 1 - Nov 1, 2026"); + expect(schedule.tooltip).toContain("covers Oct 1 - Nov 1, 2026 and resets every 30d"); + }); + + it("subtracts the exact duration for day and week windows", () => { + expect(describeBudgetResetSchedule("7d", localIso(2026, 6, 15)).period).toBe("Jul 8 - Jul 15, 2026"); + expect(describeBudgetResetSchedule("2w", localIso(2026, 6, 15)).period).toBe("Jul 1 - Jul 15, 2026"); + expect(describeBudgetResetSchedule("weekly", localIso(2026, 6, 15)).period).toBe("Jul 8 - Jul 15, 2026"); + }); + + it("walks the month back in UTC so a non-UTC viewer sees the proxy's window", () => { + const originalTz = process.env.TZ; + process.env.TZ = "America/New_York"; + try { + const schedule = describeBudgetResetSchedule("30d", "2026-03-01T00:00:00Z"); + expect(schedule.period).toBe("Jan 31 - Feb 28, 2026"); + } finally { + process.env.TZ = originalTz; + } + }); + + it("clamps month windows to the last day of a shorter month", () => { + expect(describeBudgetResetSchedule("1mo", localIso(2026, 2, 31)).period).toBe("Feb 28 - Mar 31, 2026"); + }); + + it("spells out both years when the period crosses a year boundary", () => { + expect(describeBudgetResetSchedule("30d", localIso(2027, 0, 10)).period).toBe("Dec 10, 2026 - Jan 10, 2027"); + }); + + it("keeps both clock times when an hourly window crosses midnight", () => { + expect(describeBudgetResetSchedule("1h", localIso(2026, 6, 16, 0)).period).toBe( + "Jul 15, 2026 23:00 - Jul 16, 2026 00:00", + ); + }); + + it("shows seconds for a window shorter than a minute", () => { + expect(describeBudgetResetSchedule("30s", localIso(2026, 6, 15)).period).toBe("Jul 15, 2026 11:59:30 - 12:00:00"); + }); + + it("shows clock times for a window that starts and ends on the same day", () => { + expect(describeBudgetResetSchedule("1h", localIso(2026, 6, 15)).period).toBe("Jul 15, 2026 11:00 - 12:00"); + }); + + it("falls back to a one day window for a duration the proxy would not recognise", () => { + expect(describeBudgetResetSchedule("fortnightly", localIso(2026, 6, 15)).period).toBe("Jul 14 - Jul 15, 2026"); + }); + + it("shows no period when the reset date is unparseable", () => { + const schedule = describeBudgetResetSchedule("30d", "not-a-date"); + expect(schedule.label).toBe("Unknown"); + expect(schedule.period).toBeNull(); + expect(schedule.tooltip).not.toMatch(/NaN|Invalid/); + }); + + it("never describes the window as a cycle", () => { + const schedules = [ + describeBudgetResetSchedule("30d", localIso(2026, 6, 15)), + describeBudgetResetSchedule("30d", null), + describeBudgetResetSchedule(null, null), + ]; + for (const schedule of schedules) { + expect(`${schedule.label} ${schedule.tooltip}`).not.toMatch(/cycle/i); + } }); }); diff --git a/ui/litellm-dashboard/src/utils/budgetUtils.ts b/ui/litellm-dashboard/src/utils/budgetUtils.ts index 23af15eb539..71638551f9f 100644 --- a/ui/litellm-dashboard/src/utils/budgetUtils.ts +++ b/ui/litellm-dashboard/src/utils/budgetUtils.ts @@ -1,4 +1,4 @@ -import dayjs from "dayjs"; +import dayjs, { Dayjs } from "dayjs"; import utc from "dayjs/plugin/utc"; dayjs.extend(utc); @@ -20,10 +20,55 @@ export function formatBudgetResetUtc(iso: string | null | undefined): string | n export interface BudgetResetSchedule { label: string; resetAt: string | null; + period: string | null; tooltip: string; } -const ROLLOVER_NOTE = "Spend above a rollover cap at reset carries into the next cycle."; +const ROLLOVER_NOTE = "Spend above a rollover cap at reset carries into the next period."; + +const DURATION_WORD_ALIASES: Record = { + hourly: "1h", + daily: "24h", + weekly: "7d", + monthly: "30d", +}; + +const DURATION_PATTERN = /^(\d+)(mo|[smhdw])$/; + +// Mirrors the proxy's get_budget_window_start: "30d" and "Nmo" span calendar months, +// everything else is a fixed length, and an unrecognised duration resets at the next midnight. +export function getBudgetPeriodStart(budgetDuration: string, resetAt: Dayjs): Dayjs { + const trimmed = budgetDuration.trim(); + const normalized = DURATION_WORD_ALIASES[trimmed.toLowerCase()] ?? trimmed; + const match = DURATION_PATTERN.exec(normalized); + if (!match) return resetAt.subtract(1, "day"); + const value = Number(match[1]); + switch (match[2]) { + case "mo": + return resetAt.subtract(value, "month"); + case "d": + return value === 30 ? resetAt.subtract(1, "month") : resetAt.subtract(value, "day"); + case "w": + return resetAt.subtract(value, "week"); + case "h": + return resetAt.subtract(value, "hour"); + case "m": + return resetAt.subtract(value, "minute"); + default: + return resetAt.subtract(value, "second"); + } +} + +export function formatBudgetPeriod(start: Dayjs, end: Dayjs): string { + const windowSeconds = end.diff(start, "second"); + if (windowSeconds < 24 * 60 * 60) { + const time = windowSeconds < 60 ? "HH:mm:ss" : "HH:mm"; + const endFormat = start.isSame(end, "day") ? time : `MMM D, YYYY ${time}`; + return `${start.format(`MMM D, YYYY ${time}`)} - ${end.format(endFormat)}`; + } + if (start.isSame(end, "year")) return `${start.format("MMM D")} - ${end.format("MMM D, YYYY")}`; + return `${start.format("MMM D, YYYY")} - ${end.format("MMM D, YYYY")}`; +} export function describeBudgetResetSchedule( budgetDuration: string | null | undefined, @@ -31,26 +76,33 @@ export function describeBudgetResetSchedule( ): BudgetResetSchedule { const resetDate = budgetResetAt ? dayjs(budgetResetAt) : null; if (resetDate?.isValid()) { - const cadence = budgetDuration ? `every ${budgetDuration}` : "on a schedule"; const timeZone = Intl.DateTimeFormat().resolvedOptions().timeZone; const label = resetDate.format("MMM D, YYYY HH:mm"); + const period = budgetDuration + ? formatBudgetPeriod(getBudgetPeriodStart(budgetDuration, resetDate.utc()).local(), resetDate) + : null; + const coverage = period + ? `Current Period Spend covers ${period} and resets every ${budgetDuration}.` + : "Current Period Spend resets on a schedule."; return { label, resetAt: resetDate.toISOString(), - tooltip: `Current Cycle Spend resets ${cadence}. Next reset ${label} (${timeZone}). ${ROLLOVER_NOTE}`, + period, + tooltip: `${coverage} Next reset ${label} (${timeZone}). ${ROLLOVER_NOTE}`, }; } if (!budgetDuration) { return { label: "Never resets", resetAt: null, - tooltip: - "This budget has no reset window, so Current Cycle Spend accumulates for as long as the membership exists.", + period: null, + tooltip: "This budget has no reset window, so this is lifetime spend for as long as the membership exists.", }; } return { label: "Unknown", resetAt: null, + period: null, tooltip: `Resets every ${budgetDuration}, but the next reset time has not been scheduled yet. ${ROLLOVER_NOTE}`, }; } From b5befe2dd0bb0899e5df8f05a20e9840609ada25 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Mon, 26 Oct 2026 17:54:32 -0700 Subject: [PATCH 025/262] test(routing): a team's wildcard serves its keys before a proxy-wide wildcard of the same pattern (#48501) Co-authored-by: joshua Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../routing/test_team_wildcard_precedence.py | 61 +++++++++++++++++++ 1 file changed, 61 insertions(+) create mode 100644 tests/integration/routing/test_team_wildcard_precedence.py diff --git a/tests/integration/routing/test_team_wildcard_precedence.py b/tests/integration/routing/test_team_wildcard_precedence.py new file mode 100644 index 00000000000..38fda682129 --- /dev/null +++ b/tests/integration/routing/test_team_wildcard_precedence.py @@ -0,0 +1,61 @@ +"""A team's own wildcard deployment serves that team's keys even when a proxy-wide wildcard of the +same pattern exists, and the proxy-wide one serves every other key (#48490).""" + +import uuid +from typing import Final + +import pytest +from integration._support.client import Gateway, Scenario + +pytestmark: Final = pytest.mark.timeout(120) + + +def _wildcard(scenario: Scenario, pattern: str, *, team_id: str | None) -> str: + identity: Final = f"wildcard-{uuid.uuid4().hex}" + scenario.gateway.post( + "/model/new", + { + "model_name": pattern, + "litellm_params": { + "model": "openai/*", + "api_key": f"provider-key-{identity}", + "api_base": f"{scenario.gateway.upstream_url}/v1", + }, + "model_info": {"id": identity, **({"team_id": team_id} if team_id is not None else {})}, + }, + ) + scenario.cleanups.callback(scenario.delete_model, identity) + return identity + + +def _served_by(gateway: Gateway, key: str, model: str) -> str: + response: Final = gateway.request( + "POST", + "/v1/chat/completions", + {"model": model, "messages": [{"role": "user", "content": "wildcard precedence control"}]}, + key=key, + ) + assert response.status_code == 200, response.text + return response.headers["x-litellm-model-id"] + + +def test_a_teams_wildcard_serves_its_keys_before_a_proxy_wide_wildcard_of_the_same_pattern(gateway: Gateway) -> None: + with gateway.scenario() as scenario: + byok_team: Final = scenario.team(models=[]) + other_team: Final = scenario.team(models=[]) + pattern: Final = f"byok-{uuid.uuid4().hex}/*" + team_wildcard: Final = _wildcard(scenario, pattern, team_id=byok_team) + shared_wildcard: Final = _wildcard(scenario, pattern, team_id=None) + model: Final = pattern.replace("*", "gpt-4o-mini") + + served: Final = { + "byok team key": _served_by(gateway, scenario.key(team_id=byok_team), model), + "other team key": _served_by(gateway, scenario.key(team_id=other_team), model), + "key without a team": _served_by(gateway, scenario.key(), model), + } + + assert served == { + "byok team key": team_wildcard, + "other team key": shared_wildcard, + "key without a team": shared_wildcard, + } From 715e9bb08d7567d58beebff640a7b32c4370342d Mon Sep 17 00:00:00 2001 From: yucheng-berri Date: Mon, 26 Oct 2026 17:57:06 -0700 Subject: [PATCH 026/262] fix(prometheus): count provider-side 401s in LLM failure and deployment metrics (#46668) * fix(prometheus): count provider-side 401s in LLM failure and deployment metrics The invalid virtual key skip no longer applies to an error the LLM provider returned while the deployment was called with its own credential, so a 401 for a bad deployment credential increments litellm_llm_api_failed_requests_metric, litellm_deployment_failure_responses and litellm_deployment_total_requests and marks litellm_deployment_state as a partial outage again. Proxy-gate rejections and a failing credential that belongs to the caller (a rejected per-user credential, an api_key sent with the request, a per-user GitHub Copilot session) keep the skip * fix(prometheus): keep a caller's own Anthropic OAuth token failure out of the deployment metrics A provider 401 on an Anthropic OAuth token the caller forwarded through the proxy is the caller's credential failing, so it stays out of the deployment failure and outage series like a caller-supplied api_key. Adds integration cells for an Anthropic deployment's own key, the forwarded caller OAuth token and a direct SDK call that brings its own key * test(prometheus): pin how a caller's own key or Authorization header on a deployment is counted An SDK Router call that passes its own api_key is counted against the one-off deployment the router builds for that key, so the operator deployment keeps only its own failure. A provider 401 on an Authorization header the caller sends through the proxy counts against the deployment, as on v1.80.12 * fix(prometheus): keep caller-sent provider credentials and token-exchange 401s out of deployment metrics A caller can send its own provider credential in the request body, such as azure_ad_token, azure_scope, the Azure Entra app fields, watsonx token, gigachat_access_token, OCI keys, AWS keys or Vertex credentials, at the top level or inside extra_body. A provider 401 on that credential is the caller's failure, so it stays out of the shared deployment's failure, request, LLM-failed and state series, as on main. A token-exchange deployment trades the caller's identity token on every call, so its 401s stay out as well, matching the router cooldown. * test(prometheus): Final locals, precise helper types and one for per comprehension in the new test helpers * test(prometheus): pin that a provider 401 at a caller-sent api_base counts against its one-off deployment * fix(prometheus): keep a provider 401 on caller-sent headers out of deployment metrics A caller can override the deployment's credential with headers it sends in the request body: headers or provider_specific_header, or an Authorization, api-key, x-api-key, x-goog-api-key or Ocp-Apim-Subscription-Key entry in extra_headers. A provider 401 on such a request is the caller's failure, so it stays out of the shared deployment's failure, request, LLM-failed and state series, as on main. * fix(prometheus): skip a provider 401 only when the caller's headers carry a credential The proxy now records headers, extra_headers or provider_specific_header in credential_fields only when they name a provider credential header (Authorization, api-key, x-api-key, x-goog-api-key, Ocp-Apim-Subscription-Key), the same way api_key is recorded. A caller that sends a plain header such as a trace id still has a provider 401 on the deployment's own key counted against the deployment. * fix(prometheus): stamp credential_fields after the proxy forwards the caller's headers A provider credential header the proxy forwards from the caller's HTTP request (forward_llm_provider_auth_headers + forward_client_headers_to_llm_api) lands in data["headers"] after proxy_server_request is built, so the stamp missed it and a 401 on that caller credential was counted against the deployment. Compute the stamp after the header forwarding steps and pin both forwarded cases. * fix(prometheus): skip a provider 401 when the caller sends any header or an OpenAI organization The proxy now records headers, extra_headers or provider_specific_header in credential_fields whenever the caller sends or the proxy forwards any header there, and records organization when the caller sends one in the body or as a forwarded OpenAI-Organization header. A forwarded header can be a gateway key such as x-portkey-api-key or an OpenAI-Project id, and a wrong organization gets a 401 from OpenAI, so these 401s stay out of the deployment metrics as on main instead of marking a healthy deployment as a partial outage. * fix(prometheus): ignore the user information the proxy adds when stamping caller headers With add_user_information_to_llm_headers on and header forwarding enabled, the proxy adds x-litellm-user_api_key_* headers to the forwarded headers. Those carry the proxy's own key and user details, not the caller's, so they no longer make a request look caller-scoped, and a provider 401 on the deployment's own key on such a request is counted. * fix(prometheus): skip a 401 raised before the provider is called or at the caller's own endpoint A deployment with no key of its own fails with LiteLLM's local "Missing Anthropic API Key" 401 before any provider call, and a caller who sends aws_bedrock_runtime_endpoint (or another provider endpoint field) can get a 401 from their own gateway. Both were counted against the shared deployment and marked it as a partial outage, where main skipped every 401. Count a 401 only once the provider was called (api_call_start_time is set), and treat caller-sent provider endpoint fields like caller credential fields. * fix(prometheus): count the deployment's own 401 on requests that carry only anthropic-version or anthropic-beta The Anthropic SDK sends anthropic-version on every request, and the proxy copies anthropic-version and anthropic-beta into provider_specific_header for Anthropic, Bedrock and Vertex. Both were treated as caller headers, so a 401 on an Anthropic deployment's own key from any Anthropic SDK client stayed out of the deployment metrics. These two headers only pick the API version and beta features. Anthropic answers a bad anthropic-version or an unknown anthropic-beta with a 400, never a 401, so they cannot turn the deployment's own key into a 401 and no longer mark the request as carrying a caller header. * test(prometheus): read and write the owned proxy's own database in the expired-key and MCP cells Since #47213 an owned proxy boots on a private database, so the expired-key update and the MCP guardrail row read now go through the gateway's database_url instead of the worker's. * fix(prometheus): keep credential_fields as main stamps it and give Prometheus its own caller_credential_fields credential_fields tells the Rust OCR bridge which stripped body fields the caller sent. Repurposing it for the Prometheus caller-credential check changed its value (organization and extra_headers added, anthropic-version-only headers dropped). Restore main's stamp unchanged and stamp the Prometheus classification under caller_credential_fields, which only Prometheus reads. * fix(prometheus): skip a provider 401 on a stored credential the caller picks by litellm_credential_name A request body litellm_credential_name swaps the deployment's stored credential for one the caller chose, so a 401 on it is the caller's, not the deployment's. Treat it like the other caller credential fields so it no longer marks a healthy shared deployment as a partial outage. --------- Co-authored-by: yucheng-berri <293926326+yucheng-berri@users.noreply.github.com> --- litellm/integrations/prometheus.py | 97 +- litellm/proxy/litellm_pre_call_utils.py | 45 + .../copilot_session_prometheus_worker.py | 162 +++ .../test_prometheus_provider_auth_failure.py | 1074 +++++++++++++++++ ..._prometheus_provider_auth_failure_chaos.py | 147 +++ ...etheus_copilot_session_auth_failure_sdk.py | 99 ++ .../test_prometheus_invalid_key_filtering.py | 441 ++++++- .../unit/proxy/test_litellm_pre_call_utils.py | 216 ++++ 8 files changed, 2220 insertions(+), 61 deletions(-) create mode 100644 tests/integration/_support/copilot_session_prometheus_worker.py create mode 100644 tests/integration/observability/test_prometheus_provider_auth_failure.py create mode 100644 tests/integration/observability/test_prometheus_provider_auth_failure_chaos.py create mode 100644 tests/integration/sdk/test_prometheus_copilot_session_auth_failure_sdk.py diff --git a/litellm/integrations/prometheus.py b/litellm/integrations/prometheus.py index 19d161b8aa4..bc8344fa686 100644 --- a/litellm/integrations/prometheus.py +++ b/litellm/integrations/prometheus.py @@ -14,6 +14,7 @@ from functools import partial from types import MappingProxyType from typing import TYPE_CHECKING, Annotated, Any, Final, Literal, Protocol, TypeAlias, TypeVar, cast +import openai from pydantic import BaseModel, Field, TypeAdapter, ValidationError from typing_extensions import ReadOnly, TypedDict, assert_never @@ -22,11 +23,13 @@ from litellm._internal_context import with_service_target from litellm._logging import print_verbose, verbose_logger from litellm.constants import ( AUTH_OBJECTS_TARGET, + LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL, PROMETHEUS_OVERFLOW_SERIES_LABEL_VALUE, PROXY_LLM_PROVIDER_FALLBACK, PROXY_REJECTED_BEFORE_ROUTING_KEY, ) from litellm.exceptions import ( + CallerCredentialAuthenticationError, MalformedRequestFieldError, validate_rate_limit_category, validate_rate_limit_type, @@ -51,6 +54,7 @@ from litellm.litellm_core_utils.get_llm_provider_logic import is_registered_cust from litellm.litellm_core_utils.service_tier_utils import ( get_service_tier_from_standard_logging_payload, ) +from litellm.llms.github_copilot.per_user_auth import github_copilot_user_session_from from litellm.llms.openai_like.json_loader import JSONProviderRegistry from litellm.models.end_user import LiteLLM_EndUserTable from litellm.models.team import LiteLLM_TeamTable @@ -269,7 +273,10 @@ _NO_LOGGED_FIELDS: Final[Mapping[str, object]] = MappingProxyType({}) def _logged_fields(value: object) -> Mapping[str, object]: - return _LOGGED_FIELDS.validate_python(value) if isinstance(value, Mapping) else _NO_LOGGED_FIELDS + try: + return _LOGGED_FIELDS.validate_python(value) + except ValidationError: + return _NO_LOGGED_FIELDS def _is_llm_provider(name: str) -> bool: @@ -359,6 +366,87 @@ def _get_proxy_llm_router() -> Router | None: return llm_router +_CALLER_CREDENTIAL_FIELDS: Final = frozenset( + { + "aws_access_key_id", + "aws_secret_access_key", + "aws_session_token", + "aws_web_identity_token", + "azure_ad_token", + "azure_password", + "azure_scope", + "azure_username", + "client_id", + "client_secret", + "gigachat_access_token", + "litellm_credential_name", + "oci_fingerprint", + "oci_key", + "oci_key_file", + "oci_tenancy", + "oci_user", + "tenant_id", + "token", + "user_config", + "vertex_ai_credentials", + "vertex_credentials", + "watsonx_credentials", + "wx_credentials", + "zen_api_key", + } +) + + +_CALLER_ENDPOINT_FIELDS: Final = frozenset( + {"aws_bedrock_runtime_endpoint", "aws_sts_endpoint", "deployment_url", "s3_endpoint_url", "sagemaker_base_url"} +) + + +_CALLER_TRANSPORT_FIELDS: Final = frozenset( + {"api_key", "extra_headers", "headers", "organization", "provider_specific_header"} +) + + +def _sent_a_provider_credential_or_endpoint(caller_body: Mapping[str, object]) -> bool: + """True when the caller's request body, or its ``extra_body``, carries a provider credential field or a + provider endpoint field.""" + sent: Final = {*caller_body, *_logged_fields(caller_body.get("extra_body"))} + return not (_CALLER_CREDENTIAL_FIELDS.isdisjoint(sent) and _CALLER_ENDPOINT_FIELDS.isdisjoint(sent)) + + +def _used_a_caller_credential(logged_call: Mapping[str, object]) -> bool: + """True when the provider was called with a credential or at an endpoint that belongs to the caller rather than + the deployment: an api_key, header, OpenAI organization or other provider credential or endpoint field the caller + sent with the request, a stored credential the caller picked by name, the caller's own Anthropic OAuth token, the caller's own GitHub Copilot connection, or the + caller's identity token that a token-exchange deployment trades in on every call.""" + litellm_params: Final = _logged_fields(logged_call.get("litellm_params")) + proxy_server_request: Final = _logged_fields(litellm_params.get("proxy_server_request")) + caller_credential_fields: Final = proxy_server_request.get("caller_credential_fields") + logged_metadata: Final = _logged_fields(_logged_fields(logged_call.get("standard_logging_object")).get("metadata")) + return ( + ( + isinstance(caller_credential_fields, tuple) + and any(field in caller_credential_fields for field in _CALLER_TRANSPORT_FIELDS) + ) + or _sent_a_provider_credential_or_endpoint(_logged_fields(proxy_server_request.get("body"))) + or bool(litellm_params.get("token_exchange_endpoint")) + or logged_metadata.get("used_client_oauth_token") is True + or github_copilot_user_session_from(litellm_params) is not None + ) + + +def _is_deployment_failure(exception: openai.APIError, logged_call: Mapping[str, object]) -> bool: + """True for an error raised while calling the deployment with its own credential, on a request the proxy + did not reject itself. An error LiteLLM raises before it calls the provider, such as a missing deployment key, + is not one.""" + return not ( + isinstance(exception, CallerCredentialAuthenticationError) + or bool(logged_call.get(LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL)) + or logged_call.get("api_call_start_time") is None + or _used_a_caller_credential(logged_call) + ) + + def _bounded_requested_model_label(requested_model: object, router_originated: bool = False) -> str | None: """ Bound ``requested_model`` label cardinality: names the router recognizes @@ -2817,6 +2905,8 @@ class PrometheusLogger(CustomLogger): information from various callback function signatures and determines if the request represents an invalid API key attempt that should be filtered from metrics. + An error raised while calling the deployment with its own credential is never skipped. + Args: kwargs: Dictionary potentially containing exception and other data user_api_key_dict: User API key authentication object (currently unused) @@ -2836,6 +2926,11 @@ class PrometheusLogger(CustomLogger): if exception is None and kwargs: exception = kwargs.get("exception") + if isinstance(exception, openai.APIError) and _is_deployment_failure( + exception, _LOGGED_FIELDS.validate_python(kwargs or {}) + ): + return False + if self._is_invalid_api_key_request(status_code, exception=exception): verbose_logger.debug( "Skipping Prometheus metrics for invalid API key request: status_code=%s, exception=%s", diff --git a/litellm/proxy/litellm_pre_call_utils.py b/litellm/proxy/litellm_pre_call_utils.py index b51eea7a876..5f1948d1c1c 100644 --- a/litellm/proxy/litellm_pre_call_utils.py +++ b/litellm/proxy/litellm_pre_call_utils.py @@ -99,6 +99,8 @@ _CREDENTIAL_HEADER_NAMES: Final = SpecialHeaders.litellm_credential_header_names {"cookie", "proxy-authorization"} ) _TRANSPORT_ONLY_CREDENTIAL_KEYS: Final = frozenset({"provider_specific_header", "headers", "api_key"}) +_REQUEST_FIELDS: Final = TypeAdapter(Mapping[str, object]) +_REQUEST_ENTRIES: Final = TypeAdapter(tuple[object, ...]) # Matches any header of the form x--session-id (case-insensitive). # Excludes the two explicit litellm headers which are handled with higher priority. @@ -289,6 +291,9 @@ _DESTINATION_ONLY_CALLBACK_VARS: Final[frozenset[str]] = frozenset({CAPTURE_MESS _CALLBACK_CREDENTIAL_KEYS: Final = frozenset(StandardCallbackDynamicParams.__annotations__) | frozenset( {TRUSTED_CALLBACK_VARS_FIELD} ) +_HEADERS_THAT_CANNOT_CHANGE_PROVIDER_AUTH: Final = frozenset( + {*(f"x-litellm-{key}" for key in StandardLoggingUserAPIKeyMetadata.__annotations__), *ANTHROPIC_API_HEADERS} +) service_logger_obj: Final = ServiceLogging() # used for tracking latency on OTEL # Bounded dedup for stale-alias warnings (FIFO eviction when over cap). _MAX_STALE_ALIAS_WARNING_KEYS: Final = 10_000 @@ -1451,6 +1456,44 @@ def clean_headers( return clean_headers +def _request_fields(value: object) -> Mapping[str, object]: + try: + return _REQUEST_FIELDS.validate_python(value) + except PydanticValidationError: + return MappingProxyType({}) + + +def _request_entries(value: object) -> tuple[object, ...]: + if value is None: + return () + try: + return _REQUEST_ENTRIES.validate_python(value) + except PydanticValidationError: + return (value,) + + +def _carries_a_caller_header(headers: object) -> bool: + return any(name.lower() not in _HEADERS_THAT_CANNOT_CHANGE_PROVIDER_AUTH for name in _request_fields(headers)) + + +def _caller_credential_fields(data: Mapping[str, object]) -> tuple[str, ...]: + """Names of the request fields through which the caller can change how the provider authenticates the call: + ``api_key``, ``organization``, and ``headers``, ``extra_headers`` or a ``provider_specific_header`` entry's + ``extra_headers`` that carry any header besides the key and user details the proxy adds under + ``add_user_information_to_llm_headers`` and the ``anthropic-version`` and ``anthropic-beta`` headers.""" + carried: Final = { + "api_key": "api_key" in data, + "extra_headers": _carries_a_caller_header(data.get("extra_headers")), + "headers": _carries_a_caller_header(data.get("headers")), + "organization": "organization" in data, + "provider_specific_header": any( + _carries_a_caller_header(_request_fields(entry).get("extra_headers")) + for entry in _request_entries(data.get("provider_specific_header")) + ), + } + return tuple(name for name, sent in sorted(carried.items()) if sent) + + def _is_credential_header(header: str) -> bool: """Whether `header` carries a caller credential rather than request context.""" return header.lower().removeprefix("x-pass-") in _CREDENTIAL_HEADER_NAMES @@ -2605,6 +2648,8 @@ async def add_litellm_data_to_request( data[_metadata_variable_name]["used_client_oauth_token"] = add_provider_specific_headers_to_request( data=data, headers=_headers ) + caller_fields: Final = _caller_credential_fields(_REQUEST_FIELDS.validate_python(data)) + data["proxy_server_request"]["caller_credential_fields"] = caller_fields # rebind-ok: data is an out-param ## Cache Controls cache_control_header: Final = _headers.get("Cache-Control", None) diff --git a/tests/integration/_support/copilot_session_prometheus_worker.py b/tests/integration/_support/copilot_session_prometheus_worker.py new file mode 100644 index 00000000000..a6b2c5d4692 --- /dev/null +++ b/tests/integration/_support/copilot_session_prometheus_worker.py @@ -0,0 +1,162 @@ +"""One SDK process for the SDK provider-401 metric cells: a provider 401 on a caller's own Copilot session, one on +the router deployment's own key, one on a key the router caller passes and one on a direct call's own key, then a +report of the deployment series on that process's default registry. Run as a script by ``run_copilot_session_worker`` so each process registers the +Prometheus metrics exactly once.""" + +from __future__ import annotations + +import asyncio +import json +import subprocess +import sys +from itertools import chain +from dataclasses import dataclass +from typing import Final + +import litellm +import openai +from litellm.integrations.prometheus import PrometheusLogger +from litellm.llms.github_copilot.per_user_auth import GithubCopilotUserSession +from prometheus_client import REGISTRY +from pydantic import TypeAdapter + +COPILOT_DEPLOYMENT: Final = "copilot-per-user-deployment" +OPERATOR_DEPLOYMENT: Final = "operator-key-deployment" +CALLER_SESSION_TOKEN: Final = "caller-copilot-session-token" +OPERATOR_KEY: Final = "rotated-operator-key" +ROUTER_CALLER_KEY: Final = "rotated-router-caller-key" +DIRECT_CALL: Final = "direct-sdk-call" +DIRECT_KEY: Final = "rotated-direct-call-key" +FAILURES: Final = "litellm_deployment_failure_responses_total" +TOTALS: Final = "litellm_deployment_total_requests_total" +LLM_FAILED: Final = "litellm_llm_api_failed_requests_metric_total" +STATE: Final = "litellm_deployment_state" +DEPLOYMENT_SERIES: Final = frozenset({FAILURES, TOTALS, LLM_FAILED, STATE}) +WORKER_TIMEOUT_SECONDS: Final = 120 + + +@dataclass(frozen=True, slots=True) +class Outcome: + deployment: str + status: int | None + + +@dataclass(frozen=True, slots=True) +class Series: + metric: str + model_id: str + api_base: str + value: float + + +@dataclass(frozen=True, slots=True) +class WorkerReport: + api_base: str + outcomes: tuple[Outcome, ...] + series: tuple[Series, ...] + + def values(self, metric: str, model_id: str) -> tuple[float, ...]: + return tuple(s.value for s in self.series if s.metric == metric and s.model_id == model_id) + + def on_the_endpoint(self, metric: str, model_id: str) -> tuple[float, ...]: + return tuple( + s.value for s in self.series if (s.metric, s.model_id, s.api_base) == (metric, model_id, self.api_base) + ) + + def outside_the_router(self, metric: str) -> tuple[float, ...]: + return tuple(s.value for s in self.series if s.metric == metric and not s.model_id) + + def on_a_one_off_deployment(self, metric: str) -> tuple[float, ...]: + named_ids: Final = ("", COPILOT_DEPLOYMENT, OPERATOR_DEPLOYMENT) + return tuple(s.value for s in self.series if s.metric == metric and s.model_id not in named_ids) + + +_REPORT: Final = TypeAdapter(WorkerReport) + + +def run_copilot_session_worker(api_base: str) -> WorkerReport: + completed: Final = subprocess.run( + (sys.executable, "-P", __file__, api_base), + capture_output=True, + text=True, + timeout=WORKER_TIMEOUT_SECONDS, + check=False, + ) + assert completed.returncode == 0, completed.stderr[-3000:] + return _REPORT.validate_json(completed.stdout.splitlines()[-1]) + + +def _deployment_series() -> tuple[Series, ...]: + samples: Final = tuple(chain.from_iterable(family.samples for family in REGISTRY.collect())) + return tuple( + Series( + metric=sample.name, + model_id=str(sample.labels.get("model_id", "")), + api_base=str(sample.labels.get("api_base", "")), + value=float(sample.value), + ) + for sample in samples + if sample.name in DEPLOYMENT_SERIES + ) + + +def _router(api_base: str) -> litellm.Router: + return litellm.Router( + model_list=[ + { + "model_name": COPILOT_DEPLOYMENT, + "litellm_params": { + "model": "github_copilot/gpt-4o", + "litellm_credential_name": "copilot-per-user", + "github_copilot_auth_type": "per_user_oauth", + }, + "model_info": {"id": COPILOT_DEPLOYMENT}, + }, + { + "model_name": OPERATOR_DEPLOYMENT, + "litellm_params": {"model": "openai/gpt-5.6", "api_base": api_base, "api_key": OPERATOR_KEY}, + "model_info": {"id": OPERATOR_DEPLOYMENT}, + }, + ], + num_retries=0, + disable_cooldowns=True, + ) + + +async def _attempt(router: litellm.Router, model: str, **extra: object) -> Outcome: + try: + await router.acompletion(model=model, messages=[{"role": "user", "content": f"{model} worker"}], **extra) + except openai.APIStatusError as error: + return Outcome(deployment=model, status=error.status_code) + return Outcome(deployment=model, status=None) + + +async def _direct_attempt(api_base: str) -> Outcome: + try: + await litellm.acompletion( + model="openai/gpt-5.6", + api_base=api_base, + api_key=DIRECT_KEY, + messages=[{"role": "user", "content": f"{DIRECT_CALL} worker"}], + ) + except openai.APIStatusError as error: + return Outcome(deployment=DIRECT_CALL, status=error.status_code) + return Outcome(deployment=DIRECT_CALL, status=None) + + +async def main(api_base: str) -> None: + litellm.callbacks = [PrometheusLogger()] # test-quality-ok: this worker process exits right after the report + session: Final = GithubCopilotUserSession(token=CALLER_SESSION_TOKEN, api_base=api_base) + router: Final = _router(api_base) + outcomes: Final = ( + await _attempt(router, COPILOT_DEPLOYMENT, github_copilot_user_session=session), + await _attempt(router, OPERATOR_DEPLOYMENT), + await _attempt(router, OPERATOR_DEPLOYMENT, api_key=ROUTER_CALLER_KEY), + await _direct_attempt(api_base), + ) + report: Final = WorkerReport(api_base=api_base, outcomes=outcomes, series=_deployment_series()) + sys.stdout.write(json.dumps(_REPORT.dump_python(report)) + "\n") + + +if __name__ == "__main__": + asyncio.run(main(sys.argv[1])) diff --git a/tests/integration/observability/test_prometheus_provider_auth_failure.py b/tests/integration/observability/test_prometheus_provider_auth_failure.py new file mode 100644 index 00000000000..13d264ca6b0 --- /dev/null +++ b/tests/integration/observability/test_prometheus_provider_auth_failure.py @@ -0,0 +1,1074 @@ +from __future__ import annotations + +import asyncio +import json +import threading +import uuid +from collections import Counter +from collections.abc import Iterator, Sequence +from dataclasses import dataclass +from hashlib import sha256 +from pathlib import Path +from typing import Final + +import httpx +import openai +import pytest +import yaml +from integration._support.client import Gateway, Scenario, eventually, gateway_from_environment +from integration._support.database import write_rows +from integration._support.mcp import ENTRY_POINTS, McpCaller, McpPeer, echo_tool, register_mcp, scripted_peer +from integration._support.process import owned_proxy +from integration._support.prometheus_series import Sample, scrape +from integration._support.wire import Reply, Request, Wire, wire_server +from pydantic import JsonValue + +RUN: Final = uuid.uuid4().hex[:8] +REJECTS: Final = "provider-rejects-credential" +HELD_REJECTS: Final = "provider-rejects-credential-when-released" +KEY_NOT_VALID: Final = "provider-key-not-valid" +RATE_LIMITS: Final = "provider-rate-limits" +RECOVERS: Final = "provider-rejects-once" +HEALTHY: Final = "provider-healthy" +AGENT_365_GUARDRAIL: Final = f"agent-365-{RUN}" +CALLER_OAUTH_TOKEN: Final = f"sk-ant-oat01-caller-{RUN}" +REVOKED_GATEWAY_KEY: Final = f"revoked-gateway-key-{RUN}" +UNKNOWN_ORGANIZATION: Final = f"org-unknown-{RUN}" +REVOKED_STORED_KEY: Final = f"sk-revoked-stored-credential-{RUN}" +AZURE_API_VERSION: Final = "2024-02-01" +CALLER_AZURE_CELLS: Final = ( + ("chat", False), + ("embeddings", False), + ("responses", False), + ("messages", False), + ("responses", True), +) +CALLER_CREDENTIAL_CELLS: Final = ( + ("caller-watsonx-token", "token"), + ("caller-gigachat-access-token", "gigachat_access_token"), +) +TOKEN_EXCHANGE_CELLS: Final = ("token-exchange", "token-exchange-credential") +KEYLESS_CELLS: Final = ("keyless", "messages-keyless") +TOKEN_EXCHANGE_SETTINGS: Final = { + "token_exchange_endpoint": "https://login.microsoftonline.com/00000000-0000-4000-8000-0000000c0b01/oauth2/v2.0/token", + "client_id": "synthetic-obo-client-id", + "client_secret": "synthetic-obo-client-secret", +} + +FAILURES: Final = "litellm_deployment_failure_responses_total" +TOTALS: Final = "litellm_deployment_total_requests_total" +LLM_FAILED: Final = "litellm_llm_api_failed_requests_metric_total" +STATE: Final = "litellm_deployment_state" +PROXY_FAILED: Final = "litellm_proxy_failed_requests_metric_total" +SUCCESSES: Final = "litellm_deployment_success_responses_total" +DEPLOYMENT_SERIES: Final = (FAILURES, TOTALS, LLM_FAILED, STATE) + +ENDPOINT_CELLS: Final = ( + "chat", + "chat-stream", + "messages", + "messages-stream", + "responses", + "responses-stream", + "embeddings", +) +REJECTED_CELLS: Final = ( + *ENDPOINT_CELLS, + "sdk-sync", + "sdk-async", + "repeated", + "fallback", + "burst", + "caller-api-key", + "caller-extra-headers", + "caller-headers", + "caller-provider-specific-header", + "plain-extra-headers", + "plain-headers", + "plain-provider-specific-header", + "forwarded-provider-header", + "forwarded-plain-header", + "forwarded-user-information", +) +GATED_CELLS: Final = ("invalid-key", "missing-key", "expired-key", "blocked-key", "no-model-access") +CALLER_SCOPE_CELLS: Final = ("forwarded-gateway-key", "caller-organization", "forwarded-organization") +HEALTHY_CELLS: Final = (*GATED_CELLS, *CALLER_SCOPE_CELLS, "healthy", "key-rpm-limit") +GUARDRAIL_ROWS: Final = ( + "SELECT COALESCE(jsonb_path_query_first(metadata, " + "'$.guardrail_information[*] ? (@.guardrail_name == $name).guardrail_status', " + "jsonb_build_object('name', %s::text)) #>> '{}', 'none') AS status " + 'FROM "LiteLLM_SpendLogs" WHERE api_key = %s AND call_type = %s' +) + + +def name(cell: str) -> str: + return f"prometheus-{cell}-{RUN}" + + +def identity(cell: str) -> str: + return f"{name(cell)}-deployment" + + +def _error(status: int, message: str, kind: str, code: str) -> Reply: + return Reply(status=status, body=json.dumps({"error": {"message": message, "type": kind, "code": code}}).encode()) + + +def _completion() -> Reply: + return Reply( + body=json.dumps( + { + "id": f"chatcmpl-{uuid.uuid4().hex}", + "object": "chat.completion", + "created": 1, + "model": "gpt-4o-mini", + "choices": [{"index": 0, "message": {"role": "assistant", "content": "ok"}, "finish_reason": "stop"}], + "usage": {"prompt_tokens": 3, "completion_tokens": 1, "total_tokens": 4}, + } + ).encode() + ) + + +class Provider: + """Answers by upstream model name. `HELD_REJECTS` waits for `release` before rejecting the credential.""" + + def __init__(self, release: threading.Event) -> None: + self._lock: Final = threading.Lock() + self._seen: Final[Counter[str]] = Counter() + self._release: Final = release + + def __call__(self, request: Request) -> Reply: + sent: Final = json.loads(request.body) + model: Final = str(sent.get("model") or sent.get("model_id") or request.target.split("/")[2]) + if request.headers.get("x-portkey-api-key") == REVOKED_GATEWAY_KEY: + return _error(401, "Invalid gateway API key", "invalid_request_error", "invalid_api_key") + if request.headers.get("authorization") == f"Bearer {REVOKED_STORED_KEY}": + return _error(401, "Incorrect API key provided: sk-revok*****", "invalid_request_error", "invalid_api_key") + if request.headers.get("openai-organization") == UNKNOWN_ORGANIZATION: + return _error( + 401, + "OpenAI-Organization header should match organization for API key", + "invalid_request_error", + "mismatched_organization", + ) + with self._lock: + self._seen[model] += 1 + attempt: Final = self._seen[model] + if model == HELD_REJECTS: + assert self._release.wait(timeout=30), "held provider reply was never released" + if model in (REJECTS, HELD_REJECTS) or (model == RECOVERS and attempt == 1): + return _error(401, "Incorrect API key provided: sk-rotat*****", "invalid_request_error", "invalid_api_key") + if model == KEY_NOT_VALID: + return _error(400, "API key not valid. Please pass a valid API key.", "invalid_request_error", "400") + if model == RATE_LIMITS: + return _error(429, "Rate limit reached for requests", "rate_limit_error", "rate_limit_exceeded") + return _completion() + + +def deployment(cell: str, upstream_model: str, api_base: str) -> dict[str, JsonValue]: + return { + "model_name": name(cell), + "litellm_params": { + "model": f"openai/{upstream_model}", + "api_key": f"sk-deployment-credential-{cell}", + "api_base": api_base, + }, + "model_info": {"id": identity(cell)}, + } + + +def anthropic_deployment(cell: str, api_base: str) -> dict[str, JsonValue]: + return { + "model_name": name(cell), + "litellm_params": { + "model": f"anthropic/{REJECTS}", + "api_key": f"sk-ant-api03-deployment-credential-{cell}", + "api_base": api_base, + }, + "model_info": {"id": identity(cell)}, + } + + +def bedrock_deployment(cell: str, opt_in: dict[str, JsonValue]) -> dict[str, JsonValue]: + return { + "model_name": name(cell), + "litellm_params": { + "model": f"bedrock/converse/{REJECTS}", + "aws_access_key_id": "AKIADEPLOYMENTCREDENTIAL", + "aws_secret_access_key": f"deployment-credential-{cell}", + "aws_region_name": "us-east-1", + **opt_in, + }, + "model_info": {"id": identity(cell)}, + } + + +def keyless_anthropic_deployment(cell: str, api_base: str) -> dict[str, JsonValue]: + return { + "model_name": name(cell), + "litellm_params": {"model": f"anthropic/{REJECTS}", "api_base": api_base}, + "model_info": {"id": identity(cell)}, + } + + +def azure_deployment(cell: str, api_base: str, credential: dict[str, JsonValue]) -> dict[str, JsonValue]: + return { + "model_name": name(cell), + "litellm_params": { + "model": f"azure/{REJECTS}", + "api_base": api_base, + "api_version": AZURE_API_VERSION, + **credential, + }, + "model_info": {"id": identity(cell)}, + } + + +def caller_credential_deployment(cell: str, field: str, api_base: str) -> dict[str, JsonValue]: + provider: Final = "watsonx" if field == "token" else "gigachat" + project: Final[dict[str, JsonValue]] = {"project_id": f"project-{RUN}"} if provider == "watsonx" else {} + return { + "model_name": name(cell), + "litellm_params": { + "model": f"{provider}/{REJECTS}", + "api_base": api_base, + field: f"deployment-credential-{cell}", + **project, + }, + "model_info": {"id": identity(cell)}, + } + + +def token_exchange_deployment(cell: str) -> dict[str, JsonValue]: + settings: Final[dict[str, JsonValue]] = ( + {"litellm_credential_name": f"m365-obo-{RUN}"} if cell.endswith("-credential") else {**TOKEN_EXCHANGE_SETTINGS} + ) + return { + "model_name": name(cell), + "litellm_params": {"model": "microsoft_365_copilot/chat", **settings}, + "model_info": {"id": identity(cell)}, + } + + +def caller_azure_cell(opt_in: str, route: str, inside_extra_body: bool) -> str: + return f"{opt_in}-caller-azure-token-{route}{'-extra-body' if inside_extra_body else ''}" + + +def config(directory: Path, upstream: Wire) -> Path: + api_base: Final = f"{upstream.url}/v1" + configuration: Final = yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text()) + configuration["model_list"] = [ + *configuration["model_list"], + *(deployment(cell, REJECTS, api_base) for cell in REJECTED_CELLS), + *(deployment(cell, HEALTHY, api_base) for cell in HEALTHY_CELLS), + deployment("held", HELD_REJECTS, api_base), + deployment("key-not-valid", KEY_NOT_VALID, api_base), + deployment("rate-limited", RATE_LIMITS, api_base), + deployment("recovers", RECOVERS, api_base), + anthropic_deployment("anthropic-own-key", upstream.url), + anthropic_deployment("anthropic-sdk-own-key", upstream.url), + anthropic_deployment("caller-oauth", upstream.url), + *(keyless_anthropic_deployment(cell, upstream.url) for cell in KEYLESS_CELLS), + bedrock_deployment( + "deployment-caller-bedrock-endpoint", + {"configurable_clientside_auth_params": ["aws_bedrock_runtime_endpoint"]}, + ), + azure_deployment("azure-own-token", upstream.url, {"azure_ad_token": "deployment-entra-token-azure-own-token"}), + *( + azure_deployment( + caller_azure_cell("deployment", route, inside_extra_body), + upstream.url, + {"configurable_clientside_auth_params": ["azure_ad_token"]}, + ) + for route, inside_extra_body in CALLER_AZURE_CELLS + ), + *(caller_credential_deployment(cell, field, upstream.url) for cell, field in CALLER_CREDENTIAL_CELLS), + *(token_exchange_deployment(cell) for cell in TOKEN_EXCHANGE_CELLS), + { + "model_name": name("caller-api-base"), + "litellm_params": { + "model": f"openai/{REJECTS}", + "api_key": "sk-deployment-credential-caller-api-base", + "api_base": api_base, + "configurable_clientside_auth_params": ["api_base"], + }, + "model_info": {"id": identity("caller-api-base")}, + }, + { + "model_name": name("caller-credential"), + "litellm_params": { + "model": "github_copilot/gpt-4o", + "litellm_credential_name": f"copilot-per-user-{RUN}", + "github_copilot_auth_type": "per_user_oauth", + }, + "model_info": {"id": identity("caller-credential")}, + }, + { + "model_name": name("caller-credential-name"), + "litellm_params": { + "model": f"openai/{HEALTHY}", + "api_base": api_base, + "litellm_credential_name": f"deployment-key-{RUN}", + }, + "model_info": {"id": identity("caller-credential-name")}, + }, + ] + configuration["credential_list"] = [ + *configuration.get("credential_list", []), + {"credential_name": f"m365-obo-{RUN}", "credential_values": {**TOKEN_EXCHANGE_SETTINGS}, "credential_info": {}}, + { + "credential_name": f"deployment-key-{RUN}", + "credential_values": {"api_key": "sk-deployment-credential-caller-credential-name"}, + "credential_info": {}, + }, + { + "credential_name": f"revoked-key-{RUN}", + "credential_values": {"api_key": REVOKED_STORED_KEY}, + "credential_info": {}, + }, + ] + configuration["guardrails"] = [ + { + "guardrail_name": AGENT_365_GUARDRAIL, + "litellm_params": { + "guardrail": "agent_365", + "mode": "pre_mcp_call", + "default_on": True, + "tenant_id": "00000000-0000-4000-8000-0000000a3650", + "client_id": "synthetic-client-id", + "client_secret": "synthetic-client-secret", + }, + } + ] + configuration["litellm_settings"]["callbacks"] = ["prometheus"] + configuration["litellm_settings"]["model_group_settings"] = { + "forward_client_headers_to_llm_api": [ + name("forwarded-provider-header"), + name("forwarded-plain-header"), + name("forwarded-gateway-key"), + name("forwarded-user-information"), + ] + } + configuration["litellm_settings"]["add_user_information_to_llm_headers"] = True + configuration["general_settings"]["forward_llm_provider_auth_headers"] = True + configuration["general_settings"]["forward_openai_org_id"] = True + configuration.setdefault("router_settings", {}).update({"num_retries": 0, "disable_cooldowns": True}) + path: Final = directory / "prometheus-provider-auth-failure.yaml" + path.write_text(yaml.safe_dump(configuration)) + return path + + +@dataclass(frozen=True, slots=True) +class Rig: + gateway: Gateway + upstream: Wire + + @property + def api_base(self) -> str: + return f"{self.upstream.url}/v1" + + +@pytest.fixture(scope="module") +def rig(tmp_path_factory: pytest.TempPathFactory) -> Iterator[Rig]: + directory: Final = tmp_path_factory.mktemp("prometheus-provider-auth-failure") + released: Final = threading.Event() + released.set() + with ( + wire_server(Provider(released)) as upstream, + gateway_from_environment() as shared, + owned_proxy( + shared, + directory, + {"PROXY_CONFIG_RELOAD_INTERVAL_SECONDS": "2"}, + config=config(directory, upstream), + remove_environment=("ANTHROPIC_API_KEY", "ANTHROPIC_AUTH_TOKEN"), + ) as owned, + ): + yield Rig(owned, upstream) + + +def opted_in_config(directory: Path, upstream: Wire) -> Path: + configuration: Final = yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text()) + configuration["model_list"] = [ + *configuration["model_list"], + *( + azure_deployment(caller_azure_cell("proxy-wide", route, inside_extra_body), upstream.url, {}) + for route, inside_extra_body in CALLER_AZURE_CELLS + ), + bedrock_deployment("proxy-wide-caller-bedrock-endpoint", {}), + ] + configuration["general_settings"]["allow_client_side_credentials"] = True + configuration["litellm_settings"]["callbacks"] = ["prometheus"] + configuration.setdefault("router_settings", {}).update({"num_retries": 0, "disable_cooldowns": True}) + path: Final = directory / "prometheus-caller-credentials-opted-in.yaml" + path.write_text(yaml.safe_dump(configuration)) + return path + + +@pytest.fixture(scope="module") +def opted_in(tmp_path_factory: pytest.TempPathFactory) -> Iterator[Rig]: + directory: Final = tmp_path_factory.mktemp("prometheus-caller-credentials-opted-in") + released: Final = threading.Event() + released.set() + with ( + wire_server(Provider(released)) as upstream, + gateway_from_environment() as shared, + owned_proxy(shared, directory, {}, config=opted_in_config(directory, upstream)) as owned, + ): + yield Rig(owned, upstream) + + +def series(samples: Sequence[Sample], metric: str, **labels: str) -> tuple[Sample, ...]: + return tuple( + sample + for sample in samples + if sample.name == metric and all(sample.labels.get(label) == value for label, value in labels.items()) + ) + + +def values(samples: Sequence[Sample], metric: str, **labels: str) -> list[float]: + return [sample.value for sample in series(samples, metric, **labels)] + + +def until(gateway: Gateway, metric: str, **labels: str) -> tuple[Sample, ...]: + return eventually(lambda: scrape(gateway), lambda samples: bool(series(samples, metric, **labels)), 30) + + +def messages(cell: str) -> list[JsonValue]: + return [{"role": "user", "content": f"{cell} {uuid.uuid4().hex}"}] + + +def send(gateway: Gateway, cell: str, model: str | None = None, key: str | None = None) -> httpx.Response: + asked: Final = model or name(cell) + stream: Final = cell.endswith("-stream") + if cell.startswith("messages"): + anthropic: Final = {"model": asked, "max_tokens": 16, "messages": messages(cell), "stream": stream} + return gateway.request("POST", "/v1/messages", anthropic, key=key) + if cell.startswith("responses"): + return gateway.request("POST", "/v1/responses", {"model": asked, "input": cell, "stream": stream}, key=key) + if cell == "embeddings": + return gateway.request("POST", "/v1/embeddings", {"model": asked, "input": cell}, key=key) + return gateway.request( + "POST", "/v1/chat/completions", {"model": asked, "messages": messages(cell), "stream": stream}, key=key + ) + + +def assert_reached_with_the_deployment_credential(rig: Rig, cell: str, attempts: int = 1) -> None: + reached: Final = rig.upstream.drain() + assert [request.headers["authorization"] for request in reached] == [ + f"Bearer sk-deployment-credential-{cell}" + ] * attempts, [request.target for request in reached] + + +def recorded(samples: Sequence[Sample], **labels: str) -> list[tuple[str, dict[str, str], float]]: + return [(sample.name, dict(sample.labels), sample.value) for sample in series_of(samples, **labels)] + + +def series_of(samples: Sequence[Sample], **labels: str) -> tuple[Sample, ...]: + return tuple( + sample + for sample in samples + if sample.name.startswith("litellm_") + and all(sample.labels.get(label) == value for label, value in labels.items()) + ) + + +def assert_kept_out_of_the_deployment_metrics(rig: Rig, cell: str) -> None: + samples: Final = until(rig.gateway, PROXY_FAILED, requested_model=name(cell)) + assert {metric: values(samples, metric, model_id=identity(cell)) for metric in DEPLOYMENT_SERIES} == { + metric: [] for metric in DEPLOYMENT_SERIES + }, recorded(samples, model_id=identity(cell)) + + +def assert_recorded_as_a_deployment_failure(rig: Rig, cell: str, status: str, count: float = 1.0) -> None: + samples: Final = until(rig.gateway, FAILURES, model_id=identity(cell)) + observed: Final = recorded(samples, model_id=identity(cell)) + assert values(samples, FAILURES, model_id=identity(cell), exception_status=status) == [count], observed + assert values(samples, TOTALS, model_id=identity(cell)) == [count], observed + assert values(samples, LLM_FAILED, model_id=identity(cell)) == [count], observed + assert values(samples, STATE, model_id=identity(cell)) == [1.0], observed + + +@pytest.mark.parametrize("cell", ENDPOINT_CELLS) +def test_a_provider_401_on_every_endpoint_counts_as_a_deployment_failure_and_a_partial_outage( + rig: Rig, cell: str +) -> None: + rig.upstream.drain() + response: Final = send(rig.gateway, cell) + assert response.status_code == 401, response.text + assert_reached_with_the_deployment_credential(rig, cell) + assert_recorded_as_a_deployment_failure(rig, cell, "401") + + +def test_a_provider_401_seen_by_the_sync_openai_client_is_recorded(rig: Rig) -> None: + rig.upstream.drain() + with ( + openai.OpenAI( + base_url=f"{rig.gateway.client.base_url}/v1", + api_key=rig.gateway.key, + max_retries=0, + http_client=httpx.Client(trust_env=False), + ) as client, + pytest.raises(openai.AuthenticationError, match="Incorrect API key provided"), + ): + client.chat.completions.create(model=name("sdk-sync"), messages=[{"role": "user", "content": "sync"}]) + assert_reached_with_the_deployment_credential(rig, "sdk-sync") + assert_recorded_as_a_deployment_failure(rig, "sdk-sync", "401") + + +def test_a_provider_401_seen_by_the_async_openai_client_is_recorded(rig: Rig) -> None: + async def ask() -> None: + async with openai.AsyncOpenAI( + base_url=f"{rig.gateway.client.base_url}/v1", + api_key=rig.gateway.key, + max_retries=0, + http_client=httpx.AsyncClient(trust_env=False), + ) as client: + await client.chat.completions.create(model=name("sdk-async"), messages=[{"role": "user", "content": "a"}]) + + rig.upstream.drain() + with pytest.raises(openai.AuthenticationError, match="Incorrect API key provided"): + asyncio.run(ask()) + assert_reached_with_the_deployment_credential(rig, "sdk-async") + assert_recorded_as_a_deployment_failure(rig, "sdk-async", "401") + + +def test_each_repeated_provider_401_is_counted_once(rig: Rig) -> None: + rig.upstream.drain() + assert [send(rig.gateway, "repeated").status_code for _ in range(3)] == [401, 401, 401] + assert_reached_with_the_deployment_credential(rig, "repeated", attempts=3) + assert_recorded_as_a_deployment_failure(rig, "repeated", "401", count=3.0) + + +def test_a_provider_401_rescued_by_a_fallback_still_counts_against_the_rejected_deployment(rig: Rig) -> None: + rig.upstream.drain() + response: Final = rig.gateway.request( + "POST", + "/v1/chat/completions", + {"model": name("fallback"), "messages": messages("fallback"), "fallbacks": [name("healthy")]}, + ) + assert response.status_code == 200, response.text + assert [request.headers["authorization"] for request in rig.upstream.drain()] == [ + "Bearer sk-deployment-credential-fallback", + "Bearer sk-deployment-credential-healthy", + ] + assert_recorded_as_a_deployment_failure(rig, "fallback", "401") + rescued: Final = eventually( + lambda: scrape(rig.gateway), lambda samples: values(samples, SUCCESSES, model_id=identity("healthy")) == [1.0] + ) + assert values(rescued, FAILURES, model_id=identity("healthy")) == [] + + +def test_a_provider_auth_message_on_a_non_401_status_is_recorded(rig: Rig) -> None: + rig.upstream.drain() + response: Final = send(rig.gateway, "key-not-valid") + assert response.status_code == 400, response.text + assert_reached_with_the_deployment_credential(rig, "key-not-valid") + assert_recorded_as_a_deployment_failure(rig, "key-not-valid", "400") + + +def test_a_provider_429_is_recorded_as_before(rig: Rig) -> None: + rig.upstream.drain() + response: Final = send(rig.gateway, "rate-limited") + assert response.status_code == 429, response.text + assert_reached_with_the_deployment_credential(rig, "rate-limited") + assert_recorded_as_a_deployment_failure(rig, "rate-limited", "429") + + +def test_a_deployment_marked_down_by_a_provider_401_is_healthy_again_after_a_success(rig: Rig) -> None: + rig.upstream.drain() + assert send(rig.gateway, "recovers").status_code == 401 + assert_recorded_as_a_deployment_failure(rig, "recovers", "401") + recovered: Final = send(rig.gateway, "recovers") + assert recovered.status_code == 200, recovered.text + assert len(rig.upstream.drain()) == 2 + eventually( + lambda: scrape(rig.gateway), + lambda samples: values(samples, STATE, model_id=identity("recovers"), api_base=rig.api_base) == [0.0], + ) + + +def test_a_per_caller_credential_rejection_stays_out_of_the_deployment_metrics(rig: Rig) -> None: + rig.upstream.drain() + response: Final = send(rig.gateway, "caller-credential") + assert response.status_code == 401, response.text + assert "Connect GitHub Copilot" in response.text, response.text + assert rig.upstream.drain() == () + samples: Final = until(rig.gateway, PROXY_FAILED, requested_model=name("caller-credential")) + assert values(samples, FAILURES, model_id=identity("caller-credential")) == [] + assert values(samples, TOTALS, model_id=identity("caller-credential")) == [] + assert values(samples, LLM_FAILED, model_id=identity("caller-credential")) == [] + assert values(samples, STATE, model_id=identity("caller-credential")) == [] + + +def deployment_series(samples: Sequence[Sample]) -> frozenset[tuple[str, tuple[tuple[str, str], ...]]]: + return frozenset((sample.name, sample.identity()) for sample in samples if sample.name in DEPLOYMENT_SERIES) + + +def test_a_provider_401_on_an_api_key_the_caller_sent_stays_out_of_the_deployment_metrics(rig: Rig) -> None: + caller_key: Final = f"sk-caller-supplied-{uuid.uuid4().hex}" + before: Final = deployment_series(scrape(rig.gateway)) + rig.upstream.drain() + response: Final = rig.gateway.request( + "POST", + "/v1/chat/completions", + {"model": name("caller-api-key"), "messages": messages("caller-api-key"), "api_key": caller_key}, + ) + assert response.status_code == 401, response.text + assert [request.headers["authorization"] for request in rig.upstream.drain()] == [f"Bearer {caller_key}"] + samples: Final = until(rig.gateway, PROXY_FAILED, requested_model=name("caller-api-key")) + assert deployment_series(samples) - before == frozenset(), recorded(samples, requested_model=name("caller-api-key")) + + +def test_a_provider_401_on_a_stored_credential_the_caller_names_leaves_a_healthy_deployment_healthy(rig: Rig) -> None: + cell: Final = "caller-credential-name" + rig.upstream.drain() + assert send(rig.gateway, cell).status_code == 200 + assert_reached_with_the_deployment_credential(rig, cell) + response: Final = rig.gateway.request( + "POST", + "/v1/chat/completions", + {"model": name(cell), "messages": messages(cell), "litellm_credential_name": f"revoked-key-{RUN}"}, + ) + assert response.status_code == 401, response.text + assert [request.headers["authorization"] for request in rig.upstream.drain()] == [f"Bearer {REVOKED_STORED_KEY}"] + samples: Final = until(rig.gateway, PROXY_FAILED, requested_model=name(cell)) + observed: Final = recorded(samples, model_id=identity(cell)) + assert values(samples, FAILURES, model_id=identity(cell)) == [], observed + assert values(samples, LLM_FAILED, model_id=identity(cell)) == [], observed + assert values(samples, TOTALS, model_id=identity(cell)) == [1.0], observed + assert values(samples, STATE, model_id=identity(cell)) == [0.0], observed + + +def anthropic_messages(gateway: Gateway, cell: str, key: str, headers: dict[str, str]) -> httpx.Response: + body: Final[dict[str, JsonValue]] = {"model": name(cell), "max_tokens": 16, "messages": messages(cell)} + return gateway.request("POST", "/v1/messages", body, key=key, headers=headers) + + +def caller_header(field: str, header: str, value: str) -> JsonValue: + if field == "provider_specific_header": + return {"custom_llm_provider": "openai", "extra_headers": {header: value}} + return {header: value} + + +@pytest.mark.parametrize( + "cell,field", + [ + ("caller-extra-headers", "extra_headers"), + ("caller-headers", "headers"), + ("caller-provider-specific-header", "provider_specific_header"), + ], +) +def test_a_provider_401_on_an_authorization_header_the_caller_sends_stays_out_of_the_deployment_metrics( + rig: Rig, cell: str, field: str +) -> None: + caller_value: Final = f"Bearer sk-{cell}-{uuid.uuid4().hex}" + rig.upstream.drain() + response: Final = rig.gateway.request( + "POST", + "/v1/chat/completions", + {"model": name(cell), "messages": messages(cell), field: caller_header(field, "Authorization", caller_value)}, + ) + assert response.status_code == 401, response.text + assert [request.headers["authorization"] for request in rig.upstream.drain()] == [caller_value] + samples: Final = until(rig.gateway, PROXY_FAILED, requested_model=name(cell)) + observed: Final = recorded(samples, model_id=identity(cell)) + assert values(samples, FAILURES, model_id=identity(cell)) == [], observed + assert values(samples, TOTALS, model_id=identity(cell)) == [], observed + assert values(samples, LLM_FAILED, model_id=identity(cell)) == [], observed + assert values(samples, STATE, model_id=identity(cell)) == [], observed + + +@pytest.mark.parametrize( + "cell,field", + [ + ("plain-extra-headers", "extra_headers"), + ("plain-headers", "headers"), + ("plain-provider-specific-header", "provider_specific_header"), + ], +) +def test_a_provider_401_on_the_deployments_own_key_stays_out_when_the_caller_sends_a_plain_header( + rig: Rig, cell: str, field: str +) -> None: + trace: Final = f"{cell}-{uuid.uuid4().hex}" + rig.upstream.drain() + response: Final = rig.gateway.request( + "POST", + "/v1/chat/completions", + {"model": name(cell), "messages": messages(cell), field: caller_header(field, "X-Caller-Trace", trace)}, + ) + assert response.status_code == 401, response.text + reached: Final = rig.upstream.drain() + assert [(request.headers["authorization"], request.headers.get("x-caller-trace")) for request in reached] == [ + (f"Bearer sk-deployment-credential-{cell}", trace) + ] + assert_kept_out_of_the_deployment_metrics(rig, cell) + + +def test_a_provider_401_on_a_provider_credential_header_the_proxy_forwards_stays_out_of_the_deployment_metrics( + rig: Rig, +) -> None: + caller_key: Final = f"AIza-forwarded-{uuid.uuid4().hex}" + rig.upstream.drain() + response: Final = rig.gateway.request( + "POST", + "/v1/chat/completions", + {"model": name("forwarded-provider-header"), "messages": messages("forwarded-provider-header")}, + headers={"x-goog-api-key": caller_key}, + ) + assert response.status_code == 401, response.text + assert [request.headers.get("x-goog-api-key") for request in rig.upstream.drain()] == [caller_key] + samples: Final = until(rig.gateway, PROXY_FAILED, requested_model=name("forwarded-provider-header")) + observed: Final = recorded(samples, model_id=identity("forwarded-provider-header")) + assert values(samples, FAILURES, model_id=identity("forwarded-provider-header")) == [], observed + assert values(samples, TOTALS, model_id=identity("forwarded-provider-header")) == [], observed + assert values(samples, LLM_FAILED, model_id=identity("forwarded-provider-header")) == [], observed + assert values(samples, STATE, model_id=identity("forwarded-provider-header")) == [], observed + + +def test_a_provider_401_on_the_deployments_own_key_stays_out_when_the_proxy_forwards_a_plain_header(rig: Rig) -> None: + trace: Final = f"forwarded-plain-header-{uuid.uuid4().hex}" + rig.upstream.drain() + response: Final = rig.gateway.request( + "POST", + "/v1/chat/completions", + {"model": name("forwarded-plain-header"), "messages": messages("forwarded-plain-header")}, + headers={"x-caller-trace": trace}, + ) + assert response.status_code == 401, response.text + assert [ + (request.headers["authorization"], request.headers.get("x-caller-trace")) for request in rig.upstream.drain() + ] == [("Bearer sk-deployment-credential-forwarded-plain-header", trace)] + assert_kept_out_of_the_deployment_metrics(rig, "forwarded-plain-header") + + +def test_a_provider_401_on_the_deployments_own_key_counts_when_the_proxy_forwards_only_its_own_user_information( + rig: Rig, +) -> None: + rig.upstream.drain() + response: Final = send(rig.gateway, "forwarded-user-information") + assert response.status_code == 401, response.text + reached: Final = rig.upstream.drain() + assert [ + (request.headers["authorization"], "x-litellm-user_api_key_hash" in request.headers) for request in reached + ] == [("Bearer sk-deployment-credential-forwarded-user-information", True)] + assert_recorded_as_a_deployment_failure(rig, "forwarded-user-information", "401") + + +def test_a_provider_401_on_a_gateway_key_the_proxy_forwards_stays_out_of_a_healthy_deployments_metrics( + rig: Rig, +) -> None: + rig.upstream.drain() + response: Final = rig.gateway.request( + "POST", + "/v1/chat/completions", + {"model": name("forwarded-gateway-key"), "messages": messages("forwarded-gateway-key")}, + headers={"x-portkey-api-key": REVOKED_GATEWAY_KEY}, + ) + assert response.status_code == 401, response.text + assert [ + (request.headers["authorization"], request.headers.get("x-portkey-api-key")) for request in rig.upstream.drain() + ] == [("Bearer sk-deployment-credential-forwarded-gateway-key", REVOKED_GATEWAY_KEY)] + assert_kept_out_of_the_deployment_metrics(rig, "forwarded-gateway-key") + + +@pytest.mark.parametrize( + "cell,body,headers", + [ + ("caller-organization", {"organization": UNKNOWN_ORGANIZATION}, {}), + ("forwarded-organization", {}, {"OpenAI-Organization": UNKNOWN_ORGANIZATION}), + ], +) +def test_a_provider_401_on_an_organization_the_caller_sends_stays_out_of_a_healthy_deployments_metrics( + rig: Rig, cell: str, body: dict[str, JsonValue], headers: dict[str, str] +) -> None: + rig.upstream.drain() + response: Final = rig.gateway.request( + "POST", "/v1/chat/completions", {"model": name(cell), "messages": messages(cell), **body}, headers=headers + ) + assert response.status_code == 401, response.text + assert [ + (request.headers["authorization"], request.headers.get("openai-organization")) + for request in rig.upstream.drain() + ] == [(f"Bearer sk-deployment-credential-{cell}", UNKNOWN_ORGANIZATION)] + assert_kept_out_of_the_deployment_metrics(rig, cell) + + +@pytest.mark.parametrize( + ("cell", "headers"), + [ + ("anthropic-own-key", {}), + ("anthropic-sdk-own-key", {"anthropic-version": "2023-06-01", "anthropic-beta": "tools-2024-04-04"}), + ], + ids=["no-client-headers", "anthropic-sdk-headers"], +) +def test_a_provider_401_on_an_anthropic_deployments_own_key_is_recorded( + rig: Rig, cell: str, headers: dict[str, str] +) -> None: + with rig.gateway.scenario() as scenario: + key: Final = scenario.key(models=[name(cell)]) + rig.upstream.drain() + response: Final = anthropic_messages(rig.gateway, cell, key, headers) + assert response.status_code == 401, response.text + assert [request.headers.get("x-api-key") for request in rig.upstream.drain()] == [ + f"sk-ant-api03-deployment-credential-{cell}" + ] + assert_recorded_as_a_deployment_failure(rig, cell, "401") + + +def test_a_provider_401_on_an_anthropic_oauth_token_the_caller_sent_stays_out_of_the_deployment_metrics( + rig: Rig, +) -> None: + with rig.gateway.scenario() as scenario: + key: Final = scenario.key(models=[name("caller-oauth")]) + rig.upstream.drain() + response: Final = anthropic_messages( + rig.gateway, + "caller-oauth", + CALLER_OAUTH_TOKEN, + {"x-litellm-api-key": key}, + ) + assert response.status_code == 401, response.text + assert [request.headers.get("authorization") for request in rig.upstream.drain()] == [ + f"Bearer {CALLER_OAUTH_TOKEN}" + ] + samples: Final = until(rig.gateway, PROXY_FAILED, requested_model=name("caller-oauth")) + assert {metric: values(samples, metric, model_id=identity("caller-oauth")) for metric in DEPLOYMENT_SERIES} == { + metric: [] for metric in DEPLOYMENT_SERIES + }, recorded(samples, requested_model=name("caller-oauth")) + + +def test_a_provider_401_on_an_azure_deployments_own_ad_token_is_recorded(rig: Rig) -> None: + rig.upstream.drain() + response: Final = send(rig.gateway, "azure-own-token") + assert response.status_code == 401, response.text + assert [request.headers.get("authorization") for request in rig.upstream.drain()] == [ + "Bearer deployment-entra-token-azure-own-token" + ] + assert_recorded_as_a_deployment_failure(rig, "azure-own-token", "401") + + +def caller_azure_request(cell: str, route: str, credential: dict[str, JsonValue]) -> tuple[str, dict[str, JsonValue]]: + if route == "embeddings": + return "/v1/embeddings", {"model": name(cell), "input": cell, **credential} + if route == "responses": + return "/v1/responses", {"model": name(cell), "input": cell, **credential} + if route == "messages": + return "/v1/messages", {"model": name(cell), "max_tokens": 16, "messages": messages(cell), **credential} + return "/v1/chat/completions", {"model": name(cell), "messages": messages(cell), **credential} + + +@pytest.mark.parametrize( + ("route", "inside_extra_body"), + CALLER_AZURE_CELLS, + ids=[f"{route}{'-extra-body' if inside_extra_body else ''}" for route, inside_extra_body in CALLER_AZURE_CELLS], +) +@pytest.mark.parametrize("opt_in", ("deployment", "proxy-wide")) +def test_a_provider_401_on_an_azure_ad_token_the_caller_sent_stays_out_of_the_deployment_metrics( + request: pytest.FixtureRequest, opt_in: str, route: str, inside_extra_body: bool +) -> None: + opted: Final[Rig] = request.getfixturevalue("rig" if opt_in == "deployment" else "opted_in") + cell: Final = caller_azure_cell(opt_in, route, inside_extra_body) + token: Final = f"caller-entra-token-{uuid.uuid4().hex}" + credential: Final[dict[str, JsonValue]] = ( + {"extra_body": {"azure_ad_token": token}} if inside_extra_body else {"azure_ad_token": token} + ) + opted.upstream.drain() + response: Final = opted.gateway.request("POST", *caller_azure_request(cell, route, credential)) + assert response.status_code == 401, response.text + assert [reached.headers.get("authorization") for reached in opted.upstream.drain()] == [ + None if inside_extra_body else f"Bearer {token}" + ] + samples: Final = until(opted.gateway, PROXY_FAILED, requested_model=name(cell)) + assert {metric: values(samples, metric, model_id=identity(cell)) for metric in DEPLOYMENT_SERIES} == { + metric: [] for metric in DEPLOYMENT_SERIES + }, recorded(samples, requested_model=name(cell)) + + +@pytest.mark.parametrize(("cell", "field"), CALLER_CREDENTIAL_CELLS, ids=[cell for cell, _ in CALLER_CREDENTIAL_CELLS]) +def test_a_provider_401_on_a_provider_credential_the_caller_sent_stays_out_of_the_deployment_metrics( + rig: Rig, cell: str, field: str +) -> None: + caller_credential: Final = f"caller-credential-{uuid.uuid4().hex}" + rig.upstream.drain() + response: Final = rig.gateway.request( + "POST", "/v1/chat/completions", {"model": name(cell), "messages": messages(cell), field: caller_credential} + ) + assert response.status_code == 401, response.text + assert [reached.headers.get("authorization") for reached in rig.upstream.drain()] == [f"Bearer {caller_credential}"] + samples: Final = until(rig.gateway, PROXY_FAILED, requested_model=name(cell)) + assert {metric: values(samples, metric, model_id=identity(cell)) for metric in DEPLOYMENT_SERIES} == { + metric: [] for metric in DEPLOYMENT_SERIES + }, recorded(samples, requested_model=name(cell)) + + +@pytest.mark.parametrize("cell", TOKEN_EXCHANGE_CELLS) +def test_a_token_exchange_deployment_rejecting_a_caller_without_an_identity_token_stays_out_of_the_deployment_metrics( + rig: Rig, cell: str +) -> None: + rig.upstream.drain() + response: Final = send(rig.gateway, cell) + assert response.status_code == 401, response.text + assert "IdP-issued access token" in response.text, response.text + assert rig.upstream.drain() == () + samples: Final = until(rig.gateway, PROXY_FAILED, requested_model=name(cell)) + assert {metric: values(samples, metric, model_id=identity(cell)) for metric in DEPLOYMENT_SERIES} == { + metric: [] for metric in DEPLOYMENT_SERIES + }, recorded(samples, requested_model=name(cell)) + + +@pytest.mark.parametrize("cell", KEYLESS_CELLS) +def test_a_missing_deployment_key_reported_before_the_provider_is_called_stays_out_of_the_deployment_metrics( + rig: Rig, cell: str +) -> None: + rig.upstream.drain() + response: Final = send(rig.gateway, cell) + assert response.status_code == 401, response.text + assert "Missing Anthropic API Key" in response.text, response.text + assert rig.upstream.drain() == () + assert_kept_out_of_the_deployment_metrics(rig, cell) + + +@pytest.mark.parametrize("opt_in", ("deployment", "proxy-wide")) +def test_a_provider_401_at_a_bedrock_endpoint_the_caller_sends_stays_out_of_the_deployment_metrics( + request: pytest.FixtureRequest, opt_in: str +) -> None: + opted: Final[Rig] = request.getfixturevalue("rig" if opt_in == "deployment" else "opted_in") + cell: Final = f"{opt_in}-caller-bedrock-endpoint" + opted.upstream.drain() + response: Final = opted.gateway.request( + "POST", + "/v1/chat/completions", + {"model": name(cell), "messages": messages(cell), "aws_bedrock_runtime_endpoint": opted.upstream.url}, + ) + assert response.status_code == 401, response.text + assert [reached.target for reached in opted.upstream.drain()] == [f"/model/{REJECTS}/converse"] + assert_kept_out_of_the_deployment_metrics(opted, cell) + + +def test_a_provider_401_at_an_api_base_the_caller_sends_counts_against_a_one_off_deployment(rig: Rig) -> None: + caller_api_base: Final = f"{rig.upstream.url}/caller-endpoint-{RUN}/v1" + rig.upstream.drain() + response: Final = rig.gateway.request( + "POST", + "/v1/chat/completions", + {"model": name("caller-api-base"), "messages": messages("caller-api-base"), "api_base": caller_api_base}, + ) + assert response.status_code == 401, response.text + assert [(reached.target, reached.headers["authorization"]) for reached in rig.upstream.drain()] == [ + (f"/caller-endpoint-{RUN}/v1/chat/completions", "Bearer sk-deployment-credential-caller-api-base") + ] + samples: Final = until(rig.gateway, FAILURES, api_base=caller_api_base) + one_off: Final = {sample.labels["model_id"] for sample in series(samples, FAILURES, api_base=caller_api_base)} + assert len(one_off) == 1 and identity("caller-api-base") not in one_off, recorded(samples, api_base=caller_api_base) + assert values(samples, FAILURES, api_base=caller_api_base, exception_status="401") == [1.0] + assert values(samples, TOTALS, api_base=caller_api_base) == [1.0] + assert values(samples, STATE, api_base=caller_api_base) == [1.0] + assert values(samples, LLM_FAILED, model_id=next(iter(one_off))) == [1.0] + assert {metric: values(samples, metric, model_id=identity("caller-api-base")) for metric in DEPLOYMENT_SERIES} == { + metric: [] for metric in DEPLOYMENT_SERIES + } + + +def _gated_key(scenario: Scenario, cell: str) -> str | None: + if cell == "invalid-key": + return f"sk-not-a-virtual-key-{uuid.uuid4().hex}" + if cell == "missing-key": + return None + if cell == "no-model-access": + return scenario.key(models=[name("healthy")]) + key: Final = scenario.key(models=[name(cell)]) + if cell == "expired-key": + write_rows( + "UPDATE \"LiteLLM_VerificationToken\" SET expires = now() - interval '1 hour' WHERE token = %s", + (sha256(key.encode()).hexdigest(),), + database_url=scenario.gateway.database_url, + ) + return key + scenario.gateway.post("/key/block", {"key": key}) + return key + + +def _gated(gateway: Gateway, cell: str, key: str | None) -> httpx.Response: + if key is None: + return gateway.client.post("/v1/chat/completions", json={"model": name(cell), "messages": messages(cell)}) + return send(gateway, cell, key=key) + + +def recorded_before(cell: str) -> list[tuple[str, str, str, float]]: + if cell in ("invalid-key", "expired-key"): + return [] + return sorted([(FAILURES, "", "", 1.0), (TOTALS, "", "", 1.0), (LLM_FAILED, identity(cell), "", 1.0)]) + + +def deployment_rows(samples: Sequence[Sample], cell: str) -> list[tuple[str, str, str, float]]: + return sorted( + (sample.name, sample.labels.get("model_id", ""), sample.labels.get("api_base", ""), sample.value) + for sample in samples + if sample.name in DEPLOYMENT_SERIES + and name(cell) in (sample.labels.get("requested_model"), sample.labels.get("model")) + ) + + +@pytest.mark.parametrize("cell", GATED_CELLS) +def test_a_request_the_proxy_rejects_itself_never_marks_the_deployment_down_and_is_recorded_as_before( + rig: Rig, cell: str +) -> None: + with rig.gateway.scenario() as scenario: + key: Final = _gated_key(scenario, cell) + rig.upstream.drain() + response: Final = _gated(rig.gateway, cell, key) + assert response.status_code == (403 if cell == "no-model-access" else 401), response.text + assert rig.upstream.drain() == () + samples: Final = until(rig.gateway, PROXY_FAILED, requested_model=name(cell)) + assert deployment_rows(samples, cell) == recorded_before(cell), recorded(samples, requested_model=name(cell)) + + +def test_a_key_rate_limit_rejected_at_the_proxy_is_still_counted_as_before(rig: Rig) -> None: + with rig.gateway.scenario() as scenario: + key: Final = scenario.key(models=[name("key-rpm-limit")], rpm_limit=1) + rig.upstream.drain() + admitted: Final = send(rig.gateway, "key-rpm-limit", key=key) + assert admitted.status_code == 200, admitted.text + limited: Final = send(rig.gateway, "key-rpm-limit", key=key) + assert limited.status_code == 429, limited.text + assert len(rig.upstream.drain()) == 1 + samples: Final = until(rig.gateway, FAILURES, requested_model=name("key-rpm-limit"), exception_status="429") + assert values(samples, FAILURES, requested_model=name("key-rpm-limit"), exception_status="429") == [1.0] + eventually( + lambda: scrape(rig.gateway), + lambda observed: ( + values(observed, STATE, model_id=identity("key-rpm-limit"), api_base=rig.api_base) == [0.0] + ), + ) + + +@pytest.fixture(scope="module") +def mcp_peer() -> Iterator[McpPeer]: + with scripted_peer(echo_tool("add")) as peer: + yield peer + + +def test_an_mcp_tool_call_the_proxy_rejects_for_the_caller_stays_out_of_the_llm_failure_metrics( + rig: Rig, mcp_peer: McpPeer +) -> None: + alias: Final = "a365" + RUN + with rig.gateway.scenario() as scenario: + server: Final = register_mcp(scenario, mcp_peer, alias) + key: Final = scenario.key(object_permission={"mcp_servers": [server]}) + hashed: Final = sha256(key.encode()).hexdigest() + outcomes: Final = { + entry: McpCaller(rig.gateway, key, entry, alias).call(f"{alias}-add", {"entry": entry}, server) + for entry in ENTRY_POINTS + } + assert all( + outcome.error is not None and "Agent 365 guardrail rejected" in outcome.raw for outcome in outcomes.values() + ), {entry: outcome.raw for entry, outcome in outcomes.items()} + eventually( + lambda: rig.gateway.rows(GUARDRAIL_ROWS, (AGENT_365_GUARDRAIL, hashed, "call_mcp_tool")), + lambda rows: [row["status"] for row in rows] == ["guardrail_intervened"] * len(ENTRY_POINTS), + seconds=70, + ) + samples: Final = scrape(rig.gateway) + assert values(samples, LLM_FAILED, hashed_api_key=hashed) == [] + assert values(samples, FAILURES, hashed_api_key=hashed) == [] + assert values(samples, TOTALS, hashed_api_key=hashed) == [] diff --git a/tests/integration/observability/test_prometheus_provider_auth_failure_chaos.py b/tests/integration/observability/test_prometheus_provider_auth_failure_chaos.py new file mode 100644 index 00000000000..a1fe1cf4f33 --- /dev/null +++ b/tests/integration/observability/test_prometheus_provider_auth_failure_chaos.py @@ -0,0 +1,147 @@ +import threading +import uuid +from collections.abc import Iterator, Sequence +from concurrent.futures import ThreadPoolExecutor +from contextlib import contextmanager +from dataclasses import dataclass +from pathlib import Path +from typing import Final + +import httpx +import psutil +from integration._support.client import Gateway, eventually +from integration._support.process import OwnedProxy, owned_proxy_process +from integration._support.prometheus_series import Sample, scrape +from integration._support.wire import Wire, wire_server +from test_prometheus_provider_auth_failure import ( + FAILURES, + LLM_FAILED, + STATE, + TOTALS, + Provider, + config, + identity, + name, + send, + values, +) + +BURST: Final = 12 +ENDPOINTS: Final = ("chat", "chat-stream", "messages", "responses") + + +@dataclass(frozen=True, slots=True) +class ChaosRig: + owned: OwnedProxy + upstream: Wire + release: threading.Event + + +@contextmanager +def _rig(gateway: Gateway, tmp_path: Path) -> Iterator[ChaosRig]: + release: Final = threading.Event() + prom_dir: Final = tmp_path / "prom" + prom_dir.mkdir() + with ( + wire_server(Provider(release)) as upstream, + owned_proxy_process( + gateway, + tmp_path, + {"PROMETHEUS_MULTIPROC_DIR": str(prom_dir)}, + config=config(tmp_path, upstream), + workers=2, + ) as owned, + ): + try: + yield ChaosRig(owned, upstream, release) + finally: + release.set() + + +def _status(gateway: Gateway, cell: str, model: str, key: str | None = None) -> int: + try: + return send(gateway, cell, model=model, key=key).status_code + except httpx.HTTPError: + return -1 + + +def _holds_a_connection_to(pid: int, port: int) -> bool: + return any(connection.raddr[1:] == (port,) for connection in psutil.Process(pid).net_connections(kind="tcp")) + + +def _workers_calling_upstream(rig: ChaosRig) -> frozenset[int]: + port: Final = int(rig.upstream.url.rsplit(":", 1)[1]) + return frozenset(pid for pid in rig.owned.worker_pids() if _holds_a_connection_to(pid, port)) + + +def _counted(samples: Sequence[Sample], cell: str) -> tuple[float, float, float]: + return ( + sum(values(samples, FAILURES, model_id=identity(cell))), + sum(values(samples, TOTALS, model_id=identity(cell))), + sum(values(samples, LLM_FAILED, model_id=identity(cell))), + ) + + +def test_a_burst_of_provider_401s_and_proxy_rejects_across_two_workers_counts_only_the_provider_401s( + gateway: Gateway, tmp_path: Path +) -> None: + with _rig(gateway, tmp_path) as rig: + rig.release.set() + workers: Final = eventually(rig.owned.worker_pids, lambda pids: len(pids) == 2) + invalid: Final = f"sk-not-a-virtual-key-{uuid.uuid4().hex}" + calls: Final[tuple[tuple[str, str, str | None], ...]] = tuple( + (ENDPOINTS[index % len(ENDPOINTS)], name("burst"), None) for index in range(BURST) + ) + tuple(("chat", name("invalid-key"), invalid) for _ in range(BURST)) + + def call(cell: str, model: str, key: str | None) -> int: + return _status(rig.owned.gateway, cell, model, key) + + with ThreadPoolExecutor(max_workers=8) as pool: + statuses: Final = tuple(pool.map(call, *zip(*calls, strict=True))) + assert statuses == (401,) * (2 * BURST), statuses + assert len(rig.upstream.drain()) == BURST + samples: Final = eventually( + lambda: scrape(rig.owned.gateway), + lambda observed: _counted(observed, "burst") == (BURST, BURST, BURST), + seconds=70, + return_last_on_timeout=True, + ) + assert _counted(samples, "burst") == (BURST, BURST, BURST), (workers, _counted(samples, "burst")) + assert set(values(samples, STATE, model_id=identity("burst"))) == {1.0} + assert values(samples, FAILURES, requested_model=name("invalid-key")) == [] + assert values(samples, LLM_FAILED, model=name("invalid-key")) == [] + + +def test_a_worker_killed_while_provider_401s_are_in_flight_loses_no_answered_failure( + gateway: Gateway, tmp_path: Path +) -> None: + with _rig(gateway, tmp_path) as rig: + eventually(rig.owned.worker_pids, lambda pids: len(pids) == 2) + with ThreadPoolExecutor(max_workers=8) as pool: + futures: Final = tuple(pool.submit(_status, rig.owned.gateway, "chat", name("held")) for _ in range(BURST)) + eventually(lambda: rig.upstream.received.qsize() >= 8, bool, seconds=30) + victim: Final = min(eventually(lambda: _workers_calling_upstream(rig), bool)) + with rig.owned.replacing_worker(victim) as kill: + kill() + rig.release.set() + statuses: Final = tuple(future.result() for future in futures) + reached: Final = len(rig.upstream.drain()) + answered: Final = statuses.count(401) + lost: Final = statuses.count(-1) + assert answered + lost == BURST and lost > 0, statuses + samples: Final = eventually( + lambda: scrape(rig.owned.gateway), + lambda observed: answered <= _counted(observed, "held")[0] <= reached, + seconds=70, + return_last_on_timeout=True, + ) + counted: Final = _counted(samples, "held") + assert answered <= counted[0] <= reached and counted[0] == counted[1] == counted[2], (statuses, counted) + follow_up: Final = _status(rig.owned.gateway, "chat", name("held")) + assert follow_up == 401 + recounted: Final = eventually( + lambda: _counted(scrape(rig.owned.gateway), "held"), + lambda observed: observed[0] == counted[0] + 1, + seconds=70, + ) + assert recounted == (counted[0] + 1,) * 3 diff --git a/tests/integration/sdk/test_prometheus_copilot_session_auth_failure_sdk.py b/tests/integration/sdk/test_prometheus_copilot_session_auth_failure_sdk.py new file mode 100644 index 00000000000..1b5e990fe41 --- /dev/null +++ b/tests/integration/sdk/test_prometheus_copilot_session_auth_failure_sdk.py @@ -0,0 +1,99 @@ +"""A provider 401 on a caller's own per-user GitHub Copilot session is the caller's credential failing, so the +shared Copilot deployment keeps no failure, request or outage series for it, while a provider 401 on the router +deployment's own key, on a key a router caller passes or on the key a direct SDK call brings is counted as a failed +request, the router caller's key against its own one-off deployment.""" + +from __future__ import annotations + +import json +from collections.abc import Iterator +from typing import Final + +import pytest +from integration._support.copilot_session_prometheus_worker import ( + CALLER_SESSION_TOKEN, + COPILOT_DEPLOYMENT, + DEPLOYMENT_SERIES, + DIRECT_CALL, + DIRECT_KEY, + FAILURES, + LLM_FAILED, + OPERATOR_DEPLOYMENT, + OPERATOR_KEY, + ROUTER_CALLER_KEY, + STATE, + TOTALS, + Outcome, + WorkerReport, + run_copilot_session_worker, +) +from integration._support.wire import Reply, Request, wire_server + + +@pytest.fixture(scope="module") +def ran() -> Iterator[tuple[WorkerReport, tuple[Request, ...]]]: + def reject(request: Request) -> Reply: + assert request.method == "POST", request.method + return Reply( + status=401, + body=json.dumps({"error": {"message": "bad credentials", "type": "authentication_error"}}).encode(), + ) + + with wire_server(reject) as upstream: + report: Final = run_copilot_session_worker(upstream.url) + yield report, upstream.drain() + + +def test_every_call_reaches_the_provider_with_its_own_credential_and_fails_with_its_401( + ran: tuple[WorkerReport, tuple[Request, ...]], +) -> None: + report, received = ran + assert report.outcomes == ( + Outcome(deployment=COPILOT_DEPLOYMENT, status=401), + Outcome(deployment=OPERATOR_DEPLOYMENT, status=401), + Outcome(deployment=OPERATOR_DEPLOYMENT, status=401), + Outcome(deployment=DIRECT_CALL, status=401), + ) + assert [r.headers.get("authorization") for r in received] == [ + f"Bearer {CALLER_SESSION_TOKEN}", + f"Bearer {OPERATOR_KEY}", + f"Bearer {ROUTER_CALLER_KEY}", + f"Bearer {DIRECT_KEY}", + ] + + +def test_a_provider_401_on_a_callers_copilot_session_stays_out_of_the_shared_deployment_metrics( + ran: tuple[WorkerReport, tuple[Request, ...]], +) -> None: + report, _ = ran + assert {s.metric for s in report.series if s.model_id == COPILOT_DEPLOYMENT} & DEPLOYMENT_SERIES == set() + + +def test_a_provider_401_on_the_deployments_own_key_counts_as_a_deployment_failure( + ran: tuple[WorkerReport, tuple[Request, ...]], +) -> None: + report, _ = ran + assert report.values(FAILURES, OPERATOR_DEPLOYMENT) == (1.0,) + assert report.values(TOTALS, OPERATOR_DEPLOYMENT) == (1.0,) + assert report.values(LLM_FAILED, OPERATOR_DEPLOYMENT) == (1.0,) + assert report.on_the_endpoint(STATE, OPERATOR_DEPLOYMENT) == (1.0,) + + +def test_a_provider_401_on_the_key_a_direct_sdk_call_brings_is_counted_as_a_failed_request( + ran: tuple[WorkerReport, tuple[Request, ...]], +) -> None: + report, _ = ran + assert report.outside_the_router(FAILURES) == (1.0,) + assert report.outside_the_router(TOTALS) == (1.0,) + assert report.outside_the_router(LLM_FAILED) == (1.0,) + + +def test_a_provider_401_on_a_key_a_router_caller_passes_counts_against_its_own_one_off_deployment( + ran: tuple[WorkerReport, tuple[Request, ...]], +) -> None: + report, _ = ran + assert report.on_a_one_off_deployment(FAILURES) == (1.0,) + assert report.on_a_one_off_deployment(TOTALS) == (1.0,) + assert report.on_a_one_off_deployment(LLM_FAILED) == (1.0,) + assert report.values(FAILURES, OPERATOR_DEPLOYMENT) == (1.0,) + assert report.values(TOTALS, OPERATOR_DEPLOYMENT) == (1.0,) diff --git a/tests/unit/integrations/test_prometheus_invalid_key_filtering.py b/tests/unit/integrations/test_prometheus_invalid_key_filtering.py index 9e8348e860a..453fd28636d 100644 --- a/tests/unit/integrations/test_prometheus_invalid_key_filtering.py +++ b/tests/unit/integrations/test_prometheus_invalid_key_filtering.py @@ -2,19 +2,63 @@ Unit tests for Prometheus invalid API key request filtering. Tests the 401 detection helpers, that LLM-level metrics skip invalid API key -requests, and that the proxy-level failed request counter still records them. +requests rejected at the proxy gate while recording a provider's 401, and that +the proxy-level failed request counter still records them. """ +from collections.abc import Iterator +from datetime import datetime +from typing import Final from unittest.mock import Mock, patch import pytest from fastapi import HTTPException from prometheus_client import REGISTRY +from prometheus_client.samples import Sample +import litellm +from litellm.constants import LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL from litellm.integrations.prometheus import PrometheusLogger +from litellm.llms.github_copilot.per_user_auth import GithubCopilotUserSession from litellm.proxy._types import ProxyErrorTypes, ProxyException, UserAPIKeyAuth +PROVIDER_CREDENTIAL_FIELDS = [ + "aws_access_key_id", + "aws_secret_access_key", + "aws_session_token", + "aws_web_identity_token", + "azure_ad_token", + "azure_password", + "azure_scope", + "azure_username", + "client_id", + "client_secret", + "gigachat_access_token", + "oci_fingerprint", + "oci_key", + "oci_key_file", + "oci_tenancy", + "oci_user", + "tenant_id", + "token", + "user_config", + "vertex_ai_credentials", + "vertex_credentials", + "watsonx_credentials", + "wx_credentials", + "zen_api_key", +] +PROVIDER_ENDPOINT_FIELDS = [ + "aws_bedrock_runtime_endpoint", + "aws_sts_endpoint", + "deployment_url", + "s3_endpoint_url", + "sagemaker_base_url", +] +CALLED_THE_PROVIDER: Final = {"api_call_start_time": datetime(2026, 10, 19, 12, 0, 0)} + + @pytest.fixture(scope="function") def prometheus_logger(): """Create a PrometheusLogger instance for testing.""" @@ -48,18 +92,13 @@ class TestExtractStatusCode: (ExceptionWithStatusCode, 401, 401), ], ) - def test_extract_from_exception( - self, prometheus_logger, exception_class, code_value, expected - ): + def test_extract_from_exception(self, prometheus_logger, exception_class, code_value, expected): exception = exception_class(code_value) assert prometheus_logger._extract_status_code(exception=exception) == expected def test_extract_from_kwargs(self, prometheus_logger): exception = ExceptionWithCode("401") - assert ( - prometheus_logger._extract_status_code(kwargs={"exception": exception}) - == 401 - ) + assert prometheus_logger._extract_status_code(kwargs={"exception": exception}) == 401 def test_extract_from_enum_values(self, prometheus_logger): enum_values = Mock(status_code="401") @@ -79,50 +118,271 @@ class TestInvalidAPIKeyDetection: ], ) def test_status_code_detection(self, prometheus_logger, status_code, expected): - assert ( - prometheus_logger._is_invalid_api_key_request(status_code=status_code) - == expected - ) + assert prometheus_logger._is_invalid_api_key_request(status_code=status_code) == expected def test_auth_error_message_detection(self, prometheus_logger): exception = AssertionError( "LiteLLM Virtual Key expected. Received=invalid-key-12345, expected to start with 'sk-'." ) - assert ( - prometheus_logger._is_invalid_api_key_request( - status_code=None, exception=exception - ) - is True - ) + assert prometheus_logger._is_invalid_api_key_request(status_code=None, exception=exception) is True def test_non_auth_exception_not_detected(self, prometheus_logger): exception = ValueError("Some other error") - assert ( - prometheus_logger._is_invalid_api_key_request( - status_code=None, exception=exception - ) - is False - ) + assert prometheus_logger._is_invalid_api_key_request(status_code=None, exception=exception) is False class TestSkipMetricsValidation: """Test high-level validation method that orchestrates detection and extraction.""" - def test_skip_for_401_exception(self, prometheus_logger): - """Test full flow: extraction -> detection -> skip decision.""" - exception = ExceptionWithCode("401") - assert ( - prometheus_logger._should_skip_metrics_for_invalid_key(exception=exception) - is True - ) + @pytest.mark.parametrize( + "exception,proxy_gate,expected", + [ + (ExceptionWithCode("401"), True, True), + (AssertionError("expected to start with 'sk-'"), True, True), + (ExceptionWithStatusCode(429), True, False), + (ExceptionWithCode("401"), False, True), + (AssertionError("expected to start with 'sk-'"), False, True), + ( + litellm.AuthenticationError( + message="Incorrect API key provided: sk-rotat*****", + llm_provider="openai", + model="gpt-4o-mini", + ), + False, + False, + ), + ( + litellm.AuthenticationError( + message="API key not valid. Please pass a valid API key.", + llm_provider="gemini", + model="gemini-2.5-flash", + ), + False, + False, + ), + ( + litellm.AuthenticationError( + message="Authentication Error, Invalid proxy server token passed.", + llm_provider="openai", + model="gpt-4o-mini", + ), + True, + True, + ), + ( + litellm.CallerCredentialAuthenticationError( + message="GitHub Copilot connection is missing for this user", + llm_provider="github_copilot", + model="gpt-4o", + ), + False, + True, + ), + ( + HTTPException(status_code=401, detail="caller did not present a token"), + False, + True, + ), + ( + litellm.BadRequestError( + message="API key not valid. Please pass a valid API key.", + llm_provider="gemini", + model="gemini-2.5-flash", + ), + False, + False, + ), + ], + ids=[ + "proxy-gate-401", + "proxy-gate-auth-message", + "proxy-gate-429", + "unmarked-proxy-401", + "unmarked-auth-message", + "provider-401", + "provider-auth-message", + "proxy-gate-litellm-auth-error", + "caller-credential-401", + "unmarked-http-exception-401", + "provider-400-auth-message", + ], + ) + def test_skip_except_for_provider_errors_the_proxy_did_not_raise( + self, prometheus_logger, exception, proxy_gate, expected + ): + kwargs: Final[dict[str, object]] = {"exception": exception, **CALLED_THE_PROVIDER} + if proxy_gate: + kwargs[LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL] = True + assert prometheus_logger._should_skip_metrics_for_invalid_key(kwargs=kwargs) is expected - def test_skip_for_auth_error_message(self, prometheus_logger): - """Test full flow: exception message -> detection -> skip decision.""" - exception = AssertionError("expected to start with 'sk-'") - assert ( - prometheus_logger._should_skip_metrics_for_invalid_key(exception=exception) - is True + @pytest.mark.parametrize( + "logged_call,expected", + [ + ({"litellm_params": {"proxy_server_request": {"caller_credential_fields": ("api_key",)}}}, True), + ( + { + "litellm_params": { + "github_copilot_user_session": GithubCopilotUserSession( + token="caller-session-token", api_base="https://api.githubcopilot.com" + ) + } + }, + True, + ), + ({"standard_logging_object": {"metadata": {"used_client_oauth_token": True}}}, True), + ({"litellm_params": {"proxy_server_request": {"caller_credential_fields": ("headers",)}}}, True), + ( + { + "litellm_params": { + "proxy_server_request": {"caller_credential_fields": ("provider_specific_header",)} + } + }, + True, + ), + ({"litellm_params": {"proxy_server_request": {"caller_credential_fields": ()}}}, False), + ({"litellm_params": {"proxy_server_request": {"caller_credential_fields": "api_key"}}}, False), + ({"standard_logging_object": {"metadata": {"used_client_oauth_token": False}}}, False), + ({"litellm_params": {"proxy_server_request": {"body": {"azure_ad_token": "caller-token"}}}}, True), + ( + { + "litellm_params": { + "proxy_server_request": {"body": {"extra_body": {"azure_ad_token": "caller-token"}}} + } + }, + True, + ), + ( + { + "litellm_params": { + "azure_ad_token": "deployment-token", + "proxy_server_request": {"body": {"model": "azure-deployment"}}, + } + }, + False, + ), + ({"litellm_params": {"proxy_server_request": {"body": {"extra_body": "azure_ad_token"}}}}, False), + ( + { + "litellm_params": { + "proxy_server_request": {"body": {"litellm_credential_name": "caller-credential"}} + } + }, + True, + ), + ( + { + "litellm_params": { + "litellm_credential_name": "deployment-credential", + "proxy_server_request": {"body": {"model": "openai-deployment"}}, + } + }, + False, + ), + ({"litellm_params": {"proxy_server_request": {"caller_credential_fields": ("extra_headers",)}}}, True), + ({"litellm_params": {"proxy_server_request": {"caller_credential_fields": ("organization",)}}}, True), + ( + { + "litellm_params": { + "proxy_server_request": {"credential_fields": ("headers",), "caller_credential_fields": ()} + } + }, + False, + ), + ( + { + "litellm_params": { + "proxy_server_request": {"body": {"extra_headers": {"Authorization": "Bearer sk-caller"}}} + } + }, + False, + ), + ], + ids=[ + "caller-supplied-api-key", + "caller-copilot-session", + "caller-anthropic-oauth-token", + "caller-supplied-headers", + "caller-supplied-provider-specific-header", + "no-caller-credential-fields", + "malformed-credential-fields", + "deployment-anthropic-key", + "caller-supplied-azure-ad-token", + "caller-supplied-azure-ad-token-in-extra-body", + "deployment-azure-ad-token", + "malformed-extra-body", + "caller-named-credential", + "deployment-named-credential", + "caller-supplied-extra-headers", + "caller-supplied-organization", + "headers-that-cannot-change-provider-auth", + "extra-headers-not-stamped-by-the-proxy", + ], + ) + def test_skip_a_provider_401_on_a_credential_the_caller_owns(self, prometheus_logger, logged_call, expected): + exception: Final = litellm.AuthenticationError( + message="Incorrect API key provided: sk-calle*****", + llm_provider="openai", + model="gpt-4o-mini", ) + kwargs: Final = {"exception": exception, **CALLED_THE_PROVIDER, **logged_call} + assert prometheus_logger._should_skip_metrics_for_invalid_key(kwargs=kwargs) is expected + + @pytest.mark.parametrize( + "logged_call,expected", + [(CALLED_THE_PROVIDER, False), ({}, True), ({"api_call_start_time": None}, True)], + ids=["provider-401", "401-before-the-provider-call", "blank-provider-call-start"], + ) + def test_skip_a_401_raised_before_the_provider_was_called(self, prometheus_logger, logged_call, expected): + exception: Final = litellm.AuthenticationError( + message="Missing Anthropic API Key - A call is being made to anthropic but no key is set", + llm_provider="anthropic", + model="claude-haiku-4-5", + ) + kwargs: Final = {"exception": exception, **logged_call} + assert prometheus_logger._should_skip_metrics_for_invalid_key(kwargs=kwargs) is expected + + @pytest.mark.parametrize("field", PROVIDER_CREDENTIAL_FIELDS + PROVIDER_ENDPOINT_FIELDS) + @pytest.mark.parametrize("inside_extra_body", [False, True], ids=["body", "extra-body"]) + def test_skip_a_provider_401_on_a_provider_credential_field_the_caller_sent( + self, prometheus_logger, field, inside_extra_body + ): + sent: Final = {field: "caller-credential"} + body: Final = {"model": "shared-deployment", **({"extra_body": sent} if inside_extra_body else sent)} + kwargs: Final = { + "exception": litellm.AuthenticationError(message="Unauthorized", llm_provider="azure", model="gpt-4o"), + "litellm_params": {"proxy_server_request": {"body": body}}, + **CALLED_THE_PROVIDER, + } + assert prometheus_logger._should_skip_metrics_for_invalid_key(kwargs=kwargs) is True + + @pytest.mark.parametrize("field", PROVIDER_CREDENTIAL_FIELDS + PROVIDER_ENDPOINT_FIELDS) + def test_count_a_provider_401_on_a_provider_credential_field_the_deployment_owns(self, prometheus_logger, field): + kwargs: Final = { + "exception": litellm.AuthenticationError(message="Unauthorized", llm_provider="azure", model="gpt-4o"), + **CALLED_THE_PROVIDER, + "litellm_params": { + field: "deployment-credential", + "proxy_server_request": {"body": {"model": "shared-deployment"}}, + }, + } + assert prometheus_logger._should_skip_metrics_for_invalid_key(kwargs=kwargs) is False + + @pytest.mark.parametrize( + "token_exchange_endpoint,expected", + [("https://login.example.com/oauth2/v2.0/token", True), ("", False), (None, False)], + ids=["token-exchange-deployment", "blank-endpoint", "no-endpoint"], + ) + def test_skip_a_provider_401_on_a_token_exchange_deployment( + self, prometheus_logger, token_exchange_endpoint, expected + ): + kwargs: Final = { + "exception": litellm.AuthenticationError( + message="Unauthorized", llm_provider="microsoft_365_copilot", model="copilot" + ), + "litellm_params": {"token_exchange_endpoint": token_exchange_endpoint, "client_secret": "deployment"}, + **CALLED_THE_PROVIDER, + } + assert prometheus_logger._should_skip_metrics_for_invalid_key(kwargs=kwargs) is expected def test_no_skip_for_valid_request(self, prometheus_logger): assert prometheus_logger._should_skip_metrics_for_invalid_key() is False @@ -147,19 +407,13 @@ class TestAsyncHooks: ), ], ) - async def test_post_call_failure_hook_counts_401_without_key_hash( - self, prometheus_logger, exception - ): + async def test_post_call_failure_hook_counts_401_without_key_hash(self, prometheus_logger, exception): unauthenticated = UserAPIKeyAuth(request_route="/v1/chat/completions") unauthenticated.api_key = "notakeyatall" with ( - patch.object( - prometheus_logger, "litellm_proxy_failed_requests_metric" - ) as mock_failed, - patch.object( - prometheus_logger, "litellm_proxy_total_requests_metric" - ) as mock_total, + patch.object(prometheus_logger, "litellm_proxy_failed_requests_metric") as mock_failed, + patch.object(prometheus_logger, "litellm_proxy_total_requests_metric") as mock_total, ): await prometheus_logger.async_post_call_failure_hook( request_data={"model": "test-model"}, @@ -176,9 +430,7 @@ class TestAsyncHooks: mock_total.labels.return_value.inc.assert_called_once() @pytest.mark.asyncio - async def test_post_call_failure_hook_keeps_resolved_identity_labels_for_401( - self, prometheus_logger - ): + async def test_post_call_failure_hook_keeps_resolved_identity_labels_for_401(self, prometheus_logger): expired_key = UserAPIKeyAuth( api_key="sk-expired", key_alias="expired-alias", @@ -191,9 +443,7 @@ class TestAsyncHooks: code=401, ) - with patch.object( - prometheus_logger, "litellm_proxy_failed_requests_metric" - ) as mock_failed: + with patch.object(prometheus_logger, "litellm_proxy_failed_requests_metric") as mock_failed: await prometheus_logger.async_post_call_failure_hook( request_data={"model": "test-model"}, original_exception=exception, @@ -207,7 +457,7 @@ class TestAsyncHooks: assert failed_labels["team"] == "team-1" @pytest.mark.asyncio - async def test_log_failure_event_skips_401(self, prometheus_logger): + async def test_log_failure_event_skips_401_rejected_at_the_proxy_gate(self, prometheus_logger): exception = ExceptionWithCode("401") kwargs = { "model": "test-model", @@ -220,20 +470,91 @@ class TestAsyncHooks: }, "exception": exception, "litellm_params": {}, + LITELLM_LOGGING_NO_UPSTREAM_LLM_CALL: True, } with ( - patch.object( - prometheus_logger, "litellm_llm_api_failed_requests_metric" - ) as mock_failed, - patch.object( - prometheus_logger, "set_llm_deployment_failure_metrics" - ) as mock_deployment, + patch.object(prometheus_logger, "litellm_llm_api_failed_requests_metric") as mock_failed, + patch.object(prometheus_logger, "set_llm_deployment_failure_metrics") as mock_deployment, ): - await prometheus_logger.async_log_failure_event( kwargs=kwargs, response_obj=None, start_time=None, end_time=None ) mock_failed.labels.assert_not_called() mock_deployment.assert_not_called() + + +def _provider_auth_failure_kwargs() -> dict[str, object]: + exception: Final = litellm.AuthenticationError( + message="Incorrect API key provided: sk-rotat*****", + llm_provider="openai", + model="gpt-4o-mini", + ) + return { + "model": "gpt-4o-mini", + "standard_logging_object": { + "metadata": { + "user_api_key_hash": "test-key", + "user_api_key_alias": "test-alias", + "user_api_key_user_id": "test-user", + "user_api_key_team_id": "test-team", + "user_api_key_team_alias": "test-team-alias", + }, + "model_group": "rotated-credential", + "model_id": "deployment-1", + "api_base": "https://api.openai.com/v1", + "custom_llm_provider": "openai", + }, + "exception": exception, + "litellm_params": {"custom_llm_provider": "openai", "metadata": {}}, + **CALLED_THE_PROVIDER, + } + + +def _metric_values(name: str, model_id: str) -> list[float]: + return [ + sample.value + for sample in _registry_samples() + if sample.name == name and sample.labels.get("model_id") == model_id + ] + + +def _registry_samples() -> Iterator[Sample]: + for metric in REGISTRY.collect(): + yield from metric.samples + + +class TestProviderAuthFailures: + """A 401 raised by the provider is an upstream failure and is recorded.""" + + @pytest.mark.asyncio + async def test_log_failure_event_records_a_provider_401(self, prometheus_logger): + await prometheus_logger.async_log_failure_event( + kwargs=_provider_auth_failure_kwargs(), + response_obj=None, + start_time=None, + end_time=None, + ) + + assert _metric_values("litellm_llm_api_failed_requests_metric_total", "deployment-1") == [1.0] + assert _metric_values("litellm_deployment_failure_responses_total", "deployment-1") == [1.0] + assert _metric_values("litellm_deployment_state", "deployment-1") == [1.0] + + def test_deployment_failure_metrics_record_a_provider_401(self, prometheus_logger): + prometheus_logger.set_llm_deployment_failure_metrics(_provider_auth_failure_kwargs()) + + failures: Final = [ + sample for sample in _registry_samples() if sample.name == "litellm_deployment_failure_responses_total" + ] + assert [ + ( + sample.labels["model_id"], + sample.labels["exception_status"], + sample.labels["api_provider"], + sample.value, + ) + for sample in failures + ] == [("deployment-1", "401", "openai", 1.0)] + assert _metric_values("litellm_deployment_total_requests_total", "deployment-1") == [1.0] + assert _metric_values("litellm_deployment_state", "deployment-1") == [1.0] diff --git a/tests/unit/proxy/test_litellm_pre_call_utils.py b/tests/unit/proxy/test_litellm_pre_call_utils.py index ed7817bd660..e03fd9850c1 100644 --- a/tests/unit/proxy/test_litellm_pre_call_utils.py +++ b/tests/unit/proxy/test_litellm_pre_call_utils.py @@ -927,6 +927,222 @@ async def test_add_litellm_data_to_request_body_snapshot_excludes_proxy_server_r assert snapshot_body["messages"] == [{"role": "user", "content": "hello"}] +FORWARD_PROVIDER_AUTH_HEADERS: Final = { + "forward_llm_provider_auth_headers": True, + "forward_client_headers_to_llm_api": True, +} + + +@pytest.mark.asyncio +@pytest.mark.parametrize( + "sent,request_headers,general_settings,expected", + [ + ({"headers": {"Authorization": "Bearer sk-caller"}}, {}, {}, ("headers",)), + ({"headers": {"X-Trace-Id": "trace-1"}}, {}, {}, ("headers",)), + ({"headers": {}}, {}, {}, ()), + ({"extra_headers": {"API-Key": "caller-azure-key"}}, {}, {}, ("extra_headers",)), + ({"extra_headers": {"OpenAI-Project": "proj_caller"}}, {}, {}, ("extra_headers",)), + ( + {"provider_specific_header": {"custom_llm_provider": "openai", "extra_headers": {"x-api-key": "caller"}}}, + {}, + {}, + ("provider_specific_header",), + ), + ( + { + "provider_specific_header": [ + {"custom_llm_provider": "anthropic", "extra_headers": {"anthropic-beta": "tools"}}, + {"custom_llm_provider": "gemini", "extra_headers": {"X-Goog-Api-Key": "caller"}}, + ] + }, + {}, + {}, + ("provider_specific_header",), + ), + ( + { + "provider_specific_header": { + "custom_llm_provider": "anthropic", + "extra_headers": {"x-caller-trace": "x"}, + } + }, + {}, + {}, + ("provider_specific_header",), + ), + ( + { + "provider_specific_header": { + "custom_llm_provider": "anthropic", + "extra_headers": {"anthropic-version": "2023-06-01", "anthropic-beta": "tools-2024-04-04"}, + } + }, + {}, + {}, + (), + ), + ({"headers": {"Anthropic-Version": "2023-06-01"}}, {}, {}, ()), + ({"organization": "org-caller"}, {}, {}, ("organization",)), + ({"headers": "authorization", "provider_specific_header": "x-api-key"}, {}, {}, ()), + ( + {"api_key": "sk-caller", "headers": {"Ocp-Apim-Subscription-Key": "caller"}}, + {}, + {}, + ("api_key", "headers"), + ), + ({}, {"anthropic-beta": "tools-2024-04-04"}, {}, ()), + ({}, {"anthropic-version": "2023-06-01", "anthropic-beta": "tools-2024-04-04"}, {}, ()), + ({}, {"openai-organization": "org-caller"}, {"forward_openai_org_id": True}, ("organization",)), + ( + {}, + {"x-litellm-api-key": "sk-virtual", "authorization": "Bearer sk-ant-oat01-caller"}, + {}, + ("provider_specific_header",), + ), + ( + {}, + {"authorization": "Bearer sk-virtual", "x-goog-api-key": "AIza-caller"}, + FORWARD_PROVIDER_AUTH_HEADERS, + ("headers",), + ), + ( + {}, + {"authorization": "Bearer sk-virtual", "x-portkey-api-key": "caller-gateway-key"}, + FORWARD_PROVIDER_AUTH_HEADERS, + ("headers",), + ), + ({}, {"authorization": "Bearer sk-virtual"}, FORWARD_PROVIDER_AUTH_HEADERS, ()), + ], + ids=[ + "authorization-in-headers", + "plain-headers", + "empty-headers", + "api-key-in-extra-headers", + "openai-project-in-extra-headers", + "credential-in-provider-specific-header", + "credential-in-one-provider-specific-header-entry", + "plain-provider-specific-header", + "anthropic-version-and-beta-in-provider-specific-header", + "anthropic-version-in-headers", + "organization", + "malformed-header-fields", + "api-key-and-credential-headers", + "proxy-forwarded-anthropic-beta", + "proxy-forwarded-anthropic-sdk-headers", + "proxy-forwarded-openai-organization", + "proxy-forwarded-anthropic-oauth-token", + "proxy-forwarded-provider-auth-header", + "proxy-forwarded-gateway-key", + "proxy-forwarding-nothing", + ], +) +async def test_caller_credential_fields_name_every_field_that_carries_a_caller_header_or_credential( + sent: dict[str, object], + request_headers: dict[str, str], + general_settings: dict[str, object], + expected: tuple[str, ...], +) -> None: + updated: Final = await _request_data_added_by_the_proxy(sent, request_headers, general_settings) + + assert updated["proxy_server_request"]["caller_credential_fields"] == expected + + +@pytest.mark.asyncio +@pytest.mark.parametrize( + "request_headers,expected", + [({}, ()), ({"x-caller-trace": "trace-1"}, ("headers",))], + ids=["user-information-only", "user-information-and-caller-header"], +) +async def test_caller_credential_fields_ignore_the_user_information_the_proxy_adds_to_forwarded_headers( + monkeypatch: pytest.MonkeyPatch, request_headers: dict[str, str], expected: tuple[str, ...] +) -> None: + monkeypatch.setattr(litellm, "add_user_information_to_llm_headers", True) + + updated: Final = await _request_data_added_by_the_proxy({}, request_headers, FORWARD_PROVIDER_AUTH_HEADERS) + + assert updated["headers"]["x-litellm-user_api_key_user_id"] == "test-user" + assert updated["proxy_server_request"]["caller_credential_fields"] == expected + + +@pytest.mark.asyncio +@pytest.mark.parametrize( + "sent,request_headers,general_settings,expected", + [ + ({"headers": {"Anthropic-Version": "2023-06-01"}}, {}, {}, ("headers",)), + ( + { + "provider_specific_header": { + "custom_llm_provider": "anthropic", + "extra_headers": {"anthropic-version": "2023-06-01"}, + } + }, + {}, + {}, + ("provider_specific_header",), + ), + ({"organization": "org-caller"}, {}, {}, ()), + ({"extra_headers": {"API-Key": "caller-azure-key"}}, {}, {}, ()), + ( + {"api_key": "sk-caller", "headers": {"Ocp-Apim-Subscription-Key": "caller"}}, + {}, + {}, + ("api_key", "headers"), + ), + ({}, {"openai-organization": "org-caller"}, {"forward_openai_org_id": True}, ()), + ( + {}, + {"authorization": "Bearer sk-virtual", "x-goog-api-key": "AIza-caller"}, + FORWARD_PROVIDER_AUTH_HEADERS, + (), + ), + ], + ids=[ + "anthropic-version-in-headers", + "anthropic-version-in-provider-specific-header", + "organization", + "api-key-in-extra-headers", + "api-key-and-credential-headers", + "proxy-forwarded-openai-organization", + "proxy-forwarded-provider-auth-header", + ], +) +async def test_credential_fields_name_the_stripped_fields_the_caller_sent( + sent: dict[str, object], + request_headers: dict[str, str], + general_settings: dict[str, object], + expected: tuple[str, ...], +) -> None: + updated: Final = await _request_data_added_by_the_proxy(sent, request_headers, general_settings) + + assert updated["proxy_server_request"]["credential_fields"] == expected + + +async def _request_data_added_by_the_proxy( + sent: dict[str, object], request_headers: dict[str, str], general_settings: dict[str, object] +) -> dict: + from litellm.proxy.litellm_pre_call_utils import add_litellm_data_to_request + + request_mock: Final = MagicMock(spec=Request) + request_mock.url = MagicMock() + request_mock.url.__str__.return_value = "http://localhost/v1/chat/completions" + request_mock.url.path = "/v1/chat/completions" + request_mock.method = "POST" + request_mock.query_params = {} + request_mock.headers = {"content-type": "application/json", **request_headers} + request_mock.client = MagicMock() + request_mock.client.host = "127.0.0.1" + data: Final = {"model": "gpt-4o-mini", "messages": [{"role": "user", "content": "hello"}], **sent} + + return await add_litellm_data_to_request( + data=data, + request=request_mock, + user_api_key_dict=UserAPIKeyAuth(api_key="hashed-key", user_id="test-user"), + proxy_config=MagicMock(), + general_settings=dict(general_settings), + version="test-version", + ) + + def test_initial_snapshot_refresh_clears_a_previous_guardrail_checkpoint() -> None: from litellm.integrations.shadow_eval_logger import GuardrailRequestSnapshot from litellm.litellm_core_utils.litellm_logging import Logging From 11779b260e4f6ef6fdd7e7add735baef4fd10e3b Mon Sep 17 00:00:00 2001 From: tin-berri Date: Mon, 26 Oct 2026 20:58:27 -0400 Subject: [PATCH 027/262] fix(ui): include endpoint-qualified models in Decisions Playground (#48504) --- .../playground/llm_calls/system_one.test.ts | 21 ++++++++++++++++++- .../playground/llm_calls/system_one.ts | 12 ++++++++--- .../src/lib/decisionModels.ts | 2 +- 3 files changed, 30 insertions(+), 5 deletions(-) diff --git a/ui/litellm-dashboard/src/app/(dashboard)/playground/llm_calls/system_one.test.ts b/ui/litellm-dashboard/src/app/(dashboard)/playground/llm_calls/system_one.test.ts index 90e9482c89c..6fb1f8c8b8d 100644 --- a/ui/litellm-dashboard/src/app/(dashboard)/playground/llm_calls/system_one.test.ts +++ b/ui/litellm-dashboard/src/app/(dashboard)/playground/llm_calls/system_one.test.ts @@ -207,18 +207,37 @@ describe("fetchDecisionModels", () => { vi.unstubAllGlobals(); }); - it("lists the key's decision models from the proxy that answers the request, sorted by name", async () => { + it("lists the key's models with decision modes or endpoints from the request proxy, sorted by name", async () => { mockFetch.mockResolvedValueOnce( modelGroupInfo([ { model_group: "pplx-decider", mode: "evaluation" }, { model_group: "gpt-5.5", mode: "chat" }, { model_group: "jev-latest", mode: "evaluation" }, { model_group: "unknown-mode", mode: null }, + { model_group: "native-decision", mode: "decisions" }, + { + model_group: "chat-decisions", + mode: "chat", + supported_endpoints: ["/v1/chat/completions", "/v1/decisions"], + }, + { model_group: "chat-systemone", mode: "chat", supported_endpoints: ["/v1/systemone"] }, + { model_group: "custom-decision", mode: "custom", supported_endpoints: ["/v1/decisions"] }, + { model_group: "endpoint-only", supported_endpoints: ["/v1/decisions"] }, + { model_group: "chat-only", mode: "chat", supported_endpoints: ["/v1/chat/completions"] }, + { model_group: "no-endpoints", mode: "chat", supported_endpoints: [] }, + { model_group: "null-endpoints", mode: "chat", supported_endpoints: null }, + { model_group: "missing-mode" }, + { model_group: "custom-mode", mode: "custom" }, ]), ); await expect(fetchDecisionModels("virtual-key", "https://custom.example.com/")).resolves.toEqual([ + "chat-decisions", + "chat-systemone", + "custom-decision", + "endpoint-only", "jev-latest", + "native-decision", "pplx-decider", ]); expect(mockFetch).toHaveBeenCalledWith( diff --git a/ui/litellm-dashboard/src/app/(dashboard)/playground/llm_calls/system_one.ts b/ui/litellm-dashboard/src/app/(dashboard)/playground/llm_calls/system_one.ts index a4030029903..035a05729ba 100644 --- a/ui/litellm-dashboard/src/app/(dashboard)/playground/llm_calls/system_one.ts +++ b/ui/litellm-dashboard/src/app/(dashboard)/playground/llm_calls/system_one.ts @@ -2,7 +2,7 @@ import { z } from "zod"; import { getGatewayBaseUrl, getGlobalLitellmHeaderName, getProxyBaseUrl } from "@/components/networking"; import { withRequiredHeaders } from "@/components/llm_calls/request_headers"; import { createApiClient } from "@/lib/http/client"; -import { isDecisionMode } from "@/lib/decisionModels"; +import { isDecisionEntry } from "@/lib/decisionModels"; import { systemOneResponseSchema, type PlaygroundRequest, @@ -26,7 +26,13 @@ export type PlaygroundDecisionRequest = | { endpoint: "/v1/decisions"; payload: OpenAIDecisionsRequest }; const modelGroupInfoSchema = z.object({ - data: z.array(z.object({ model_group: z.string(), mode: z.string().nullish() })), + data: z.array( + z.object({ + model_group: z.string(), + mode: z.string().nullish(), + supported_endpoints: z.array(z.string()).nullish(), + }), + ), }); function proxyClient(customBaseUrl?: string, getDefaultBaseUrl: () => string = getProxyBaseUrl) { @@ -56,7 +62,7 @@ export async function fetchDecisionModels( }); return modelGroupInfoSchema .parse(body) - .data.filter((group) => isDecisionMode(group.mode)) + .data.filter(isDecisionEntry) .map((group) => group.model_group) .sort((a, b) => a.localeCompare(b)); } diff --git a/ui/litellm-dashboard/src/lib/decisionModels.ts b/ui/litellm-dashboard/src/lib/decisionModels.ts index 1808b13c62b..15c632fe055 100644 --- a/ui/litellm-dashboard/src/lib/decisionModels.ts +++ b/ui/litellm-dashboard/src/lib/decisionModels.ts @@ -38,7 +38,7 @@ export const displayMode = (mode: string | null | undefined): string | undefined export const expandModeFilterValues = (modes: readonly string[]): readonly string[] => modes.flatMap((mode) => (mode === DECISIONS_MODE ? DECISION_MODE_VALUES : [mode])); -const isDecisionEntry = (entry: CostMapEntry): boolean => +export const isDecisionEntry = (entry: Pick): boolean => isDecisionMode(entry.mode) || (entry.supported_endpoints ?? []).some((endpoint) => DECISION_ENDPOINTS.has(endpoint)); const parsedEntries = (costMap: unknown): ReadonlyArray => { From 45183428a54043186a401e419b8c0b09df682169 Mon Sep 17 00:00:00 2001 From: tin-berri Date: Mon, 26 Oct 2026 21:00:39 -0400 Subject: [PATCH 028/262] feat(ui): persist model group alias display ordering (#48500) --- ui/litellm-dashboard/eslint-suppressions.json | 3 - .../ModelGroupAliasPanel.integration.test.tsx | 1 + .../panels/ModelGroupAliasPanel.tsx | 5 +- .../model_group_alias_ordering.test.ts | 76 ++++++ .../components/model_group_alias_ordering.ts | 57 +++++ ..._group_alias_settings.integration.test.tsx | 218 ++++++++++++++++++ .../model_group_alias_settings.test.tsx | 66 ------ .../components/model_group_alias_settings.tsx | 186 ++++++++++++++- 8 files changed, 533 insertions(+), 79 deletions(-) create mode 100644 ui/litellm-dashboard/src/components/model_group_alias_ordering.test.ts create mode 100644 ui/litellm-dashboard/src/components/model_group_alias_ordering.ts create mode 100644 ui/litellm-dashboard/src/components/model_group_alias_settings.integration.test.tsx delete mode 100644 ui/litellm-dashboard/src/components/model_group_alias_settings.test.tsx diff --git a/ui/litellm-dashboard/eslint-suppressions.json b/ui/litellm-dashboard/eslint-suppressions.json index 32777b43504..724c49eb3b3 100644 --- a/ui/litellm-dashboard/eslint-suppressions.json +++ b/ui/litellm-dashboard/eslint-suppressions.json @@ -1730,9 +1730,6 @@ "src/components/model_group_alias_settings.tsx": { "local/filename-pascal-case": { "count": 1 - }, - "react-hooks/set-state-in-effect": { - "count": 1 } }, "src/components/model_info_view.tsx": { diff --git a/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/panels/ModelGroupAliasPanel.integration.test.tsx b/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/panels/ModelGroupAliasPanel.integration.test.tsx index 227a34335a3..36a9f92dfd4 100644 --- a/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/panels/ModelGroupAliasPanel.integration.test.tsx +++ b/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/panels/ModelGroupAliasPanel.integration.test.tsx @@ -10,6 +10,7 @@ vi.mock("@/app/(dashboard)/hooks/useAuthorized", () => ({ vi.mock("@/components/networking", () => ({ getCallbacksCall: vi.fn(), + getProxyBaseUrl: () => "https://proxy.test", getRouterSettingsCall: vi.fn(), setCallbacksCall: vi.fn(), })); diff --git a/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/panels/ModelGroupAliasPanel.tsx b/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/panels/ModelGroupAliasPanel.tsx index 025923e08e9..e6c720f38cf 100644 --- a/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/panels/ModelGroupAliasPanel.tsx +++ b/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/panels/ModelGroupAliasPanel.tsx @@ -2,7 +2,7 @@ import { useEffect, useState } from "react"; import ModelGroupAliasSettings from "@/components/model_group_alias_settings"; -import { getCallbacksCall, getRouterSettingsCall } from "@/components/networking"; +import { getCallbacksCall, getProxyBaseUrl, getRouterSettingsCall } from "@/components/networking"; import useAuthorized from "@/app/(dashboard)/hooks/useAuthorized"; export default function ModelGroupAliasPanel() { @@ -22,6 +22,7 @@ export default function ModelGroupAliasPanel() { : null; const managedByConfig = currentAliasOwnership?.managedByConfig ?? false; const ownershipLoading = Boolean(accessToken && !currentAliasOwnership); + const preferenceScope = userID ? JSON.stringify([getProxyBaseUrl(), userID]) : null; useEffect(() => { if (!accessToken) { @@ -62,6 +63,8 @@ export default function ModelGroupAliasPanel() { return ( ({ + id: aliasName, + aliasName, + targetModelGroup, +}); +const names = (aliases: readonly AliasItem[]): string[] => aliases.map((alias) => alias.aliasName); + +describe("orderAliases", () => { + const aliases = Object.freeze([row("Zebra", "alpha10"), row("alpha10", "beta"), row("alpha2", "Alpha2")]); + + it.each<{ sortBy: AliasDisplayPreferences["sortBy"]; descending: boolean; expected: string[] }>([ + { sortBy: "aliasName", descending: false, expected: ["alpha2", "alpha10", "Zebra"] }, + { sortBy: "aliasName", descending: true, expected: ["Zebra", "alpha10", "alpha2"] }, + { sortBy: "targetModelGroup", descending: false, expected: ["alpha2", "Zebra", "alpha10"] }, + { sortBy: "targetModelGroup", descending: true, expected: ["alpha10", "Zebra", "alpha2"] }, + ])("sorts $sortBy with descending=$descending without changing the input", ({ sortBy, descending, expected }) => { + expect(names(orderAliases(aliases, { ...DEFAULT_ALIAS_DISPLAY, sortBy, descending }))).toEqual(expected); + expect(names(aliases)).toEqual(["Zebra", "alpha10", "alpha2"]); + }); + + it.each([false, true])( + "breaks equal-target ties by alias name regardless of input order, descending=%s", + (descending) => { + const tied = [row("beta", "shared"), row("Alpha", "SHARED"), row("gamma", "shared")]; + const preferences: AliasDisplayPreferences = { ...DEFAULT_ALIAS_DISPLAY, sortBy: "targetModelGroup", descending }; + expect(names(orderAliases(tied, preferences))).toEqual(["Alpha", "beta", "gamma"]); + expect(names(orderAliases([...tied].reverse(), preferences))).toEqual(["Alpha", "beta", "gamma"]); + }, + ); + + it.each([ + { descending: false, remaining: ["alpha", "beta", "subscription/a", "subscription/c"] }, + { descending: true, remaining: ["beta", "alpha", "subscription/c", "subscription/a"] }, + ])("keeps ordered pins first and alias-prefix matches last, descending=$descending", ({ descending, remaining }) => { + const grouped = [ + row("subscription/c", "c"), + row("beta", "b"), + row("ordinary", "y"), + row("subscription/a", "a"), + row("alpha", "subscription/x"), + row("subscription/z", "z"), + ]; + const preferences = { + ...DEFAULT_ALIAS_DISPLAY, + descending, + pinned: ["missing", "subscription/z", "ordinary"], + lastPrefix: "subscription/", + }; + expect(names(orderAliases(grouped, preferences))).toEqual(["subscription/z", "ordinary", ...remaining]); + }); +}); + +describe("movePinnedAlias", () => { + const pinned = Object.freeze(["first", "middle", "last"]); + + it.each<{ name: string; direction: -1 | 1; expected: string[] }>([ + { name: "middle", direction: -1, expected: ["middle", "first", "last"] }, + { name: "middle", direction: 1, expected: ["first", "last", "middle"] }, + { name: "first", direction: -1, expected: ["first", "middle", "last"] }, + { name: "last", direction: 1, expected: ["first", "middle", "last"] }, + { name: "missing", direction: -1, expected: ["first", "middle", "last"] }, + { name: "missing", direction: 1, expected: ["first", "middle", "last"] }, + ])("moves $name in direction $direction without changing the input", ({ name, direction, expected }) => { + expect(movePinnedAlias(pinned, name, direction)).toEqual(expected); + expect(pinned).toEqual(["first", "middle", "last"]); + }); +}); diff --git a/ui/litellm-dashboard/src/components/model_group_alias_ordering.ts b/ui/litellm-dashboard/src/components/model_group_alias_ordering.ts new file mode 100644 index 00000000000..cbec78b63cb --- /dev/null +++ b/ui/litellm-dashboard/src/components/model_group_alias_ordering.ts @@ -0,0 +1,57 @@ +import { z } from "zod"; +import { storageKey } from "@/lib/storage"; + +export interface AliasItem { + id: string; + aliasName: string; + targetModelGroup: string; +} + +const aliasDisplayFields = { + sortBy: z.enum(["aliasName", "targetModelGroup"]), + descending: z.boolean(), + pinned: z.array(z.string()).transform((names) => [...new Set(names)]), + lastPrefix: z.string(), +}; +const aliasDisplaySchema = z.object(aliasDisplayFields); + +export type AliasDisplayPreferences = z.infer; + +export const DEFAULT_ALIAS_DISPLAY: AliasDisplayPreferences = { + sortBy: "aliasName", + descending: false, + pinned: [], + lastPrefix: "", +}; + +export const aliasDisplayStorage = (scope: string) => + storageKey("local", `litellm_alias_display_v1_${scope}`, aliasDisplaySchema, DEFAULT_ALIAS_DISPLAY); + +const alphabetical = new Intl.Collator(undefined, { numeric: true, sensitivity: "base" }); + +export function orderAliases(aliases: readonly AliasItem[], preferences: AliasDisplayPreferences): AliasItem[] { + const ranks = new Map(preferences.pinned.map((name, index) => [name, index])); + const group = (name: string): number => { + if (ranks.has(name)) return 0; + return preferences.lastPrefix && name.startsWith(preferences.lastPrefix) ? 2 : 1; + }; + return [...aliases].sort((a, b) => { + const groupDifference = group(a.aliasName) - group(b.aliasName); + if (groupDifference) return groupDifference; + if (ranks.has(a.aliasName) && ranks.has(b.aliasName)) { + return ranks.get(a.aliasName)! - ranks.get(b.aliasName)!; + } + const fieldDifference = alphabetical.compare(a[preferences.sortBy], b[preferences.sortBy]); + return fieldDifference * (preferences.descending ? -1 : 1) || a.aliasName.localeCompare(b.aliasName); + }); +} + +export function movePinnedAlias(pinned: readonly string[], name: string, direction: -1 | 1): string[] { + const index = pinned.indexOf(name); + const target = index + direction; + if (index < 0 || target < 0 || target >= pinned.length) return [...pinned]; + return pinned.map((value, position) => { + if (position === index) return pinned[target]; + return position === target ? name : value; + }); +} diff --git a/ui/litellm-dashboard/src/components/model_group_alias_settings.integration.test.tsx b/ui/litellm-dashboard/src/components/model_group_alias_settings.integration.test.tsx new file mode 100644 index 00000000000..816f5629567 --- /dev/null +++ b/ui/litellm-dashboard/src/components/model_group_alias_settings.integration.test.tsx @@ -0,0 +1,218 @@ +/* @vitest-environment jsdom */ +import { act, fireEvent, render, screen, within } from "@testing-library/react"; +import userEvent from "@testing-library/user-event"; +import { afterEach, beforeEach, describe, expect, it, vi } from "vitest"; +import { setCallbacksCall } from "@/components/networking"; +import { aliasDisplayStorage } from "./model_group_alias_ordering"; +import ModelGroupAliasSettings from "./model_group_alias_settings"; + +vi.mock("@/components/networking", () => ({ + setCallbacksCall: vi.fn(), +})); + +const BLOCKED_STORAGE = { + getItem: () => null, + setItem: () => { + throw new Error("storage blocked"); + }, +}; + +const aliases = { + "fast-model": "claude-haiku", + "smart-model": { model: "claude-sonnet", hidden: true }, +}; + +const displayAliases = { + zeta: "standard", + "subscription/zeta": "standard", + tester: "standard", + alpha: "subscription/fast", + reviewer: { model: "subscription/reasoning", hidden: true }, + "subscription/alpha": "standard", +}; + +const rowNames = () => + within(screen.getByRole("table")) + .getAllByRole("row") + .slice(1) + .map((row) => within(row).getAllByRole("cell")[0].textContent); + +describe("ModelGroupAliasSettings", () => { + beforeEach(() => { + vi.clearAllMocks(); + localStorage.clear(); + vi.mocked(setCallbacksCall).mockResolvedValue({}); + }); + + afterEach(() => { + vi.restoreAllMocks(); + vi.unstubAllGlobals(); + }); + + it("locks config-owned aliases while keeping their names and targets visible", async () => { + render( + , + ); + + expect( + screen.getByText( + "These aliases are defined in config.yaml and are read-only here. Edit the config file to change them.", + ), + ).toBeInTheDocument(); + expect(screen.getByPlaceholderText("e.g., gpt-4o")).toBeDisabled(); + expect(screen.getByPlaceholderText("e.g., gpt-4o-mini-openai")).toBeDisabled(); + expect(screen.getByRole("button", { name: "Add Alias" })).toBeDisabled(); + expect(screen.getByRole("button", { name: "Edit alias fast-model" })).toBeDisabled(); + expect(screen.getByRole("button", { name: "Delete alias fast-model" })).toBeDisabled(); + expect(screen.getByRole("button", { name: "Edit alias smart-model" })).toBeDisabled(); + expect(screen.getByRole("button", { name: "Delete alias smart-model" })).toBeDisabled(); + + expect(await screen.findByText("fast-model")).toBeInTheDocument(); + expect(screen.getByText("claude-haiku")).toBeInTheDocument(); + expect(screen.getByText("smart-model")).toBeInTheDocument(); + expect(screen.getByText("claude-sonnet")).toBeInTheDocument(); + + await userEvent.setup().click(screen.getByRole("button", { name: "Delete alias fast-model" })); + expect(setCallbacksCall).not.toHaveBeenCalled(); + }); + + it("keeps aliases editable by default and saves the current string representation after delete", async () => { + const user = userEvent.setup(); + render( + , + ); + + expect(await screen.findByText("fast-model")).toBeInTheDocument(); + expect(screen.getByRole("button", { name: "Edit alias fast-model" })).toBeEnabled(); + expect(screen.getByRole("button", { name: "Delete alias fast-model" })).toBeEnabled(); + + await user.click(screen.getByRole("button", { name: "Delete alias fast-model" })); + + expect(setCallbacksCall).toHaveBeenCalledWith("test-token", { + router_settings: { model_group_alias: { "smart-model": "claude-sonnet" } }, + }); + }); + + it("keeps ordered pins above sorted groups across remounts without changing routing", async () => { + const user = userEvent.setup(); + const originalAliases = structuredClone(displayAliases); + const props = { + preferenceScope: "test-user-proxy", + accessToken: "test-token", + initialModelGroupAlias: displayAliases, + managedByConfig: true, + }; + const view = render(); + + await user.click(screen.getByRole("button", { name: "Pin alias tester" })); + await user.click(screen.getByRole("button", { name: "Pin alias reviewer" })); + await user.click(screen.getByRole("button", { name: "Move reviewer up" })); + fireEvent.change(screen.getByLabelText("Place aliases with this prefix last"), { + target: { value: "subscription/" }, + }); + expect(rowNames()).toEqual(["reviewer", "tester", "alpha", "zeta", "subscription/alpha", "subscription/zeta"]); + + await user.click(screen.getByRole("button", { name: "Alias Name" })); + expect(rowNames()).toEqual(["reviewer", "tester", "zeta", "alpha", "subscription/zeta", "subscription/alpha"]); + expect(screen.getByRole("columnheader", { name: "Alias Name" })).toHaveAttribute("aria-sort", "descending"); + await user.click(screen.getByRole("button", { name: "Target Model Group" })); + expect(rowNames()).toEqual(["reviewer", "tester", "zeta", "alpha", "subscription/alpha", "subscription/zeta"]); + await user.click(screen.getByRole("button", { name: "Target Model Group" })); + expect(rowNames()).toEqual(["reviewer", "tester", "alpha", "zeta", "subscription/alpha", "subscription/zeta"]); + view.unmount(); + render(); + expect(rowNames()).toEqual(["reviewer", "tester", "alpha", "zeta", "subscription/alpha", "subscription/zeta"]); + expect(screen.getByLabelText("Place aliases with this prefix last")).toHaveValue("subscription/"); + expect(screen.getByRole("button", { name: "Move reviewer up" })).toBeDisabled(); + expect(setCallbacksCall).not.toHaveBeenCalled(); + expect(displayAliases).toEqual(originalAliases); + + await user.click(screen.getByRole("button", { name: "Reset display order" })); + expect(rowNames()).toEqual(["alpha", "reviewer", "subscription/alpha", "subscription/zeta", "tester", "zeta"]); + expect(screen.getByRole("columnheader", { name: "Alias Name" })).toHaveAttribute("aria-sort", "ascending"); + }); + + it.each([false, true])( + "preserves pins through loading and successful edits (storage blocked: %s)", + async (blocked) => { + if (blocked) vi.stubGlobal("localStorage", BLOCKED_STORAGE); + const user = userEvent.setup(); + const props = { preferenceScope: "test-user-proxy", accessToken: "test-token" }; + const view = render(); + await user.click(screen.getByRole("button", { name: "Pin alias tester" })); + view.rerender(); + view.rerender(); + expect(rowNames()[0]).toBe("tester"); + await user.click(screen.getByRole("button", { name: "Edit alias tester" })); + const editRow = screen.getByRole("row", { name: /Save Cancel$/ }); + fireEvent.change(within(editRow).getAllByRole("textbox")[0], { target: { value: "renamed" } }); + vi.spyOn(console, "error").mockImplementation(() => {}); + vi.mocked(setCallbacksCall).mockRejectedValueOnce(new Error("save failed")); + await user.click(screen.getByRole("button", { name: "Save" })); + await user.click(screen.getByRole("button", { name: "Cancel" })); + expect(screen.getByRole("button", { name: "Unpin alias tester" })).toBeInTheDocument(); + + await user.click(screen.getByRole("button", { name: "Edit alias tester" })); + const retryRow = screen.getByRole("row", { name: /Save Cancel$/ }); + fireEvent.change(within(retryRow).getAllByRole("textbox")[0], { target: { value: "renamed" } }); + const pendingSave = Promise.withResolvers(); + vi.mocked(setCallbacksCall).mockReturnValueOnce(pendingSave.promise); + await user.click(screen.getByRole("button", { name: "Save" })); + fireEvent.change(screen.getByLabelText("Place aliases with this prefix last"), { + target: { value: "subscription/" }, + }); + await act(async () => pendingSave.resolve()); + expect(screen.getByLabelText("Place aliases with this prefix last")).toHaveValue("subscription/"); + expect(rowNames()[0]).toBe("renamed"); + expect(screen.getByRole("button", { name: "Unpin alias renamed" })).toBeInTheDocument(); + await user.click(screen.getByRole("button", { name: "Delete alias renamed" })); + fireEvent.change(screen.getByPlaceholderText("e.g., gpt-4o"), { target: { value: "renamed" } }); + fireEvent.change(screen.getByPlaceholderText("e.g., gpt-4o-mini-openai"), { target: { value: "standard" } }); + await user.click(screen.getByRole("button", { name: "Add Alias" })); + expect(rowNames()[0]).toBe("alpha"); + expect(screen.getByRole("button", { name: "Pin alias renamed" })).toBeInTheDocument(); + }, + ); + + it("falls back from corrupt preferences and isolates preferences by scope", async () => { + const user = userEvent.setup(); + localStorage.setItem(aliasDisplayStorage("test-user-proxy").name, '{"sortBy":"unknown"}'); + const props = { accessToken: "test-token", initialModelGroupAlias: displayAliases }; + const view = render(); + expect(rowNames()[0]).toBe("alpha"); + await user.click(screen.getByRole("button", { name: "Pin alias tester" })); + view.rerender(); + expect(rowNames()[0]).toBe("alpha"); + view.rerender(); + expect(rowNames()[0]).toBe("tester"); + view.rerender(); + expect(screen.getByRole("button", { name: "Pin alias tester" })).toBeDisabled(); + }); + + it("keeps display changes usable when browser storage refuses writes", async () => { + const user = userEvent.setup(); + vi.stubGlobal("localStorage", BLOCKED_STORAGE); + render( + , + ); + await user.click(screen.getByRole("button", { name: "Pin alias tester" })); + expect(rowNames()[0]).toBe("tester"); + expect(screen.getByRole("status")).toHaveTextContent("could not be saved"); + await user.click(screen.getByRole("button", { name: "Unpin alias tester" })); + expect(rowNames()[0]).toBe("alpha"); + expect(setCallbacksCall).not.toHaveBeenCalled(); + }); +}); diff --git a/ui/litellm-dashboard/src/components/model_group_alias_settings.test.tsx b/ui/litellm-dashboard/src/components/model_group_alias_settings.test.tsx deleted file mode 100644 index fe59e6eb139..00000000000 --- a/ui/litellm-dashboard/src/components/model_group_alias_settings.test.tsx +++ /dev/null @@ -1,66 +0,0 @@ -/* @vitest-environment jsdom */ -import { render, screen } from "@testing-library/react"; -import userEvent from "@testing-library/user-event"; -import { afterEach, beforeEach, describe, expect, it, vi } from "vitest"; -import { setCallbacksCall } from "@/components/networking"; -import ModelGroupAliasSettings from "./model_group_alias_settings"; - -vi.mock("@/components/networking", () => ({ - setCallbacksCall: vi.fn(), -})); - -const aliases = { - "fast-model": "claude-haiku", - "smart-model": { model: "claude-sonnet", hidden: true }, -}; - -describe("ModelGroupAliasSettings", () => { - beforeEach(() => { - vi.clearAllMocks(); - vi.mocked(setCallbacksCall).mockResolvedValue({}); - }); - - afterEach(() => { - vi.restoreAllMocks(); - }); - - it("locks config-owned aliases while keeping their names and targets visible", async () => { - render(); - - expect( - screen.getByText( - "These aliases are defined in config.yaml and are read-only here. Edit the config file to change them.", - ), - ).toBeInTheDocument(); - expect(screen.getByPlaceholderText("e.g., gpt-4o")).toBeDisabled(); - expect(screen.getByPlaceholderText("e.g., gpt-4o-mini-openai")).toBeDisabled(); - expect(screen.getByRole("button", { name: "Add Alias" })).toBeDisabled(); - expect(screen.getByRole("button", { name: "Edit alias fast-model" })).toBeDisabled(); - expect(screen.getByRole("button", { name: "Delete alias fast-model" })).toBeDisabled(); - expect(screen.getByRole("button", { name: "Edit alias smart-model" })).toBeDisabled(); - expect(screen.getByRole("button", { name: "Delete alias smart-model" })).toBeDisabled(); - - expect(await screen.findByText("fast-model")).toBeInTheDocument(); - expect(screen.getByText("claude-haiku")).toBeInTheDocument(); - expect(screen.getByText("smart-model")).toBeInTheDocument(); - expect(screen.getByText("claude-sonnet")).toBeInTheDocument(); - - await userEvent.setup().click(screen.getByRole("button", { name: "Delete alias fast-model" })); - expect(setCallbacksCall).not.toHaveBeenCalled(); - }); - - it("keeps aliases editable by default and saves the current string representation after delete", async () => { - const user = userEvent.setup(); - render(); - - expect(await screen.findByText("fast-model")).toBeInTheDocument(); - expect(screen.getByRole("button", { name: "Edit alias fast-model" })).toBeEnabled(); - expect(screen.getByRole("button", { name: "Delete alias fast-model" })).toBeEnabled(); - - await user.click(screen.getByRole("button", { name: "Delete alias fast-model" })); - - expect(setCallbacksCall).toHaveBeenCalledWith("test-token", { - router_settings: { model_group_alias: { "smart-model": "claude-sonnet" } }, - }); - }); -}); diff --git a/ui/litellm-dashboard/src/components/model_group_alias_settings.tsx b/ui/litellm-dashboard/src/components/model_group_alias_settings.tsx index d3cebc76e98..4a5e7fce9ba 100644 --- a/ui/litellm-dashboard/src/components/model_group_alias_settings.tsx +++ b/ui/litellm-dashboard/src/components/model_group_alias_settings.tsx @@ -1,9 +1,30 @@ -import React, { useState, useEffect } from "react"; +import React, { useState, useEffect, useMemo, useRef } from "react"; +import { + ColumnDef, + TableOptions, + Updater, + functionalUpdate, + getCoreRowModel, + useReactTable, +} from "@tanstack/react-table"; +import { ArrowDown, ArrowUp, Pin, PinOff } from "lucide-react"; import { PlusCircleIcon, PencilIcon, TrashIcon, ChevronDownIcon, ChevronRightIcon } from "@heroicons/react/outline"; import { setCallbacksCall } from "./networking"; import { Card, CardTitle } from "@/components/ui/card"; import { Table, TableBody, TableCell, TableHead, TableHeader, TableRow } from "@/components/ui/table"; import { toast } from "@/lib/toast"; +import { readStorage, useStoredValue } from "@/lib/storage"; +import { DataTableSortHeader } from "@/components/shared/DataTable/DataTableSortHeader"; +import { Button } from "@/components/ui/button"; +import { Input } from "@/components/ui/input"; +import { + AliasDisplayPreferences, + AliasItem, + aliasDisplayStorage, + DEFAULT_ALIAS_DISPLAY, + movePinnedAlias, + orderAliases, +} from "./model_group_alias_ordering"; type ModelGroupAliasValue = string | { model: string; hidden?: boolean }; @@ -13,12 +34,30 @@ interface ModelGroupAliasSettingsProps { onAliasUpdate?: (updatedAlias: { [key: string]: string }) => void; managedByConfig?: boolean; ownershipLoading?: boolean; + preferenceScope: string | null; } -interface AliasItem { - id: string; - aliasName: string; - targetModelGroup: string; +const ALIAS_COLUMNS: ColumnDef[] = [ + { accessorKey: "aliasName", sortDescFirst: false }, + { accessorKey: "targetModelGroup", sortDescFirst: false }, +]; + +function useAliasDisplayPreferences(preferenceScope: string | null) { + const preferenceKey = useMemo(() => aliasDisplayStorage(preferenceScope ?? ""), [preferenceScope]); + const [storedPreferences, storePreferences] = useStoredValue(preferenceKey); + const [unsavedPreferences, setUnsavedPreferences] = useState(null); + const unsavedRef = useRef(null); + const preferences = preferenceScope === null ? DEFAULT_ALIAS_DISPLAY : unsavedPreferences ?? storedPreferences; + const updatePreferences = (updater: Updater) => { + if (preferenceScope === null) return; + const next = functionalUpdate(updater, unsavedRef.current ?? readStorage(preferenceKey)); + storePreferences(next); + const saved = JSON.stringify(readStorage(preferenceKey)) === JSON.stringify(next); + // rebind-ok: Async saves need the latest fallback when browser storage refuses writes. + unsavedRef.current = saved ? null : next; + setUnsavedPreferences(unsavedRef.current); + }; + return { preferences, updatePreferences, unsavedPreferences }; } const ModelGroupAliasSettings: React.FC = ({ @@ -27,12 +66,39 @@ const ModelGroupAliasSettings: React.FC = ({ onAliasUpdate, managedByConfig = false, ownershipLoading = false, + preferenceScope, }) => { + "use no memo"; + const [aliases, setAliases] = useState([]); const [newAlias, setNewAlias] = useState({ aliasName: "", targetModelGroup: "" }); const [editingAlias, setEditingAlias] = useState(null); const writesDisabled = managedByConfig || ownershipLoading; const [isExpanded, setIsExpanded] = useState(true); + const { preferences, updatePreferences, unsavedPreferences } = useAliasDisplayPreferences(preferenceScope); + const displayAliases = useMemo(() => orderAliases(aliases, preferences), [aliases, preferences]); + const visiblePins = preferences.pinned.filter((name) => aliases.some((alias) => alias.aliasName === name)); + const sorting = [{ id: preferences.sortBy, desc: preferences.descending }]; + const tableOptions: TableOptions = { + data: displayAliases, + columns: ALIAS_COLUMNS, + getCoreRowModel: getCoreRowModel(), + manualSorting: true, + enableSorting: preferenceScope !== null, + enableSortingRemoval: false, + enableMultiSort: false, + state: { sorting }, + onSortingChange: (updater) => { + const selected = functionalUpdate(updater, sorting)[0]; + updatePreferences({ + ...preferences, + sortBy: selected?.id === "targetModelGroup" ? "targetModelGroup" : "aliasName", + descending: selected?.desc ?? false, + }); + }, + }; + const table = useReactTable(tableOptions); + const sortDirection = preferences.descending ? "descending" : "ascending"; useEffect(() => { const aliasArray = Object.entries(initialModelGroupAlias).map(([aliasName, value], index) => ({ @@ -128,8 +194,15 @@ const ModelGroupAliasSettings: React.FC = ({ } const updatedAliases = aliases.map((alias) => (alias.id === editingAlias.id ? editingAlias : alias)); + const originalName = aliases.find((alias) => alias.id === editingAlias.id)?.aliasName; if (await saveAliasesToBackend(updatedAliases)) { + if (originalName !== editingAlias.aliasName) { + updatePreferences((current) => ({ + ...current, + pinned: current.pinned.map((name) => (name === originalName ? editingAlias.aliasName : name)), + })); + } setAliases(updatedAliases); setEditingAlias(null); toast.success("Alias updated successfully"); @@ -144,8 +217,13 @@ const ModelGroupAliasSettings: React.FC = ({ if (writesDisabled) return; const updatedAliases = aliases.filter((alias) => alias.id !== aliasId); + const deletedName = aliases.find((alias) => alias.id === aliasId)?.aliasName; if (await saveAliasesToBackend(updatedAliases)) { + updatePreferences((current) => ({ + ...current, + pinned: current.pinned.filter((name) => name !== deletedName), + })); setAliases(updatedAliases); toast.success("Alias deleted successfully"); } @@ -235,18 +313,57 @@ const ModelGroupAliasSettings: React.FC = ({

Manage Existing Aliases

+
+
+ + updatePreferences({ ...preferences, lastPrefix: event.target.value })} + /> +
+ +
+

+ {unsavedPreferences + ? "Display order could not be saved in this browser. Your changes apply until you leave this page." + : "Display preferences are saved for your account in this browser. Pinned aliases stay first in your chosen order."} +

- Alias Name - Target Model Group + + + + + + + Display order Actions - {aliases.map((alias) => ( + {displayAliases.map((alias) => ( {editingAlias && !writesDisabled && editingAlias.id === alias.id ? ( <> @@ -276,6 +393,7 @@ const ModelGroupAliasSettings: React.FC = ({ className="w-full px-2 py-1 border border-border rounded-md text-sm" /> +
+ {visiblePins.includes(alias.aliasName) && + ([-1, 1] as const).map((direction) => ( + + ))} +
+